diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 7d435297..e0ca454d 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -59,6 +59,18 @@ body: - iOS - Android - Other/Cloud + - type: dropdown + id: device + attributes: + label: What device are you running WebUI on? + multiple: true + options: + - Nvidia GPUs (RTX 20 above) + - Nvidia GPUs (GTX 16 below) + - AMD GPUs (RX 6000 above) + - AMD GPUs (RX 5000 below) + - CPU + - Other GPUs - type: dropdown id: browsers attributes: diff --git a/.github/workflows/on_pull_request.yaml b/.github/workflows/on_pull_request.yaml index a168be5b..d42965b1 100644 --- a/.github/workflows/on_pull_request.yaml +++ b/.github/workflows/on_pull_request.yaml @@ -18,22 +18,29 @@ jobs: steps: - name: Checkout Code uses: actions/checkout@v3 - - name: Set up Python 3.10 - uses: actions/setup-python@v4 + - uses: actions/setup-python@v4 with: - python-version: 3.10.6 - cache: pip - cache-dependency-path: | - **/requirements*txt - - name: Install PyLint - run: | - python -m pip install --upgrade pip - pip install pylint - # This lets PyLint check to see if it can resolve imports - - name: Install dependencies - run: | - export COMMANDLINE_ARGS="--skip-torch-cuda-test --exit" - python launch.py - - name: Analysing the code with pylint - run: | - pylint $(git ls-files '*.py') + python-version: 3.11 + # NB: there's no cache: pip here since we're not installing anything + # from the requirements.txt file(s) in the repository; it's faster + # not to have GHA download an (at the time of writing) 4 GB cache + # of PyTorch and other dependencies. + - name: Install Ruff + run: pip install ruff==0.0.265 + - name: Run Ruff + run: ruff . + +# The rest are currently disabled pending fixing of e.g. installing the torch dependency. + +# - name: Install PyLint +# run: | +# python -m pip install --upgrade pip +# pip install pylint +# # This lets PyLint check to see if it can resolve imports +# - name: Install dependencies +# run: | +# export COMMANDLINE_ARGS="--skip-torch-cuda-test --exit" +# python launch.py +# - name: Analysing the code with pylint +# run: | +# pylint $(git ls-files '*.py') diff --git a/.github/workflows/run_tests.yaml b/.github/workflows/run_tests.yaml index 9a0b8d22..0708398b 100644 --- a/.github/workflows/run_tests.yaml +++ b/.github/workflows/run_tests.yaml @@ -17,8 +17,14 @@ jobs: cache: pip cache-dependency-path: | **/requirements*txt + launch.py - name: Run tests run: python launch.py --tests test --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test + env: + PIP_DISABLE_PIP_VERSION_CHECK: "1" + PIP_PROGRESS_BAR: "off" + TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu + WEBUI_LAUNCH_LIVE_OUTPUT: "1" - name: Upload main app stdout-stderr uses: actions/upload-artifact@v3 if: always() diff --git a/CHANGELOG.md b/CHANGELOG.md index d1727864..8cf444ca 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,16 @@ +## 1.2.1 + +### Features: + * add an option to always refer to lora by filenames + +### Bug Fixes: + * never refer to lora by an alias if multiple loras have same alias or the alias is called none + * fix upscalers disappearing after the user reloads UI + * allow bf16 in safe unpickler (resolves problems with loading some loras) + * allow web UI to be ran fully offline + * fix localizations not working + * fix error for loras: 'LatentDiffusion' object has no attribute 'lora_layer_mapping' + ## 1.2.0 ### Features: diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py index bc11cc6e..7f450086 100644 --- a/extensions-builtin/LDSR/ldsr_model_arch.py +++ b/extensions-builtin/LDSR/ldsr_model_arch.py @@ -88,7 +88,7 @@ class LDSR: x_t = None logs = None - for n in range(n_runs): + for _ in range(n_runs): if custom_shape is not None: x_t = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device) x_t = repeat(x_t, '1 c h w -> b c h w', b=custom_shape[0]) @@ -110,7 +110,6 @@ class LDSR: diffusion_steps = int(steps) eta = 1.0 - down_sample_method = 'Lanczos' gc.collect() if torch.cuda.is_available: @@ -131,11 +130,11 @@ class LDSR: im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS) else: print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)") - + # pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge')) - + logs = self.run(model["model"], im_padded, diffusion_steps, eta) sample = logs["sample"] @@ -158,7 +157,7 @@ class LDSR: def get_cond(selected_path): - example = dict() + example = {} up_f = 4 c = selected_path.convert('RGB') c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0) @@ -196,7 +195,7 @@ def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_s @torch.no_grad() def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize_x0=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None, corrector_kwargs=None, x_T=None, ddim_use_x0_pred=False): - log = dict() + log = {} z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key, return_first_stage_outputs=True, @@ -244,7 +243,7 @@ def make_convolutional_sample(batch, model, custom_steps=None, eta=1.0, quantize x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True) log["sample_noquant"] = x_sample_noquant log["sample_diff"] = torch.abs(x_sample_noquant - x_sample) - except: + except Exception: pass log["sample"] = x_sample diff --git a/extensions-builtin/LDSR/scripts/ldsr_model.py b/extensions-builtin/LDSR/scripts/ldsr_model.py index da19cff1..fbbe9005 100644 --- a/extensions-builtin/LDSR/scripts/ldsr_model.py +++ b/extensions-builtin/LDSR/scripts/ldsr_model.py @@ -7,7 +7,8 @@ from basicsr.utils.download_util import load_file_from_url from modules.upscaler import Upscaler, UpscalerData from ldsr_model_arch import LDSR from modules import shared, script_callbacks -import sd_hijack_autoencoder, sd_hijack_ddpm_v1 +import sd_hijack_autoencoder # noqa: F401 +import sd_hijack_ddpm_v1 # noqa: F401 class UpscalerLDSR(Upscaler): diff --git a/extensions-builtin/LDSR/sd_hijack_autoencoder.py b/extensions-builtin/LDSR/sd_hijack_autoencoder.py index 8e03c7f8..81c5101b 100644 --- a/extensions-builtin/LDSR/sd_hijack_autoencoder.py +++ b/extensions-builtin/LDSR/sd_hijack_autoencoder.py @@ -1,16 +1,21 @@ # The content of this file comes from the ldm/models/autoencoder.py file of the compvis/stable-diffusion repo # The VQModel & VQModelInterface were subsequently removed from ldm/models/autoencoder.py when we moved to the stability-ai/stablediffusion repo # As the LDSR upscaler relies on VQModel & VQModelInterface, the hijack aims to put them back into the ldm.models.autoencoder - +import numpy as np import torch import pytorch_lightning as pl import torch.nn.functional as F from contextlib import contextmanager + +from torch.optim.lr_scheduler import LambdaLR + +from ldm.modules.ema import LitEma from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer from ldm.modules.diffusionmodules.model import Encoder, Decoder from ldm.util import instantiate_from_config import ldm.models.autoencoder +from packaging import version class VQModel(pl.LightningModule): def __init__(self, @@ -19,7 +24,7 @@ class VQModel(pl.LightningModule): n_embed, embed_dim, ckpt_path=None, - ignore_keys=[], + ignore_keys=None, image_key="image", colorize_nlabels=None, monitor=None, @@ -57,7 +62,7 @@ class VQModel(pl.LightningModule): print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.") if ckpt_path is not None: - self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys) + self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or []) self.scheduler_config = scheduler_config self.lr_g_factor = lr_g_factor @@ -76,11 +81,11 @@ class VQModel(pl.LightningModule): if context is not None: print(f"{context}: Restored training weights") - def init_from_ckpt(self, path, ignore_keys=list()): + def init_from_ckpt(self, path, ignore_keys=None): sd = torch.load(path, map_location="cpu")["state_dict"] keys = list(sd.keys()) for k in keys: - for ik in ignore_keys: + for ik in ignore_keys or []: if k.startswith(ik): print("Deleting key {} from state_dict.".format(k)) del sd[k] @@ -165,7 +170,7 @@ class VQModel(pl.LightningModule): def validation_step(self, batch, batch_idx): log_dict = self._validation_step(batch, batch_idx) with self.ema_scope(): - log_dict_ema = self._validation_step(batch, batch_idx, suffix="_ema") + self._validation_step(batch, batch_idx, suffix="_ema") return log_dict def _validation_step(self, batch, batch_idx, suffix=""): @@ -232,7 +237,7 @@ class VQModel(pl.LightningModule): return self.decoder.conv_out.weight def log_images(self, batch, only_inputs=False, plot_ema=False, **kwargs): - log = dict() + log = {} x = self.get_input(batch, self.image_key) x = x.to(self.device) if only_inputs: @@ -249,7 +254,8 @@ class VQModel(pl.LightningModule): if plot_ema: with self.ema_scope(): xrec_ema, _ = self(x) - if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema) + if x.shape[1] > 3: + xrec_ema = self.to_rgb(xrec_ema) log["reconstructions_ema"] = xrec_ema return log @@ -264,7 +270,7 @@ class VQModel(pl.LightningModule): class VQModelInterface(VQModel): def __init__(self, embed_dim, *args, **kwargs): - super().__init__(embed_dim=embed_dim, *args, **kwargs) + super().__init__(*args, embed_dim=embed_dim, **kwargs) self.embed_dim = embed_dim def encode(self, x): @@ -282,5 +288,5 @@ class VQModelInterface(VQModel): dec = self.decoder(quant) return dec -setattr(ldm.models.autoencoder, "VQModel", VQModel) -setattr(ldm.models.autoencoder, "VQModelInterface", VQModelInterface) +ldm.models.autoencoder.VQModel = VQModel +ldm.models.autoencoder.VQModelInterface = VQModelInterface diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index 5c0488e5..631a08ef 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -48,7 +48,7 @@ class DDPMV1(pl.LightningModule): beta_schedule="linear", loss_type="l2", ckpt_path=None, - ignore_keys=[], + ignore_keys=None, load_only_unet=False, monitor="val/loss", use_ema=True, @@ -100,7 +100,7 @@ class DDPMV1(pl.LightningModule): if monitor is not None: self.monitor = monitor if ckpt_path is not None: - self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet) + self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet) self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) @@ -182,13 +182,13 @@ class DDPMV1(pl.LightningModule): if context is not None: print(f"{context}: Restored training weights") - def init_from_ckpt(self, path, ignore_keys=list(), only_model=False): + def init_from_ckpt(self, path, ignore_keys=None, only_model=False): sd = torch.load(path, map_location="cpu") if "state_dict" in list(sd.keys()): sd = sd["state_dict"] keys = list(sd.keys()) for k in keys: - for ik in ignore_keys: + for ik in ignore_keys or []: if k.startswith(ik): print("Deleting key {} from state_dict.".format(k)) del sd[k] @@ -375,7 +375,7 @@ class DDPMV1(pl.LightningModule): @torch.no_grad() def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs): - log = dict() + log = {} x = self.get_input(batch, self.first_stage_key) N = min(x.shape[0], N) n_row = min(x.shape[0], n_row) @@ -383,7 +383,7 @@ class DDPMV1(pl.LightningModule): log["inputs"] = x # get diffusion row - diffusion_row = list() + diffusion_row = [] x_start = x[:n_row] for t in range(self.num_timesteps): @@ -444,13 +444,13 @@ class LatentDiffusionV1(DDPMV1): conditioning_key = None ckpt_path = kwargs.pop("ckpt_path", None) ignore_keys = kwargs.pop("ignore_keys", []) - super().__init__(conditioning_key=conditioning_key, *args, **kwargs) + super().__init__(*args, conditioning_key=conditioning_key, **kwargs) self.concat_mode = concat_mode self.cond_stage_trainable = cond_stage_trainable self.cond_stage_key = cond_stage_key try: self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1 - except: + except Exception: self.num_downs = 0 if not scale_by_std: self.scale_factor = scale_factor @@ -460,7 +460,7 @@ class LatentDiffusionV1(DDPMV1): self.instantiate_cond_stage(cond_stage_config) self.cond_stage_forward = cond_stage_forward self.clip_denoised = False - self.bbox_tokenizer = None + self.bbox_tokenizer = None self.restarted_from_ckpt = False if ckpt_path is not None: @@ -792,7 +792,7 @@ class LatentDiffusionV1(DDPMV1): z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L ) # 2. apply model loop over last dim - if isinstance(self.first_stage_model, VQModelInterface): + if isinstance(self.first_stage_model, VQModelInterface): output_list = [self.first_stage_model.decode(z[:, :, :, :, i], force_not_quantize=predict_cids or force_not_quantize) for i in range(z.shape[-1])] @@ -877,16 +877,6 @@ class LatentDiffusionV1(DDPMV1): c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float())) return self.p_losses(x, c, t, *args, **kwargs) - def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset - def rescale_bbox(bbox): - x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2]) - y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3]) - w = min(bbox[2] / crop_coordinates[2], 1 - x0) - h = min(bbox[3] / crop_coordinates[3], 1 - y0) - return x0, y0, w, h - - return [rescale_bbox(b) for b in bboxes] - def apply_model(self, x_noisy, t, cond, return_ids=False): if isinstance(cond, dict): @@ -900,7 +890,7 @@ class LatentDiffusionV1(DDPMV1): if hasattr(self, "split_input_params"): assert len(cond) == 1 # todo can only deal with one conditioning atm - assert not return_ids + assert not return_ids ks = self.split_input_params["ks"] # eg. (128, 128) stride = self.split_input_params["stride"] # eg. (64, 64) @@ -1126,7 +1116,7 @@ class LatentDiffusionV1(DDPMV1): if cond is not None: if isinstance(cond, dict): cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else - list(map(lambda x: x[:batch_size], cond[key])) for key in cond} + [x[:batch_size] for x in cond[key]] for key in cond} else: cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size] @@ -1157,8 +1147,10 @@ class LatentDiffusionV1(DDPMV1): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(x0_partial) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) return img, intermediates @torch.no_grad() @@ -1205,8 +1197,10 @@ class LatentDiffusionV1(DDPMV1): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(img) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) if return_intermediates: return img, intermediates @@ -1221,7 +1215,7 @@ class LatentDiffusionV1(DDPMV1): if cond is not None: if isinstance(cond, dict): cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else - list(map(lambda x: x[:batch_size], cond[key])) for key in cond} + [x[:batch_size] for x in cond[key]] for key in cond} else: cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size] return self.p_sample_loop(cond, @@ -1253,7 +1247,7 @@ class LatentDiffusionV1(DDPMV1): use_ddim = ddim_steps is not None - log = dict() + log = {} z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key, return_first_stage_outputs=True, force_c_encode=True, @@ -1280,7 +1274,7 @@ class LatentDiffusionV1(DDPMV1): if plot_diffusion_rows: # get diffusion row - diffusion_row = list() + diffusion_row = [] z_start = z[:n_row] for t in range(self.num_timesteps): if t % self.log_every_t == 0 or t == self.num_timesteps - 1: @@ -1322,7 +1316,7 @@ class LatentDiffusionV1(DDPMV1): if inpaint: # make a simple center square - b, h, w = z.shape[0], z.shape[2], z.shape[3] + h, w = z.shape[2], z.shape[3] mask = torch.ones(N, h, w).to(self.device) # zeros will be filled in mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0. @@ -1424,10 +1418,10 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1): # TODO: move all layout-specific hacks to this class def __init__(self, cond_stage_key, *args, **kwargs): assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"' - super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs) + super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs) def log_images(self, batch, N=8, *args, **kwargs): - logs = super().log_images(batch=batch, N=N, *args, **kwargs) + logs = super().log_images(*args, batch=batch, N=N, **kwargs) key = 'train' if self.training else 'validation' dset = self.trainer.datamodule.datasets[key] @@ -1443,7 +1437,7 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1): logs['bbox_image'] = cond_img return logs -setattr(ldm.models.diffusion.ddpm, "DDPMV1", DDPMV1) -setattr(ldm.models.diffusion.ddpm, "LatentDiffusionV1", LatentDiffusionV1) -setattr(ldm.models.diffusion.ddpm, "DiffusionWrapperV1", DiffusionWrapperV1) -setattr(ldm.models.diffusion.ddpm, "Layout2ImgDiffusionV1", Layout2ImgDiffusionV1) +ldm.models.diffusion.ddpm.DDPMV1 = DDPMV1 +ldm.models.diffusion.ddpm.LatentDiffusionV1 = LatentDiffusionV1 +ldm.models.diffusion.ddpm.DiffusionWrapperV1 = DiffusionWrapperV1 +ldm.models.diffusion.ddpm.Layout2ImgDiffusionV1 = Layout2ImgDiffusionV1 diff --git a/extensions-builtin/Lora/lora.py b/extensions-builtin/Lora/lora.py index ba1293df..1308c48b 100644 --- a/extensions-builtin/Lora/lora.py +++ b/extensions-builtin/Lora/lora.py @@ -1,4 +1,3 @@ -import glob import os import re import torch @@ -133,6 +132,10 @@ def load_lora(name, filename): sd = sd_models.read_state_dict(filename) + # this should not be needed but is here as an emergency fix for an unknown error people are experiencing in 1.2.0 + if not hasattr(shared.sd_model, 'lora_layer_mapping'): + assign_lora_names_to_compvis_modules(shared.sd_model) + keys_failed_to_match = {} is_sd2 = 'model_transformer_resblocks' in shared.sd_model.lora_layer_mapping @@ -173,7 +176,7 @@ def load_lora(name, filename): else: print(f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}') continue - assert False, f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}' + raise AssertionError(f"Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}") with torch.no_grad(): module.weight.copy_(weight) @@ -185,7 +188,7 @@ def load_lora(name, filename): elif lora_key == "lora_down.weight": lora_module.down = module else: - assert False, f'Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha' + raise AssertionError(f"Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha") if len(keys_failed_to_match) > 0: print(f"Failed to match keys when loading Lora {filename}: {keys_failed_to_match}") @@ -203,7 +206,7 @@ def load_loras(names, multipliers=None): loaded_loras.clear() loras_on_disk = [available_lora_aliases.get(name, None) for name in names] - if any([x is None for x in loras_on_disk]): + if any(x is None for x in loras_on_disk): list_available_loras() loras_on_disk = [available_lora_aliases.get(name, None) for name in names] @@ -310,7 +313,7 @@ def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.Mu print(f'failed to calculate lora weights for layer {lora_layer_name}') - setattr(self, "lora_current_names", wanted_names) + self.lora_current_names = wanted_names def lora_forward(module, input, original_forward): @@ -344,8 +347,8 @@ def lora_forward(module, input, original_forward): def lora_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]): - setattr(self, "lora_current_names", ()) - setattr(self, "lora_weights_backup", None) + self.lora_current_names = () + self.lora_weights_backup = None def lora_Linear_forward(self, input): @@ -393,6 +396,8 @@ def lora_MultiheadAttention_load_state_dict(self, *args, **kwargs): def list_available_loras(): available_loras.clear() available_lora_aliases.clear() + forbidden_lora_aliases.clear() + forbidden_lora_aliases.update({"none": 1}) os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True) @@ -406,6 +411,9 @@ def list_available_loras(): available_loras[name] = entry + if entry.alias in available_lora_aliases: + forbidden_lora_aliases[entry.alias.lower()] = 1 + available_lora_aliases[name] = entry available_lora_aliases[entry.alias] = entry @@ -419,7 +427,7 @@ def infotext_pasted(infotext, params): added = [] - for k, v in params.items(): + for k in params: if not k.startswith("AddNet Model "): continue @@ -445,6 +453,7 @@ def infotext_pasted(infotext, params): available_loras = {} available_lora_aliases = {} +forbidden_lora_aliases = {} loaded_loras = [] list_available_loras() diff --git a/extensions-builtin/Lora/scripts/lora_script.py b/extensions-builtin/Lora/scripts/lora_script.py index 7db971fd..728e0b86 100644 --- a/extensions-builtin/Lora/scripts/lora_script.py +++ b/extensions-builtin/Lora/scripts/lora_script.py @@ -53,7 +53,8 @@ script_callbacks.on_infotext_pasted(lora.infotext_pasted) shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), { - "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in lora.available_loras]}, refresh=lora.list_available_loras), + "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None", *lora.available_loras]}, refresh=lora.list_available_loras), + "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}), })) diff --git a/extensions-builtin/Lora/ui_extra_networks_lora.py b/extensions-builtin/Lora/ui_extra_networks_lora.py index a0edbc1e..2050e3fa 100644 --- a/extensions-builtin/Lora/ui_extra_networks_lora.py +++ b/extensions-builtin/Lora/ui_extra_networks_lora.py @@ -15,13 +15,19 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): def list_items(self): for name, lora_on_disk in lora.available_loras.items(): path, ext = os.path.splitext(lora_on_disk.filename) + + if shared.opts.lora_preferred_name == "Filename" or lora_on_disk.alias.lower() in lora.forbidden_lora_aliases: + alias = name + else: + alias = lora_on_disk.alias + yield { "name": name, "filename": path, "preview": self.find_preview(path), "description": self.find_description(path), "search_term": self.search_terms_from_path(lora_on_disk.filename), - "prompt": json.dumps(f""), + "prompt": json.dumps(f""), "local_preview": f"{path}.{shared.opts.samples_format}", "metadata": json.dumps(lora_on_disk.metadata, indent=4) if lora_on_disk.metadata else None, } diff --git a/extensions-builtin/ScuNET/scripts/scunet_model.py b/extensions-builtin/ScuNET/scripts/scunet_model.py index c7fd5739..cc2cbc6a 100644 --- a/extensions-builtin/ScuNET/scripts/scunet_model.py +++ b/extensions-builtin/ScuNET/scripts/scunet_model.py @@ -10,10 +10,9 @@ from tqdm import tqdm from basicsr.utils.download_util import load_file_from_url import modules.upscaler -from modules import devices, modelloader +from modules import devices, modelloader, script_callbacks from scunet_model_arch import SCUNet as net from modules.shared import opts -from modules import images class UpscalerScuNET(modules.upscaler.Upscaler): @@ -133,8 +132,19 @@ class UpscalerScuNET(modules.upscaler.Upscaler): model = net(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64) model.load_state_dict(torch.load(filename), strict=True) model.eval() - for k, v in model.named_parameters(): + for _, v in model.named_parameters(): v.requires_grad = False model = model.to(device) return model + + +def on_ui_settings(): + import gradio as gr + from modules import shared + + shared.opts.add_option("SCUNET_tile", shared.OptionInfo(256, "Tile size for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")).info("0 = no tiling")) + shared.opts.add_option("SCUNET_tile_overlap", shared.OptionInfo(8, "Tile overlap for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, section=('upscaling', "Upscaling")).info("Low values = visible seam")) + + +script_callbacks.on_ui_settings(on_ui_settings) diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py index 43ca8d36..b51a8806 100644 --- a/extensions-builtin/ScuNET/scunet_model_arch.py +++ b/extensions-builtin/ScuNET/scunet_model_arch.py @@ -61,7 +61,9 @@ class WMSA(nn.Module): Returns: output: tensor shape [b h w c] """ - if self.type != 'W': x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + if self.type != 'W': + x = torch.roll(x, shifts=(-(self.window_size // 2), -(self.window_size // 2)), dims=(1, 2)) + x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size) h_windows = x.size(1) w_windows = x.size(2) @@ -85,8 +87,9 @@ class WMSA(nn.Module): output = self.linear(output) output = rearrange(output, 'b (w1 w2) (p1 p2) c -> b (w1 p1) (w2 p2) c', w1=h_windows, p1=self.window_size) - if self.type != 'W': output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), - dims=(1, 2)) + if self.type != 'W': + output = torch.roll(output, shifts=(self.window_size // 2, self.window_size // 2), dims=(1, 2)) + return output def relative_embedding(self): @@ -262,4 +265,4 @@ class SCUNet(nn.Module): nn.init.constant_(m.bias, 0) elif isinstance(m, nn.LayerNorm): nn.init.constant_(m.bias, 0) - nn.init.constant_(m.weight, 1.0) \ No newline at end of file + nn.init.constant_(m.weight, 1.0) diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index e8783bca..0ba50487 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -1,4 +1,3 @@ -import contextlib import os import numpy as np @@ -8,7 +7,7 @@ from basicsr.utils.download_util import load_file_from_url from tqdm import tqdm from modules import modelloader, devices, script_callbacks, shared -from modules.shared import cmd_opts, opts, state +from modules.shared import opts, state from swinir_model_arch import SwinIR as net from swinir_model_arch_v2 import Swin2SR as net2 from modules.upscaler import Upscaler, UpscalerData @@ -45,7 +44,7 @@ class UpscalerSwinIR(Upscaler): img = upscale(img, model) try: torch.cuda.empty_cache() - except: + except Exception: pass return img @@ -151,7 +150,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale): for w_idx in w_idx_list: if state.interrupted or state.skipped: break - + in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile] out_patch = model(in_patch) out_patch_mask = torch.ones_like(out_patch) diff --git a/extensions-builtin/SwinIR/swinir_model_arch.py b/extensions-builtin/SwinIR/swinir_model_arch.py index 863f42db..93b93274 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch.py +++ b/extensions-builtin/SwinIR/swinir_model_arch.py @@ -644,7 +644,7 @@ class SwinIR(nn.Module): """ def __init__(self, img_size=64, patch_size=1, in_chans=3, - embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6], + embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6), window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None, drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, norm_layer=nn.LayerNorm, ape=False, patch_norm=True, @@ -805,7 +805,7 @@ class SwinIR(nn.Module): def forward(self, x): H, W = x.shape[2:] x = self.check_image_size(x) - + self.mean = self.mean.type_as(x) x = (x - self.mean) * self.img_range @@ -844,7 +844,7 @@ class SwinIR(nn.Module): H, W = self.patches_resolution flops += H * W * 3 * self.embed_dim * 9 flops += self.patch_embed.flops() - for i, layer in enumerate(self.layers): + for layer in self.layers: flops += layer.flops() flops += H * W * 3 * self.embed_dim * self.embed_dim flops += self.upsample.flops() diff --git a/extensions-builtin/SwinIR/swinir_model_arch_v2.py b/extensions-builtin/SwinIR/swinir_model_arch_v2.py index 0e28ae6e..dad22cca 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch_v2.py +++ b/extensions-builtin/SwinIR/swinir_model_arch_v2.py @@ -74,7 +74,7 @@ class WindowAttention(nn.Module): """ def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0., - pretrained_window_size=[0, 0]): + pretrained_window_size=(0, 0)): super().__init__() self.dim = dim @@ -241,7 +241,7 @@ class SwinTransformerBlock(nn.Module): attn_mask = None self.register_buffer("attn_mask", attn_mask) - + def calculate_mask(self, x_size): # calculate attention mask for SW-MSA H, W = x_size @@ -263,7 +263,7 @@ class SwinTransformerBlock(nn.Module): attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2) attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0)) - return attn_mask + return attn_mask def forward(self, x, x_size): H, W = x_size @@ -288,7 +288,7 @@ class SwinTransformerBlock(nn.Module): attn_windows = self.attn(x_windows, mask=self.attn_mask) # nW*B, window_size*window_size, C else: attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device)) - + # merge windows attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C) shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H' W' C @@ -369,7 +369,7 @@ class PatchMerging(nn.Module): H, W = self.input_resolution flops = (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim flops += H * W * self.dim // 2 - return flops + return flops class BasicLayer(nn.Module): """ A basic Swin Transformer layer for one stage. @@ -447,7 +447,7 @@ class BasicLayer(nn.Module): nn.init.constant_(blk.norm1.weight, 0) nn.init.constant_(blk.norm2.bias, 0) nn.init.constant_(blk.norm2.weight, 0) - + class PatchEmbed(nn.Module): r""" Image to Patch Embedding Args: @@ -492,7 +492,7 @@ class PatchEmbed(nn.Module): flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1]) if self.norm is not None: flops += Ho * Wo * self.embed_dim - return flops + return flops class RSTB(nn.Module): """Residual Swin Transformer Block (RSTB). @@ -531,7 +531,7 @@ class RSTB(nn.Module): num_heads=num_heads, window_size=window_size, mlp_ratio=mlp_ratio, - qkv_bias=qkv_bias, + qkv_bias=qkv_bias, drop=drop, attn_drop=attn_drop, drop_path=drop_path, norm_layer=norm_layer, @@ -622,7 +622,7 @@ class Upsample(nn.Sequential): else: raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.') super(Upsample, self).__init__(*m) - + class Upsample_hf(nn.Sequential): """Upsample module. @@ -642,7 +642,7 @@ class Upsample_hf(nn.Sequential): m.append(nn.PixelShuffle(3)) else: raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.') - super(Upsample_hf, self).__init__(*m) + super(Upsample_hf, self).__init__(*m) class UpsampleOneStep(nn.Sequential): @@ -667,8 +667,8 @@ class UpsampleOneStep(nn.Sequential): H, W = self.input_resolution flops = H * W * self.num_feat * 3 * 9 return flops - - + + class Swin2SR(nn.Module): r""" Swin2SR @@ -698,8 +698,8 @@ class Swin2SR(nn.Module): """ def __init__(self, img_size=64, patch_size=1, in_chans=3, - embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6], - window_size=7, mlp_ratio=4., qkv_bias=True, + embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6), + window_size=7, mlp_ratio=4., qkv_bias=True, drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, norm_layer=nn.LayerNorm, ape=False, patch_norm=True, use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv', @@ -764,7 +764,7 @@ class Swin2SR(nn.Module): num_heads=num_heads[i_layer], window_size=window_size, mlp_ratio=self.mlp_ratio, - qkv_bias=qkv_bias, + qkv_bias=qkv_bias, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results norm_layer=norm_layer, @@ -776,7 +776,7 @@ class Swin2SR(nn.Module): ) self.layers.append(layer) - + if self.upsampler == 'pixelshuffle_hf': self.layers_hf = nn.ModuleList() for i_layer in range(self.num_layers): @@ -787,7 +787,7 @@ class Swin2SR(nn.Module): num_heads=num_heads[i_layer], window_size=window_size, mlp_ratio=self.mlp_ratio, - qkv_bias=qkv_bias, + qkv_bias=qkv_bias, drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results norm_layer=norm_layer, @@ -799,7 +799,7 @@ class Swin2SR(nn.Module): ) self.layers_hf.append(layer) - + self.norm = norm_layer(self.num_features) # build the last conv layer in deep feature extraction @@ -829,10 +829,10 @@ class Swin2SR(nn.Module): self.conv_aux = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) self.conv_after_aux = nn.Sequential( nn.Conv2d(3, num_feat, 3, 1, 1), - nn.LeakyReLU(inplace=True)) + nn.LeakyReLU(inplace=True)) self.upsample = Upsample(upscale, num_feat) self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) - + elif self.upsampler == 'pixelshuffle_hf': self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1), nn.LeakyReLU(inplace=True)) @@ -846,7 +846,7 @@ class Swin2SR(nn.Module): nn.Conv2d(embed_dim, num_feat, 3, 1, 1), nn.LeakyReLU(inplace=True)) self.conv_last_hf = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) - + elif self.upsampler == 'pixelshuffledirect': # for lightweight SR (to save parameters) self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch, @@ -905,7 +905,7 @@ class Swin2SR(nn.Module): x = self.patch_unembed(x, x_size) return x - + def forward_features_hf(self, x): x_size = (x.shape[2], x.shape[3]) x = self.patch_embed(x) @@ -919,7 +919,7 @@ class Swin2SR(nn.Module): x = self.norm(x) # B L C x = self.patch_unembed(x, x_size) - return x + return x def forward(self, x): H, W = x.shape[2:] @@ -951,7 +951,7 @@ class Swin2SR(nn.Module): x = self.conv_after_body(self.forward_features(x)) + x x_before = self.conv_before_upsample(x) x_out = self.conv_last(self.upsample(x_before)) - + x_hf = self.conv_first_hf(x_before) x_hf = self.conv_after_body_hf(self.forward_features_hf(x_hf)) + x_hf x_hf = self.conv_before_upsample_hf(x_hf) @@ -977,15 +977,15 @@ class Swin2SR(nn.Module): x_first = self.conv_first(x) res = self.conv_after_body(self.forward_features(x_first)) + x_first x = x + self.conv_last(res) - + x = x / self.img_range + self.mean if self.upsampler == "pixelshuffle_aux": return x[:, :, :H*self.upscale, :W*self.upscale], aux - + elif self.upsampler == "pixelshuffle_hf": x_out = x_out / self.img_range + self.mean return x_out[:, :, :H*self.upscale, :W*self.upscale], x[:, :, :H*self.upscale, :W*self.upscale], x_hf[:, :, :H*self.upscale, :W*self.upscale] - + else: return x[:, :, :H*self.upscale, :W*self.upscale] @@ -994,7 +994,7 @@ class Swin2SR(nn.Module): H, W = self.patches_resolution flops += H * W * 3 * self.embed_dim * 9 flops += self.patch_embed.flops() - for i, layer in enumerate(self.layers): + for layer in self.layers: flops += layer.flops() flops += H * W * 3 * self.embed_dim * self.embed_dim flops += self.upsample.flops() @@ -1014,4 +1014,4 @@ if __name__ == '__main__': x = torch.randn((1, 3, height, width)) x = model(x) - print(x.shape) \ No newline at end of file + print(x.shape) diff --git a/javascript/extraNetworks.js b/javascript/extraNetworks.js index c85bc79a..4d9a522c 100644 --- a/javascript/extraNetworks.js +++ b/javascript/extraNetworks.js @@ -68,18 +68,27 @@ var re_extranet_g = /\s+<([^:]+:[^:]+):[\d\.]+>/g; function tryToRemoveExtraNetworkFromPrompt(textarea, text){ var m = text.match(re_extranet) - if(! m) return false - - var partToSearch = m[1] var replaced = false - var newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found){ - m = found.match(re_extranet); - if(m[1] == partToSearch){ - replaced = true; - return "" - } - return found; - }) + var newTextareaText + if(m) { + var partToSearch = m[1] + newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found){ + m = found.match(re_extranet); + if(m[1] == partToSearch){ + replaced = true; + return "" + } + return found; + }) + } else { + newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found){ + if(found == text) { + replaced = true; + return "" + } + return found; + }) + } if(replaced){ textarea.value = newTextareaText diff --git a/javascript/localization.js b/javascript/localization.js index 0123b877..86e5ca67 100644 --- a/javascript/localization.js +++ b/javascript/localization.js @@ -109,18 +109,23 @@ function processNode(node){ } function dumpTranslations(){ + if(!hasLocalization()) { + // If we don't have any localization, + // we will not have traversed the app to find + // original_lines, so do that now. + processNode(gradioApp()); + } var dumped = {} if (localization.rtl) { - dumped.rtl = true + dumped.rtl = true; } - Object.keys(original_lines).forEach(function(text){ - if(dumped[text] !== undefined) return + for (const text in original_lines) { + if(dumped[text] !== undefined) continue; + dumped[text] = localization[text] || text; + } - dumped[text] = localization[text] || text - }) - - return dumped + return dumped; } function download_localization() { @@ -137,7 +142,11 @@ function download_localization() { document.body.removeChild(element); } -if(hasLocalization()) { +document.addEventListener("DOMContentLoaded", function () { + if (!hasLocalization()) { + return; + } + onUiUpdate(function (m) { m.forEach(function (mutation) { mutation.addedNodes.forEach(function (node) { @@ -146,26 +155,23 @@ if(hasLocalization()) { }); }) + processNode(gradioApp()) - document.addEventListener("DOMContentLoaded", function () { - processNode(gradioApp()) + if (localization.rtl) { // if the language is from right to left, + (new MutationObserver((mutations, observer) => { // wait for the style to load + mutations.forEach(mutation => { + mutation.addedNodes.forEach(node => { + if (node.tagName === 'STYLE') { + observer.disconnect(); - if (localization.rtl) { // if the language is from right to left, - (new MutationObserver((mutations, observer) => { // wait for the style to load - mutations.forEach(mutation => { - mutation.addedNodes.forEach(node => { - if (node.tagName === 'STYLE') { - observer.disconnect(); - - for (const x of node.sheet.rules) { // find all rtl media rules - if (Array.from(x.media || []).includes('rtl')) { - x.media.appendMedium('all'); // enable them - } + for (const x of node.sheet.rules) { // find all rtl media rules + if (Array.from(x.media || []).includes('rtl')) { + x.media.appendMedium('all'); // enable them } } - }) - }); - })).observe(gradioApp(), { childList: true }); - } - }) -} + } + }) + }); + })).observe(gradioApp(), { childList: true }); + } +}) diff --git a/javascript/ui_settings_hints.js b/javascript/ui_settings_hints.js index 87a289d3..6d1933dc 100644 --- a/javascript/ui_settings_hints.js +++ b/javascript/ui_settings_hints.js @@ -1,41 +1,62 @@ // various hints and extra info for the settings tab -onUiLoaded(function(){ - createLink = function(elem_id, text, href){ - var a = document.createElement('A') - a.textContent = text - a.target = '_blank'; +settingsHintsSetup = false - elem = gradioApp().querySelector('#'+elem_id) - elem.insertBefore(a, elem.querySelector('label')) +onOptionsChanged(function(){ + if(settingsHintsSetup) return + settingsHintsSetup = true - return a - } + gradioApp().querySelectorAll('#settings [id^=setting_]').forEach(function(div){ + var name = div.id.substr(8) + var commentBefore = opts._comments_before[name] + var commentAfter = opts._comments_after[name] - createLink("setting_samples_filename_pattern", "[wiki] ").href = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory" - createLink("setting_directories_filename_pattern", "[wiki] ").href = "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory" + if(! commentBefore && !commentAfter) return - createLink("setting_quicksettings_list", "[info] ").addEventListener("click", function(event){ - requestGet("./internal/quicksettings-hint", {}, function(data){ - var table = document.createElement('table') - table.className = 'settings-value-table' + var span = null + if(div.classList.contains('gradio-checkbox')) span = div.querySelector('label span') + else if(div.classList.contains('gradio-checkboxgroup')) span = div.querySelector('span').firstChild + else if(div.classList.contains('gradio-radio')) span = div.querySelector('span').firstChild + else span = div.querySelector('label span').firstChild - data.forEach(function(obj){ - var tr = document.createElement('tr') - var td = document.createElement('td') - td.textContent = obj.name - tr.appendChild(td) + if(!span) return - var td = document.createElement('td') - td.textContent = obj.label - tr.appendChild(td) - - table.appendChild(tr) - }) - - popup(table); - }) - }); + if(commentBefore){ + var comment = document.createElement('DIV') + comment.className = 'settings-comment' + comment.innerHTML = commentBefore + span.parentElement.insertBefore(document.createTextNode('\xa0'), span) + span.parentElement.insertBefore(comment, span) + span.parentElement.insertBefore(document.createTextNode('\xa0'), span) + } + if(commentAfter){ + var comment = document.createElement('DIV') + comment.className = 'settings-comment' + comment.innerHTML = commentAfter + span.parentElement.insertBefore(comment, span.nextSibling) + span.parentElement.insertBefore(document.createTextNode('\xa0'), span.nextSibling) + } + }) }) +function settingsHintsShowQuicksettings(){ + requestGet("./internal/quicksettings-hint", {}, function(data){ + var table = document.createElement('table') + table.className = 'settings-value-table' + data.forEach(function(obj){ + var tr = document.createElement('tr') + var td = document.createElement('td') + td.textContent = obj.name + tr.appendChild(td) + + var td = document.createElement('td') + td.textContent = obj.label + tr.appendChild(td) + + table.appendChild(tr) + }) + + popup(table); + }) +} diff --git a/launch.py b/launch.py index cfc0cffa..f8380911 100644 --- a/launch.py +++ b/launch.py @@ -3,25 +3,23 @@ import subprocess import os import sys import importlib.util -import shlex import platform import json +from functools import lru_cache from modules import cmd_args from modules.paths_internal import script_path, extensions_dir -commandline_args = os.environ.get('COMMANDLINE_ARGS', "") -sys.argv += shlex.split(commandline_args) - args, _ = cmd_args.parser.parse_known_args() python = sys.executable git = os.environ.get('GIT', "git") index_url = os.environ.get('INDEX_URL', "") -stored_commit_hash = None -stored_git_tag = None dir_repos = "repositories" +# Whether to default to printing command output +default_command_live = (os.environ.get('WEBUI_LAUNCH_LIVE_OUTPUT') == "1") + if 'GRADIO_ANALYTICS_ENABLED' not in os.environ: os.environ['GRADIO_ANALYTICS_ENABLED'] = 'False' @@ -57,65 +55,52 @@ Use --skip-python-version-check to suppress this warning. """) +@lru_cache() def commit_hash(): - global stored_commit_hash - - if stored_commit_hash is not None: - return stored_commit_hash - try: - stored_commit_hash = run(f"{git} rev-parse HEAD").strip() + return subprocess.check_output([git, "rev-parse", "HEAD"], shell=False, encoding='utf8').strip() except Exception: - stored_commit_hash = "" - - return stored_commit_hash + return "" +@lru_cache() def git_tag(): - global stored_git_tag - - if stored_git_tag is not None: - return stored_git_tag - try: - stored_git_tag = run(f"{git} describe --tags").strip() + return subprocess.check_output([git, "describe", "--tags"], shell=False, encoding='utf8').strip() except Exception: - stored_git_tag = "" - - return stored_git_tag + return "" -def run(command, desc=None, errdesc=None, custom_env=None, live=False): +def run(command, desc=None, errdesc=None, custom_env=None, live: bool = default_command_live) -> str: if desc is not None: print(desc) - if live: - result = subprocess.run(command, shell=True, env=os.environ if custom_env is None else custom_env) - if result.returncode != 0: - raise RuntimeError(f"""{errdesc or 'Error running command'}. -Command: {command} -Error code: {result.returncode}""") + run_kwargs = { + "args": command, + "shell": True, + "env": os.environ if custom_env is None else custom_env, + "encoding": 'utf8', + "errors": 'ignore', + } - return "" + if not live: + run_kwargs["stdout"] = run_kwargs["stderr"] = subprocess.PIPE - result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True, env=os.environ if custom_env is None else custom_env) + result = subprocess.run(**run_kwargs) if result.returncode != 0: + error_bits = [ + f"{errdesc or 'Error running command'}.", + f"Command: {command}", + f"Error code: {result.returncode}", + ] + if result.stdout: + error_bits.append(f"stdout: {result.stdout}") + if result.stderr: + error_bits.append(f"stderr: {result.stderr}") + raise RuntimeError("\n".join(error_bits)) - message = f"""{errdesc or 'Error running command'}. -Command: {command} -Error code: {result.returncode} -stdout: {result.stdout.decode(encoding="utf8", errors="ignore") if len(result.stdout)>0 else ''} -stderr: {result.stderr.decode(encoding="utf8", errors="ignore") if len(result.stderr)>0 else ''} -""" - raise RuntimeError(message) - - return result.stdout.decode(encoding="utf8", errors="ignore") - - -def check_run(command): - result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) - return result.returncode == 0 + return (result.stdout or "") def is_installed(package): @@ -131,11 +116,7 @@ def repo_dir(name): return os.path.join(script_path, dir_repos, name) -def run_python(code, desc=None, errdesc=None): - return run(f'"{python}" -c "{code}"', desc, errdesc) - - -def run_pip(command, desc=None, live=False): +def run_pip(command, desc=None, live=default_command_live): if args.skip_install: return @@ -143,8 +124,9 @@ def run_pip(command, desc=None, live=False): return run(f'"{python}" -m pip {command} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}", live=live) -def check_run_python(code): - return check_run(f'"{python}" -c "{code}"') +def check_run_python(code: str) -> bool: + result = subprocess.run([python, "-c", code], capture_output=True, shell=False) + return result.returncode == 0 def git_clone(url, dir, name, commithash=None): @@ -237,13 +219,14 @@ def run_extensions_installers(settings_file): def prepare_environment(): - torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url https://download.pytorch.org/whl/cu118") + torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu118") + torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url {torch_index_url}") requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt") xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.17') - gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379") - clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1") - openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b") + gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "https://github.com/TencentARC/GFPGAN/archive/8d2447a2d918f8eba5a4a01463fd48e45126a379.zip") + clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip") + openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip") stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git") taming_transformers_repo = os.environ.get('TAMING_TRANSFORMERS_REPO', "https://github.com/CompVis/taming-transformers.git") @@ -270,8 +253,11 @@ def prepare_environment(): if args.reinstall_torch or not is_installed("torch") or not is_installed("torchvision"): run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True) - if not args.skip_torch_cuda_test: - run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'") + if not args.skip_torch_cuda_test and not check_run_python("import torch; assert torch.cuda.is_available()"): + raise RuntimeError( + 'Torch is not able to use GPU; ' + 'add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check' + ) if not is_installed("gfpgan"): run_pip(f"install {gfpgan_package}", "gfpgan") @@ -319,7 +305,7 @@ def prepare_environment(): if args.update_all_extensions: git_pull_recursive(extensions_dir) - + if "--exit" in sys.argv: print("Exiting because of --exit argument") exit(0) diff --git a/modules/Roboto-Regular.ttf b/modules/Roboto-Regular.ttf new file mode 100644 index 00000000..500b1045 Binary files /dev/null and b/modules/Roboto-Regular.ttf differ diff --git a/modules/api/api.py b/modules/api/api.py index 9bb95dfd..165985c3 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -15,7 +15,8 @@ from secrets import compare_digest import modules.shared as shared from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing -from modules.api.models import * +from modules.api import models +from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.textual_inversion.textual_inversion import create_embedding, train_embedding from modules.textual_inversion.preprocess import preprocess @@ -25,21 +26,24 @@ from modules.sd_models import checkpoints_list, unload_model_weights, reload_mod from modules.sd_models_config import find_checkpoint_config_near_filename from modules.realesrgan_model import get_realesrgan_models from modules import devices -from typing import List +from typing import Dict, List, Any import piexif import piexif.helper + def upscaler_to_index(name: str): try: return [x.name.lower() for x in shared.sd_upscalers].index(name.lower()) - except: - raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in sd_upscalers])}") + except Exception as e: + raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in shared.sd_upscalers])}") from e + def script_name_to_index(name, scripts): try: return [script.title().lower() for script in scripts].index(name.lower()) - except: - raise HTTPException(status_code=422, detail=f"Script '{name}' not found") + except Exception as e: + raise HTTPException(status_code=422, detail=f"Script '{name}' not found") from e + def validate_sampler_name(name): config = sd_samplers.all_samplers_map.get(name, None) @@ -48,20 +52,23 @@ def validate_sampler_name(name): return name + def setUpscalers(req: dict): reqDict = vars(req) reqDict['extras_upscaler_1'] = reqDict.pop('upscaler_1', None) reqDict['extras_upscaler_2'] = reqDict.pop('upscaler_2', None) return reqDict + def decode_base64_to_image(encoding): if encoding.startswith("data:image/"): encoding = encoding.split(";")[1].split(",")[1] try: image = Image.open(BytesIO(base64.b64decode(encoding))) return image - except Exception as err: - raise HTTPException(status_code=500, detail="Invalid encoded image") + except Exception as e: + raise HTTPException(status_code=500, detail="Invalid encoded image") from e + def encode_pil_to_base64(image): with io.BytesIO() as output_bytes: @@ -92,6 +99,7 @@ def encode_pil_to_base64(image): return base64.b64encode(bytes_data) + def api_middleware(app: FastAPI): rich_available = True try: @@ -99,7 +107,7 @@ def api_middleware(app: FastAPI): import starlette # importing just so it can be placed on silent list from rich.console import Console console = Console() - except: + except Exception: import traceback rich_available = False @@ -157,7 +165,7 @@ def api_middleware(app: FastAPI): class Api: def __init__(self, app: FastAPI, queue_lock: Lock): if shared.cmd_opts.api_auth: - self.credentials = dict() + self.credentials = {} for auth in shared.cmd_opts.api_auth.split(","): user, password = auth.split(":") self.credentials[user] = password @@ -166,36 +174,36 @@ class Api: self.app = app self.queue_lock = queue_lock api_middleware(self.app) - self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse) - self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse) - self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse) - self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse) - self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse) - self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse) + self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=models.TextToImageResponse) + self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=models.ImageToImageResponse) + self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=models.ExtrasSingleImageResponse) + self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=models.ExtrasBatchImagesResponse) + self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=models.PNGInfoResponse) + self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=models.ProgressResponse) self.add_api_route("/sdapi/v1/interrogate", self.interrogateapi, methods=["POST"]) self.add_api_route("/sdapi/v1/interrupt", self.interruptapi, methods=["POST"]) self.add_api_route("/sdapi/v1/skip", self.skip, methods=["POST"]) - self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=OptionsModel) + self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=models.OptionsModel) self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"]) - self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=FlagsModel) - self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem]) - self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[UpscalerItem]) - self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[SDModelItem]) - self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem]) - self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem]) - self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem]) - self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem]) - self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse) + self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=models.FlagsModel) + self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[models.SamplerItem]) + self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[models.UpscalerItem]) + self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[models.SDModelItem]) + self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[models.HypernetworkItem]) + self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[models.FaceRestorerItem]) + self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[models.RealesrganItem]) + self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem]) + self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) - self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse) - self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse) - self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse) - self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse) - self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse) - self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse) + self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse) + self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse) + self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse) + self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse) + self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse) + self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse) self.add_api_route("/sdapi/v1/unload-checkpoint", self.unloadapi, methods=["POST"]) self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"]) - self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=ScriptsList) + self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=models.ScriptsList) self.default_script_arg_txt2img = [] self.default_script_arg_img2img = [] @@ -219,17 +227,17 @@ class Api: script_idx = script_name_to_index(script_name, script_runner.selectable_scripts) script = script_runner.selectable_scripts[script_idx] return script, script_idx - + def get_scripts_list(self): t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles] i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles] - return ScriptsList(txt2img = t2ilist, img2img = i2ilist) + return models.ScriptsList(txt2img=t2ilist, img2img=i2ilist) def get_script(self, script_name, script_runner): if script_name is None or script_name == "": return None, None - + script_idx = script_name_to_index(script_name, script_runner.scripts) return script_runner.scripts[script_idx] @@ -264,11 +272,11 @@ class Api: if request.alwayson_scripts and (len(request.alwayson_scripts) > 0): for alwayson_script_name in request.alwayson_scripts.keys(): alwayson_script = self.get_script(alwayson_script_name, script_runner) - if alwayson_script == None: + if alwayson_script is None: raise HTTPException(status_code=422, detail=f"always on script {alwayson_script_name} not found") # Selectable script in always on script param check - if alwayson_script.alwayson == False: - raise HTTPException(status_code=422, detail=f"Cannot have a selectable script in the always on scripts params") + if alwayson_script.alwayson is False: + raise HTTPException(status_code=422, detail="Cannot have a selectable script in the always on scripts params") # always on script with no arg should always run so you don't really need to add them to the requests if "args" in request.alwayson_scripts[alwayson_script_name]: # min between arg length in scriptrunner and arg length in the request @@ -276,7 +284,7 @@ class Api: script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx] return script_args - def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI): + def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI): script_runner = scripts.scripts_txt2img if not script_runner.scripts: script_runner.initialize_scripts(False) @@ -310,7 +318,7 @@ class Api: p.outpath_samples = opts.outdir_txt2img_samples shared.state.begin() - if selectable_scripts != None: + if selectable_scripts is not None: p.script_args = script_args processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here else: @@ -320,9 +328,9 @@ class Api: b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else [] - return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js()) + return models.TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js()) - def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI): + def img2imgapi(self, img2imgreq: models.StableDiffusionImg2ImgProcessingAPI): init_images = img2imgreq.init_images if init_images is None: raise HTTPException(status_code=404, detail="Init image not found") @@ -367,7 +375,7 @@ class Api: p.outpath_samples = opts.outdir_img2img_samples shared.state.begin() - if selectable_scripts != None: + if selectable_scripts is not None: p.script_args = script_args processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here else: @@ -381,9 +389,9 @@ class Api: img2imgreq.init_images = None img2imgreq.mask = None - return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js()) + return models.ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js()) - def extras_single_image_api(self, req: ExtrasSingleImageRequest): + def extras_single_image_api(self, req: models.ExtrasSingleImageRequest): reqDict = setUpscalers(req) reqDict['image'] = decode_base64_to_image(reqDict['image']) @@ -391,9 +399,9 @@ class Api: with self.queue_lock: result = postprocessing.run_extras(extras_mode=0, image_folder="", input_dir="", output_dir="", save_output=False, **reqDict) - return ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1]) + return models.ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1]) - def extras_batch_images_api(self, req: ExtrasBatchImagesRequest): + def extras_batch_images_api(self, req: models.ExtrasBatchImagesRequest): reqDict = setUpscalers(req) image_list = reqDict.pop('imageList', []) @@ -402,15 +410,15 @@ class Api: with self.queue_lock: result = postprocessing.run_extras(extras_mode=1, image_folder=image_folder, image="", input_dir="", output_dir="", save_output=False, **reqDict) - return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) + return models.ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1]) - def pnginfoapi(self, req: PNGInfoRequest): + def pnginfoapi(self, req: models.PNGInfoRequest): if(not req.image.strip()): - return PNGInfoResponse(info="") + return models.PNGInfoResponse(info="") image = decode_base64_to_image(req.image.strip()) if image is None: - return PNGInfoResponse(info="") + return models.PNGInfoResponse(info="") geninfo, items = images.read_info_from_image(image) if geninfo is None: @@ -418,13 +426,13 @@ class Api: items = {**{'parameters': geninfo}, **items} - return PNGInfoResponse(info=geninfo, items=items) + return models.PNGInfoResponse(info=geninfo, items=items) - def progressapi(self, req: ProgressRequest = Depends()): + def progressapi(self, req: models.ProgressRequest = Depends()): # copy from check_progress_call of ui.py if shared.state.job_count == 0: - return ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo) + return models.ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo) # avoid dividing zero progress = 0.01 @@ -446,9 +454,9 @@ class Api: if shared.state.current_image and not req.skip_current_image: current_image = encode_pil_to_base64(shared.state.current_image) - return ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo) + return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo) - def interrogateapi(self, interrogatereq: InterrogateRequest): + def interrogateapi(self, interrogatereq: models.InterrogateRequest): image_b64 = interrogatereq.image if image_b64 is None: raise HTTPException(status_code=404, detail="Image not found") @@ -465,7 +473,7 @@ class Api: else: raise HTTPException(status_code=404, detail="Model not found") - return InterrogateResponse(caption=processed) + return models.InterrogateResponse(caption=processed) def interruptapi(self): shared.state.interrupt() @@ -570,36 +578,36 @@ class Api: filename = create_embedding(**args) # create empty embedding sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings() # reload embeddings so new one can be immediately used shared.state.end() - return CreateResponse(info=f"create embedding filename: {filename}") + return models.CreateResponse(info=f"create embedding filename: {filename}") except AssertionError as e: shared.state.end() - return TrainResponse(info=f"create embedding error: {e}") + return models.TrainResponse(info=f"create embedding error: {e}") def create_hypernetwork(self, args: dict): try: shared.state.begin() filename = create_hypernetwork(**args) # create empty embedding shared.state.end() - return CreateResponse(info=f"create hypernetwork filename: {filename}") + return models.CreateResponse(info=f"create hypernetwork filename: {filename}") except AssertionError as e: shared.state.end() - return TrainResponse(info=f"create hypernetwork error: {e}") + return models.TrainResponse(info=f"create hypernetwork error: {e}") def preprocess(self, args: dict): try: shared.state.begin() preprocess(**args) # quick operation unless blip/booru interrogation is enabled shared.state.end() - return PreprocessResponse(info = 'preprocess complete') + return models.PreprocessResponse(info = 'preprocess complete') except KeyError as e: shared.state.end() - return PreprocessResponse(info=f"preprocess error: invalid token: {e}") + return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}") except AssertionError as e: shared.state.end() - return PreprocessResponse(info=f"preprocess error: {e}") + return models.PreprocessResponse(info=f"preprocess error: {e}") except FileNotFoundError as e: shared.state.end() - return PreprocessResponse(info=f'preprocess error: {e}') + return models.PreprocessResponse(info=f'preprocess error: {e}') def train_embedding(self, args: dict): try: @@ -617,10 +625,10 @@ class Api: if not apply_optimizations: sd_hijack.apply_optimizations() shared.state.end() - return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") + return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") except AssertionError as msg: shared.state.end() - return TrainResponse(info=f"train embedding error: {msg}") + return models.TrainResponse(info=f"train embedding error: {msg}") def train_hypernetwork(self, args: dict): try: @@ -641,14 +649,15 @@ class Api: if not apply_optimizations: sd_hijack.apply_optimizations() shared.state.end() - return TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") - except AssertionError as msg: + return models.TrainResponse(info=f"train embedding complete: filename: {filename} error: {error}") + except AssertionError: shared.state.end() - return TrainResponse(info=f"train embedding error: {error}") + return models.TrainResponse(info=f"train embedding error: {error}") def get_memory(self): try: - import os, psutil + import os + import psutil process = psutil.Process(os.getpid()) res = process.memory_info() # only rss is cross-platform guaranteed so we dont rely on other values ram_total = 100 * res.rss / process.memory_percent() # and total memory is calculated as actual value is not cross-platform safe @@ -675,10 +684,10 @@ class Api: 'events': warnings, } else: - cuda = { 'error': 'unavailable' } + cuda = {'error': 'unavailable'} except Exception as err: - cuda = { 'error': f'{err}' } - return MemoryResponse(ram = ram, cuda = cuda) + cuda = {'error': f'{err}'} + return models.MemoryResponse(ram=ram, cuda=cuda) def launch(self, server_name, port): self.app.include_router(self.router) diff --git a/modules/api/models.py b/modules/api/models.py index 4a70f440..006ccdb7 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -223,8 +223,9 @@ for key in _options: if(_options[key].dest != 'help'): flag = _options[key] _type = str - if _options[key].default is not None: _type = type(_options[key].default) - flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))}) + if _options[key].default is not None: + _type = type(_options[key].default) + flags.update({flag.dest: (_type, Field(default=flag.default, description=flag.help))}) FlagsModel = create_model("Flags", **flags) @@ -288,4 +289,4 @@ class MemoryResponse(BaseModel): class ScriptsList(BaseModel): txt2img: list = Field(default=None,title="Txt2img", description="Titles of scripts (txt2img)") - img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)") \ No newline at end of file + img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)") diff --git a/modules/cmd_args.py b/modules/cmd_args.py index d906a571..f4a4ab36 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -1,6 +1,6 @@ import argparse import os -from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file +from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir, sd_default_config, sd_model_file # noqa: F401 parser = argparse.ArgumentParser() @@ -102,4 +102,4 @@ parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gra parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers") parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False) parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False) -parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy') \ No newline at end of file +parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy') diff --git a/modules/codeformer/codeformer_arch.py b/modules/codeformer/codeformer_arch.py index 11dcc3ee..12db6814 100644 --- a/modules/codeformer/codeformer_arch.py +++ b/modules/codeformer/codeformer_arch.py @@ -1,14 +1,12 @@ # this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py import math -import numpy as np import torch from torch import nn, Tensor import torch.nn.functional as F -from typing import Optional, List +from typing import Optional -from modules.codeformer.vqgan_arch import * -from basicsr.utils import get_root_logger +from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock from basicsr.utils.registry import ARCH_REGISTRY def calc_mean_std(feat, eps=1e-5): @@ -121,7 +119,7 @@ class TransformerSALayer(nn.Module): tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask: Optional[Tensor] = None, query_pos: Optional[Tensor] = None): - + # self attention tgt2 = self.norm1(tgt) q = k = self.with_pos_embed(tgt2, query_pos) @@ -161,10 +159,10 @@ class Fuse_sft_block(nn.Module): @ARCH_REGISTRY.register() class CodeFormer(VQAutoEncoder): - def __init__(self, dim_embd=512, n_head=8, n_layers=9, + def __init__(self, dim_embd=512, n_head=8, n_layers=9, codebook_size=1024, latent_size=256, - connect_list=['32', '64', '128', '256'], - fix_modules=['quantize','generator']): + connect_list=('32', '64', '128', '256'), + fix_modules=('quantize', 'generator')): super(CodeFormer, self).__init__(512, 64, [1, 2, 2, 4, 4, 8], 'nearest',2, [16], codebook_size) if fix_modules is not None: @@ -181,14 +179,14 @@ class CodeFormer(VQAutoEncoder): self.feat_emb = nn.Linear(256, self.dim_embd) # transformer - self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0) + self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0) for _ in range(self.n_layers)]) # logits_predict head self.idx_pred_layer = nn.Sequential( nn.LayerNorm(dim_embd), nn.Linear(dim_embd, codebook_size, bias=False)) - + self.channels = { '16': 512, '32': 256, @@ -223,7 +221,7 @@ class CodeFormer(VQAutoEncoder): enc_feat_dict = {} out_list = [self.fuse_encoder_block[f_size] for f_size in self.connect_list] for i, block in enumerate(self.encoder.blocks): - x = block(x) + x = block(x) if i in out_list: enc_feat_dict[str(x.shape[-1])] = x.clone() @@ -268,11 +266,11 @@ class CodeFormer(VQAutoEncoder): fuse_list = [self.fuse_generator_block[f_size] for f_size in self.connect_list] for i, block in enumerate(self.generator.blocks): - x = block(x) + x = block(x) if i in fuse_list: # fuse after i-th block f_size = str(x.shape[-1]) if w>0: x = self.fuse_convs_dict[f_size](enc_feat_dict[f_size].detach(), x, w) out = x # logits doesn't need softmax before cross_entropy loss - return out, logits, lq_feat \ No newline at end of file + return out, logits, lq_feat diff --git a/modules/codeformer/vqgan_arch.py b/modules/codeformer/vqgan_arch.py index e7293683..09ee6660 100644 --- a/modules/codeformer/vqgan_arch.py +++ b/modules/codeformer/vqgan_arch.py @@ -5,17 +5,15 @@ VQGAN code, adapted from the original created by the Unleashing Transformers aut https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py ''' -import numpy as np import torch import torch.nn as nn import torch.nn.functional as F -import copy from basicsr.utils import get_root_logger from basicsr.utils.registry import ARCH_REGISTRY def normalize(in_channels): return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True) - + @torch.jit.script def swish(x): @@ -212,15 +210,15 @@ class AttnBlock(nn.Module): # compute attention b, c, h, w = q.shape q = q.reshape(b, c, h*w) - q = q.permute(0, 2, 1) + q = q.permute(0, 2, 1) k = k.reshape(b, c, h*w) - w_ = torch.bmm(q, k) + w_ = torch.bmm(q, k) w_ = w_ * (int(c)**(-0.5)) w_ = F.softmax(w_, dim=2) # attend to values v = v.reshape(b, c, h*w) - w_ = w_.permute(0, 2, 1) + w_ = w_.permute(0, 2, 1) h_ = torch.bmm(v, w_) h_ = h_.reshape(b, c, h, w) @@ -272,18 +270,18 @@ class Encoder(nn.Module): def forward(self, x): for block in self.blocks: x = block(x) - + return x class Generator(nn.Module): def __init__(self, nf, emb_dim, ch_mult, res_blocks, img_size, attn_resolutions): super().__init__() - self.nf = nf - self.ch_mult = ch_mult + self.nf = nf + self.ch_mult = ch_mult self.num_resolutions = len(self.ch_mult) self.num_res_blocks = res_blocks - self.resolution = img_size + self.resolution = img_size self.attn_resolutions = attn_resolutions self.in_channels = emb_dim self.out_channels = 3 @@ -317,29 +315,29 @@ class Generator(nn.Module): blocks.append(nn.Conv2d(block_in_ch, self.out_channels, kernel_size=3, stride=1, padding=1)) self.blocks = nn.ModuleList(blocks) - + def forward(self, x): for block in self.blocks: x = block(x) - + return x - + @ARCH_REGISTRY.register() class VQAutoEncoder(nn.Module): - def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=[16], codebook_size=1024, emb_dim=256, + def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256, beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None): super().__init__() logger = get_root_logger() - self.in_channels = 3 - self.nf = nf - self.n_blocks = res_blocks + self.in_channels = 3 + self.nf = nf + self.n_blocks = res_blocks self.codebook_size = codebook_size self.embed_dim = emb_dim self.ch_mult = ch_mult self.resolution = img_size - self.attn_resolutions = attn_resolutions + self.attn_resolutions = attn_resolutions or [16] self.quantizer_type = quantizer self.encoder = Encoder( self.in_channels, @@ -365,11 +363,11 @@ class VQAutoEncoder(nn.Module): self.kl_weight ) self.generator = Generator( - self.nf, + self.nf, self.embed_dim, - self.ch_mult, - self.n_blocks, - self.resolution, + self.ch_mult, + self.n_blocks, + self.resolution, self.attn_resolutions ) @@ -434,4 +432,4 @@ class VQGANDiscriminator(nn.Module): raise ValueError('Wrong params!') def forward(self, x): - return self.main(x) \ No newline at end of file + return self.main(x) diff --git a/modules/codeformer_model.py b/modules/codeformer_model.py index 8d84bbc9..ececdbae 100644 --- a/modules/codeformer_model.py +++ b/modules/codeformer_model.py @@ -33,11 +33,9 @@ def setup_model(dirname): try: from torchvision.transforms.functional import normalize from modules.codeformer.codeformer_arch import CodeFormer - from basicsr.utils.download_util import load_file_from_url - from basicsr.utils import imwrite, img2tensor, tensor2img + from basicsr.utils import img2tensor, tensor2img from facelib.utils.face_restoration_helper import FaceRestoreHelper from facelib.detection.retinaface import retinaface - from modules.shared import cmd_opts net_class = CodeFormer @@ -96,7 +94,7 @@ def setup_model(dirname): self.face_helper.get_face_landmarks_5(only_center_face=False, resize=640, eye_dist_threshold=5) self.face_helper.align_warp_face() - for idx, cropped_face in enumerate(self.face_helper.cropped_faces): + for cropped_face in self.face_helper.cropped_faces: cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True) normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True) cropped_face_t = cropped_face_t.unsqueeze(0).to(devices.device_codeformer) diff --git a/modules/config_states.py b/modules/config_states.py index 2ea00929..db65bcdb 100644 --- a/modules/config_states.py +++ b/modules/config_states.py @@ -14,7 +14,7 @@ from collections import OrderedDict import git from modules import shared, extensions -from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path, config_states_dir +from modules.paths_internal import script_path, config_states_dir all_config_states = OrderedDict() @@ -35,7 +35,7 @@ def list_config_states(): j["filepath"] = path config_states.append(j) - config_states = list(sorted(config_states, key=lambda cs: cs["created_at"], reverse=True)) + config_states = sorted(config_states, key=lambda cs: cs["created_at"], reverse=True) for cs in config_states: timestamp = time.asctime(time.gmtime(cs["created_at"])) @@ -83,6 +83,8 @@ def get_extension_config(): ext_config = {} for ext in extensions.extensions: + ext.read_info_from_repo() + entry = { "name": ext.name, "path": ext.path, diff --git a/modules/deepbooru.py b/modules/deepbooru.py index 122fce7f..547e1b4c 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -2,7 +2,6 @@ import os import re import torch -from PIL import Image import numpy as np from modules import modelloader, paths, deepbooru_model, devices, images, shared @@ -79,7 +78,7 @@ class DeepDanbooru: res = [] - filtertags = set([x.strip().replace(' ', '_') for x in shared.opts.deepbooru_filter_tags.split(",")]) + filtertags = {x.strip().replace(' ', '_') for x in shared.opts.deepbooru_filter_tags.split(",")} for tag in [x for x in tags if x not in filtertags]: probability = probability_dict[tag] diff --git a/modules/devices.py b/modules/devices.py index c705a3cb..d8a34a0f 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -65,7 +65,7 @@ def enable_tf32(): # enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't # see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407 - if any([torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())]): + if any(torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())): torch.backends.cudnn.benchmark = True torch.backends.cuda.matmul.allow_tf32 = True diff --git a/modules/esrgan_model.py b/modules/esrgan_model.py index f4369257..a009eb42 100644 --- a/modules/esrgan_model.py +++ b/modules/esrgan_model.py @@ -6,7 +6,7 @@ from PIL import Image from basicsr.utils.download_util import load_file_from_url import modules.esrgan_model_arch as arch -from modules import shared, modelloader, images, devices +from modules import modelloader, images, devices from modules.upscaler import Upscaler, UpscalerData from modules.shared import opts @@ -16,9 +16,7 @@ def mod2normal(state_dict): # this code is copied from https://github.com/victorca25/iNNfer if 'conv_first.weight' in state_dict: crt_net = {} - items = [] - for k, v in state_dict.items(): - items.append(k) + items = list(state_dict) crt_net['model.0.weight'] = state_dict['conv_first.weight'] crt_net['model.0.bias'] = state_dict['conv_first.bias'] @@ -52,9 +50,7 @@ def resrgan2normal(state_dict, nb=23): if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict: re8x = 0 crt_net = {} - items = [] - for k, v in state_dict.items(): - items.append(k) + items = list(state_dict) crt_net['model.0.weight'] = state_dict['conv_first.weight'] crt_net['model.0.bias'] = state_dict['conv_first.bias'] diff --git a/modules/esrgan_model_arch.py b/modules/esrgan_model_arch.py index 6071fea7..2b9888ba 100644 --- a/modules/esrgan_model_arch.py +++ b/modules/esrgan_model_arch.py @@ -2,7 +2,6 @@ from collections import OrderedDict import math -import functools import torch import torch.nn as nn import torch.nn.functional as F @@ -106,7 +105,7 @@ class ResidualDenseBlock_5C(nn.Module): Modified options that can be used: - "Partial Convolution based Padding" arXiv:1811.11718 - "Spectral normalization" arXiv:1802.05957 - - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C. + - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C. {Rakotonirina} and A. {Rasoanaivo} """ @@ -171,7 +170,7 @@ class GaussianNoise(nn.Module): scale = self.sigma * x.detach() if self.is_relative_detach else self.sigma * x sampled_noise = self.noise.repeat(*x.size()).normal_() * scale x = x + sampled_noise - return x + return x def conv1x1(in_planes, out_planes, stride=1): return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) @@ -438,9 +437,11 @@ def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias= padding = padding if pad_type == 'zero' else 0 if convtype=='PartialConv2D': + from torchvision.ops import PartialConv2d # this is definitely not going to work, but PartialConv2d doesn't work anyway and this shuts up static analyzer c = PartialConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, bias=bias, groups=groups) elif convtype=='DeformConv2D': + from torchvision.ops import DeformConv2d # not tested c = DeformConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, bias=bias, groups=groups) elif convtype=='Conv3D': diff --git a/modules/extensions.py b/modules/extensions.py index 34d9d654..359a7aa5 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -1,13 +1,12 @@ import os import sys +import threading import traceback -import time -from datetime import datetime import git from modules import shared -from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path +from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path # noqa: F401 extensions = [] @@ -25,6 +24,8 @@ def active(): class Extension: + lock = threading.Lock() + def __init__(self, name, path, enabled=True, is_builtin=False): self.name = name self.path = path @@ -43,8 +44,13 @@ class Extension: if self.is_builtin or self.have_info_from_repo: return - self.have_info_from_repo = True + with self.lock: + if self.have_info_from_repo: + return + self.do_read_info_from_repo() + + def do_read_info_from_repo(self): repo = None try: if os.path.exists(os.path.join(self.path, ".git")): @@ -59,18 +65,18 @@ class Extension: try: self.status = 'unknown' self.remote = next(repo.remote().urls, None) - head = repo.head.commit self.commit_date = repo.head.commit.committed_date - ts = time.asctime(time.gmtime(self.commit_date)) if repo.active_branch: self.branch = repo.active_branch.name - self.commit_hash = head.hexsha - self.version = f'{self.commit_hash[:8]} ({ts})' + self.commit_hash = repo.head.commit.hexsha + self.version = repo.git.describe("--always", "--tags") # compared to `self.commit_hash[:8]` this takes about 30% more time total but since we run it in parallel we don't care except Exception as ex: print(f"Failed reading extension data from Git repository ({self.name}): {ex}", file=sys.stderr) self.remote = None + self.have_info_from_repo = True + def list_files(self, subdir, extension): from modules import scripts diff --git a/modules/extra_networks.py b/modules/extra_networks.py index 1978673d..f9db41bc 100644 --- a/modules/extra_networks.py +++ b/modules/extra_networks.py @@ -91,7 +91,7 @@ def deactivate(p, extra_network_data): """call deactivate for extra networks in extra_network_data in specified order, then call deactivate for all remaining registered networks""" - for extra_network_name, extra_network_args in extra_network_data.items(): + for extra_network_name in extra_network_data: extra_network = extra_network_registry.get(extra_network_name, None) if extra_network is None: continue diff --git a/modules/extra_networks_hypernet.py b/modules/extra_networks_hypernet.py index 04f27c9f..aa2a14ef 100644 --- a/modules/extra_networks_hypernet.py +++ b/modules/extra_networks_hypernet.py @@ -1,4 +1,4 @@ -from modules import extra_networks, shared, extra_networks +from modules import extra_networks, shared from modules.hypernetworks import hypernetwork diff --git a/modules/extras.py b/modules/extras.py index ff4e9c4e..bdf9b3b7 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -136,14 +136,14 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ result_is_instruct_pix2pix_model = False if theta_func2: - shared.state.textinfo = f"Loading B" + shared.state.textinfo = "Loading B" print(f"Loading {secondary_model_info.filename}...") theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu') else: theta_1 = None if theta_func1: - shared.state.textinfo = f"Loading C" + shared.state.textinfo = "Loading C" print(f"Loading {tertiary_model_info.filename}...") theta_2 = sd_models.read_state_dict(tertiary_model_info.filename, map_location='cpu') @@ -199,7 +199,7 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ result_is_inpainting_model = True else: theta_0[key] = theta_func2(a, b, multiplier) - + theta_0[key] = to_half(theta_0[key], save_as_half) shared.state.sampling_step += 1 diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index fe8b18b2..f1a2204c 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -1,15 +1,11 @@ import base64 -import html import io -import math import os import re -from pathlib import Path import gradio as gr from modules.paths import data_path from modules import shared, ui_tempdir, script_callbacks -import tempfile from PIL import Image re_param_code = r'\s*([\w ]+):\s*("(?:\\"[^,]|\\"|\\|[^\"])+"|[^,]*)(?:,|$)' @@ -23,14 +19,14 @@ registered_param_bindings = [] class ParamBinding: - def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=[]): + def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=None): self.paste_button = paste_button self.tabname = tabname self.source_text_component = source_text_component self.source_image_component = source_image_component self.source_tabname = source_tabname self.override_settings_component = override_settings_component - self.paste_field_names = paste_field_names + self.paste_field_names = paste_field_names or [] def reset(): @@ -251,7 +247,7 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model lines.append(lastline) lastline = '' - for i, line in enumerate(lines): + for line in lines: line = line.strip() if line.startswith("Negative prompt:"): done_with_prompt = True @@ -312,6 +308,8 @@ infotext_to_setting_name_mapping = [ ('UniPC skip type', 'uni_pc_skip_type'), ('UniPC order', 'uni_pc_order'), ('UniPC lower order final', 'uni_pc_lower_order_final'), + ('Token merging ratio', 'token_merging_ratio'), + ('Token merging ratio hr', 'token_merging_ratio_hr'), ('RNG', 'randn_source'), ('NGMS', 's_min_uncond'), ] diff --git a/modules/gfpgan_model.py b/modules/gfpgan_model.py index fbe6215a..0131dea4 100644 --- a/modules/gfpgan_model.py +++ b/modules/gfpgan_model.py @@ -78,7 +78,7 @@ def setup_model(dirname): try: from gfpgan import GFPGANer - from facexlib import detection, parsing + from facexlib import detection, parsing # noqa: F401 global user_path global have_gfpgan global gfpgan_constructor diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 1fc49537..570b5603 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -1,4 +1,3 @@ -import csv import datetime import glob import html @@ -18,7 +17,7 @@ from modules.textual_inversion.learn_schedule import LearnRateScheduler from torch import einsum from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_ -from collections import defaultdict, deque +from collections import deque from statistics import stdev, mean @@ -178,34 +177,34 @@ class Hypernetwork: def weights(self): res = [] - for k, layers in self.layers.items(): + for layers in self.layers.values(): for layer in layers: res += layer.parameters() return res def train(self, mode=True): - for k, layers in self.layers.items(): + for layers in self.layers.values(): for layer in layers: layer.train(mode=mode) for param in layer.parameters(): param.requires_grad = mode def to(self, device): - for k, layers in self.layers.items(): + for layers in self.layers.values(): for layer in layers: layer.to(device) return self def set_multiplier(self, multiplier): - for k, layers in self.layers.items(): + for layers in self.layers.values(): for layer in layers: layer.multiplier = multiplier return self def eval(self): - for k, layers in self.layers.items(): + for layers in self.layers.values(): for layer in layers: layer.eval() for param in layer.parameters(): @@ -404,7 +403,7 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None): k = self.to_k(context_k) v = self.to_v(context_v) - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) + q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q, k, v)) sim = einsum('b i d, b j d -> b i j', q, k) * self.scale @@ -541,7 +540,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi return hypernetwork, filename scheduler = LearnRateScheduler(learn_rate, steps, initial_step) - + clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else None if clip_grad: clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False) @@ -594,7 +593,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi print(e) scaler = torch.cuda.amp.GradScaler() - + batch_size = ds.batch_size gradient_step = ds.gradient_step # n steps = batch_size * gradient_step * n image processed @@ -620,7 +619,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi try: sd_hijack_checkpoint.add() - for i in range((steps-initial_step) * gradient_step): + for _ in range((steps-initial_step) * gradient_step): if scheduler.finished: break if shared.state.interrupted: @@ -637,7 +636,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi if clip_grad: clip_grad_sched.step(hypernetwork.step) - + with devices.autocast(): x = batch.latent_sample.to(devices.device, non_blocking=pin_memory) if use_weight: @@ -658,14 +657,14 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi _loss_step += loss.item() scaler.scale(loss).backward() - + # go back until we reach gradient accumulation steps if (j + 1) % gradient_step != 0: continue loss_logging.append(_loss_step) if clip_grad: clip_grad(weights, clip_grad_sched.learn_rate) - + scaler.step(optimizer) scaler.update() hypernetwork.step += 1 @@ -675,7 +674,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi _loss_step = 0 steps_done = hypernetwork.step + 1 - + epoch_num = hypernetwork.step // steps_per_epoch epoch_step = hypernetwork.step % steps_per_epoch diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py index 76599f5a..8b6255e2 100644 --- a/modules/hypernetworks/ui.py +++ b/modules/hypernetworks/ui.py @@ -1,19 +1,17 @@ import html -import os -import re import gradio as gr import modules.hypernetworks.hypernetwork from modules import devices, sd_hijack, shared not_available = ["hardswish", "multiheadattention"] -keys = list(x for x in modules.hypernetworks.hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available) +keys = [x for x in modules.hypernetworks.hypernetwork.HypernetworkModule.activation_dict if x not in not_available] def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, dropout_structure=None): filename = modules.hypernetworks.hypernetwork.create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure, activation_func, weight_init, add_layer_norm, use_dropout, dropout_structure) - return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {filename}", "" + return gr.Dropdown.update(choices=sorted(shared.hypernetworks)), f"Created: {filename}", "" def train_hypernetwork(*args): diff --git a/modules/images.py b/modules/images.py index a41965ab..b2de3662 100644 --- a/modules/images.py +++ b/modules/images.py @@ -13,17 +13,24 @@ import numpy as np import piexif import piexif.helper from PIL import Image, ImageFont, ImageDraw, PngImagePlugin -from fonts.ttf import Roboto import string import json import hashlib from modules import sd_samplers, shared, script_callbacks, errors -from modules.shared import opts, cmd_opts +from modules.paths_internal import roboto_ttf_file +from modules.shared import opts LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS) +def get_font(fontsize: int): + try: + return ImageFont.truetype(opts.font or roboto_ttf_file, fontsize) + except Exception: + return ImageFont.truetype(roboto_ttf_file, fontsize) + + def image_grid(imgs, batch_size=1, rows=None): if rows is None: if opts.n_rows > 0: @@ -142,14 +149,8 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0): lines.append(word) return lines - def get_font(fontsize): - try: - return ImageFont.truetype(opts.font or Roboto, fontsize) - except Exception: - return ImageFont.truetype(Roboto, fontsize) - def draw_texts(drawing, draw_x, draw_y, lines, initial_fnt, initial_fontsize): - for i, line in enumerate(lines): + for line in lines: fnt = initial_fnt fontsize = initial_fontsize while drawing.multiline_textsize(line.text, font=fnt)[0] > line.allowed_width and fontsize > 0: @@ -366,7 +367,7 @@ class FilenameGenerator: self.seed = seed self.prompt = prompt self.image = image - + def hasprompt(self, *args): lower = self.prompt.lower() if self.p is None or self.prompt is None: @@ -409,13 +410,13 @@ class FilenameGenerator: time_format = args[0] if len(args) > 0 and args[0] != "" else self.default_time_format try: time_zone = pytz.timezone(args[1]) if len(args) > 1 else None - except pytz.exceptions.UnknownTimeZoneError as _: + except pytz.exceptions.UnknownTimeZoneError: time_zone = None time_zone_time = time_datetime.astimezone(time_zone) try: formatted_time = time_zone_time.strftime(time_format) - except (ValueError, TypeError) as _: + except (ValueError, TypeError): formatted_time = time_zone_time.strftime(self.default_time_format) return sanitize_filename_part(formatted_time, replace_spaces=False) @@ -472,9 +473,9 @@ def get_next_sequence_number(path, basename): prefix_length = len(basename) for p in os.listdir(path): if p.startswith(basename): - l = os.path.splitext(p[prefix_length:])[0].split('-') # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element) + parts = os.path.splitext(p[prefix_length:])[0].split('-') # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element) try: - result = max(int(l[0]), result) + result = max(int(parts[0]), result) except ValueError: pass diff --git a/modules/img2img.py b/modules/img2img.py index 9fc3a698..d704bf90 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -1,19 +1,15 @@ -import math import os -import sys -import traceback import numpy as np from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError -from modules import devices, sd_samplers +from modules import sd_samplers from modules.generation_parameters_copypaste import create_override_settings_dict from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images from modules.shared import opts, state import modules.shared as shared import modules.processing as processing from modules.ui import plaintext_to_html -import modules.images as images import modules.scripts @@ -59,7 +55,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args): # try to find corresponding mask for an image using simple filename matching mask_image_path = os.path.join(inpaint_mask_dir, os.path.basename(image)) # if not found use first one ("same mask for all images" use-case) - if not mask_image_path in inpaint_masks: + if mask_image_path not in inpaint_masks: mask_image_path = inpaint_masks[0] mask_image = Image.open(mask_image_path) p.image_mask = mask_image diff --git a/modules/interrogate.py b/modules/interrogate.py index 9f7d657f..111b1322 100644 --- a/modules/interrogate.py +++ b/modules/interrogate.py @@ -11,7 +11,6 @@ import torch.hub from torchvision import transforms from torchvision.transforms.functional import InterpolationMode -import modules.shared as shared from modules import devices, paths, shared, lowvram, modelloader, errors blip_image_eval_size = 384 @@ -160,7 +159,7 @@ class InterrogateModels: text_array = text_array[0:int(shared.opts.interrogate_clip_dict_limit)] top_count = min(top_count, len(text_array)) - text_tokens = clip.tokenize([text for text in text_array], truncate=True).to(devices.device_interrogate) + text_tokens = clip.tokenize(list(text_array), truncate=True).to(devices.device_interrogate) text_features = self.clip_model.encode_text(text_tokens).type(self.dtype) text_features /= text_features.norm(dim=-1, keepdim=True) @@ -208,8 +207,8 @@ class InterrogateModels: image_features /= image_features.norm(dim=-1, keepdim=True) - for name, topn, items in self.categories(): - matches = self.rank(image_features, items, top_count=topn) + for cat in self.categories(): + matches = self.rank(image_features, cat.items, top_count=cat.topn) for match, score in matches: if shared.opts.interrogate_return_ranks: res += f", ({match}:{score/100:.3f})" diff --git a/modules/localization.py b/modules/localization.py index f6a6f2fb..ee9c65e7 100644 --- a/modules/localization.py +++ b/modules/localization.py @@ -23,7 +23,7 @@ def list_localizations(dirname): localizations[fn] = file.path -def localization_js(current_localization_name): +def localization_js(current_localization_name: str) -> str: fn = localizations.get(current_localization_name, None) data = {} if fn is not None: @@ -34,4 +34,4 @@ def localization_js(current_localization_name): print(f"Error loading localization from {fn}:", file=sys.stderr) print(traceback.format_exc(), file=sys.stderr) - return f"var localization = {json.dumps(data)}\n" + return f"window.localization = {json.dumps(data)}" diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 40ce2101..d74c6b95 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -1,6 +1,5 @@ import torch import platform -from modules import paths from modules.sd_hijack_utils import CondFunc from packaging import version @@ -43,7 +42,7 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/79383 CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs), lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')) - # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 + # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs), lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps') # MPS workaround for https://github.com/pytorch/pytorch/issues/90532 @@ -61,4 +60,4 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/92311 if platform.processor() == 'i386': for funcName in ['torch.argmax', 'torch.Tensor.argmax']: - CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps') \ No newline at end of file + CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps') diff --git a/modules/masking.py b/modules/masking.py index a5c4d2da..be9f84c7 100644 --- a/modules/masking.py +++ b/modules/masking.py @@ -4,7 +4,7 @@ from PIL import Image, ImageFilter, ImageOps def get_crop_region(mask, pad=0): """finds a rectangular region that contains all masked ares in an image. Returns (x1, y1, x2, y2) coordinates of the rectangle. For example, if a user has painted the top-right part of a 512x512 image", the result may be (256, 0, 512, 256)""" - + h, w = mask.shape crop_left = 0 diff --git a/modules/modelloader.py b/modules/modelloader.py index cb85ac4f..2a479bcb 100644 --- a/modules/modelloader.py +++ b/modules/modelloader.py @@ -1,4 +1,3 @@ -import glob import os import shutil import importlib @@ -40,7 +39,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None if os.path.islink(full_path) and not os.path.exists(full_path): print(f"Skipping broken symlink: {full_path}") continue - if ext_blacklist is not None and any([full_path.endswith(x) for x in ext_blacklist]): + if ext_blacklist is not None and any(full_path.endswith(x) for x in ext_blacklist): continue if full_path not in output: output.append(full_path) @@ -108,29 +107,15 @@ def move_files(src_path: str, dest_path: str, ext_filter: str = None): print(f"Moving {file} from {src_path} to {dest_path}.") try: shutil.move(fullpath, dest_path) - except: + except Exception: pass if len(os.listdir(src_path)) == 0: print(f"Removing empty folder: {src_path}") shutil.rmtree(src_path, True) - except: + except Exception: pass -builtin_upscaler_classes = [] -forbidden_upscaler_classes = set() - - -def list_builtin_upscalers(): - builtin_upscaler_classes.clear() - builtin_upscaler_classes.extend(Upscaler.__subclasses__()) - -def forbid_loaded_nonbuiltin_upscalers(): - for cls in Upscaler.__subclasses__(): - if cls not in builtin_upscaler_classes: - forbidden_upscaler_classes.add(cls) - - def load_upscalers(): # We can only do this 'magic' method to dynamically load upscalers if they are referenced, # so we'll try to import any _model.py files before looking in __subclasses__ @@ -141,15 +126,22 @@ def load_upscalers(): full_model = f"modules.{model_name}_model" try: importlib.import_module(full_model) - except: + except Exception: pass datas = [] commandline_options = vars(shared.cmd_opts) - for cls in Upscaler.__subclasses__(): - if cls in forbidden_upscaler_classes: - continue + # some of upscaler classes will not go away after reloading their modules, and we'll end + # up with two copies of those classes. The newest copy will always be the last in the list, + # so we go from end to beginning and ignore duplicates + used_classes = {} + for cls in reversed(Upscaler.__subclasses__()): + classname = str(cls) + if classname not in used_classes: + used_classes[classname] = cls + + for cls in reversed(used_classes.values()): name = cls.__name__ cmd_name = f"{name.lower().replace('upscaler', '')}_models_path" scaler = cls(commandline_options.get(cmd_name, None)) diff --git a/modules/models/diffusion/ddpm_edit.py b/modules/models/diffusion/ddpm_edit.py index f880bc3c..3fb76b65 100644 --- a/modules/models/diffusion/ddpm_edit.py +++ b/modules/models/diffusion/ddpm_edit.py @@ -52,7 +52,7 @@ class DDPM(pl.LightningModule): beta_schedule="linear", loss_type="l2", ckpt_path=None, - ignore_keys=[], + ignore_keys=None, load_only_unet=False, monitor="val/loss", use_ema=True, @@ -107,7 +107,7 @@ class DDPM(pl.LightningModule): print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.") if ckpt_path is not None: - self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet) + self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet) # If initialing from EMA-only checkpoint, create EMA model after loading. if self.use_ema and not load_ema: @@ -194,7 +194,9 @@ class DDPM(pl.LightningModule): if context is not None: print(f"{context}: Restored training weights") - def init_from_ckpt(self, path, ignore_keys=list(), only_model=False): + def init_from_ckpt(self, path, ignore_keys=None, only_model=False): + ignore_keys = ignore_keys or [] + sd = torch.load(path, map_location="cpu") if "state_dict" in list(sd.keys()): sd = sd["state_dict"] @@ -403,7 +405,7 @@ class DDPM(pl.LightningModule): @torch.no_grad() def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs): - log = dict() + log = {} x = self.get_input(batch, self.first_stage_key) N = min(x.shape[0], N) n_row = min(x.shape[0], n_row) @@ -411,7 +413,7 @@ class DDPM(pl.LightningModule): log["inputs"] = x # get diffusion row - diffusion_row = list() + diffusion_row = [] x_start = x[:n_row] for t in range(self.num_timesteps): @@ -473,13 +475,13 @@ class LatentDiffusion(DDPM): conditioning_key = None ckpt_path = kwargs.pop("ckpt_path", None) ignore_keys = kwargs.pop("ignore_keys", []) - super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs) + super().__init__(*args, conditioning_key=conditioning_key, load_ema=load_ema, **kwargs) self.concat_mode = concat_mode self.cond_stage_trainable = cond_stage_trainable self.cond_stage_key = cond_stage_key try: self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1 - except: + except Exception: self.num_downs = 0 if not scale_by_std: self.scale_factor = scale_factor @@ -891,16 +893,6 @@ class LatentDiffusion(DDPM): c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float())) return self.p_losses(x, c, t, *args, **kwargs) - def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset - def rescale_bbox(bbox): - x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2]) - y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3]) - w = min(bbox[2] / crop_coordinates[2], 1 - x0) - h = min(bbox[3] / crop_coordinates[3], 1 - y0) - return x0, y0, w, h - - return [rescale_bbox(b) for b in bboxes] - def apply_model(self, x_noisy, t, cond, return_ids=False): if isinstance(cond, dict): @@ -1140,7 +1132,7 @@ class LatentDiffusion(DDPM): if cond is not None: if isinstance(cond, dict): cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else - list(map(lambda x: x[:batch_size], cond[key])) for key in cond} + [x[:batch_size] for x in cond[key]] for key in cond} else: cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size] @@ -1171,8 +1163,10 @@ class LatentDiffusion(DDPM): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(x0_partial) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) return img, intermediates @torch.no_grad() @@ -1219,8 +1213,10 @@ class LatentDiffusion(DDPM): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(img) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) if return_intermediates: return img, intermediates @@ -1235,7 +1231,7 @@ class LatentDiffusion(DDPM): if cond is not None: if isinstance(cond, dict): cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else - list(map(lambda x: x[:batch_size], cond[key])) for key in cond} + [x[:batch_size] for x in cond[key]] for key in cond} else: cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size] return self.p_sample_loop(cond, @@ -1267,7 +1263,7 @@ class LatentDiffusion(DDPM): use_ddim = False - log = dict() + log = {} z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key, return_first_stage_outputs=True, force_c_encode=True, @@ -1295,7 +1291,7 @@ class LatentDiffusion(DDPM): if plot_diffusion_rows: # get diffusion row - diffusion_row = list() + diffusion_row = [] z_start = z[:n_row] for t in range(self.num_timesteps): if t % self.log_every_t == 0 or t == self.num_timesteps - 1: @@ -1337,7 +1333,7 @@ class LatentDiffusion(DDPM): if inpaint: # make a simple center square - b, h, w = z.shape[0], z.shape[2], z.shape[3] + h, w = z.shape[2], z.shape[3] mask = torch.ones(N, h, w).to(self.device) # zeros will be filled in mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0. @@ -1439,10 +1435,10 @@ class Layout2ImgDiffusion(LatentDiffusion): # TODO: move all layout-specific hacks to this class def __init__(self, cond_stage_key, *args, **kwargs): assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"' - super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs) + super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs) def log_images(self, batch, N=8, *args, **kwargs): - logs = super().log_images(batch=batch, N=N, *args, **kwargs) + logs = super().log_images(*args, batch=batch, N=N, **kwargs) key = 'train' if self.training else 'validation' dset = self.trainer.datamodule.datasets[key] diff --git a/modules/models/diffusion/uni_pc/__init__.py b/modules/models/diffusion/uni_pc/__init__.py index e1265e3f..dbb35964 100644 --- a/modules/models/diffusion/uni_pc/__init__.py +++ b/modules/models/diffusion/uni_pc/__init__.py @@ -1 +1 @@ -from .sampler import UniPCSampler +from .sampler import UniPCSampler # noqa: F401 diff --git a/modules/models/diffusion/uni_pc/sampler.py b/modules/models/diffusion/uni_pc/sampler.py index a241c8a7..0a9defa1 100644 --- a/modules/models/diffusion/uni_pc/sampler.py +++ b/modules/models/diffusion/uni_pc/sampler.py @@ -54,7 +54,8 @@ class UniPCSampler(object): if conditioning is not None: if isinstance(conditioning, dict): ctmp = conditioning[list(conditioning.keys())[0]] - while isinstance(ctmp, list): ctmp = ctmp[0] + while isinstance(ctmp, list): + ctmp = ctmp[0] cbs = ctmp.shape[0] if cbs != batch_size: print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") diff --git a/modules/models/diffusion/uni_pc/uni_pc.py b/modules/models/diffusion/uni_pc/uni_pc.py index 11b330bc..d257a728 100644 --- a/modules/models/diffusion/uni_pc/uni_pc.py +++ b/modules/models/diffusion/uni_pc/uni_pc.py @@ -1,7 +1,6 @@ import torch -import torch.nn.functional as F import math -from tqdm.auto import trange +import tqdm class NoiseScheduleVP: @@ -179,13 +178,13 @@ def model_wrapper( model, noise_schedule, model_type="noise", - model_kwargs={}, + model_kwargs=None, guidance_type="uncond", #condition=None, #unconditional_condition=None, guidance_scale=1., classifier_fn=None, - classifier_kwargs={}, + classifier_kwargs=None, ): """Create a wrapper function for the noise prediction model. @@ -276,6 +275,9 @@ def model_wrapper( A noise prediction model that accepts the noised data and the continuous time as the inputs. """ + model_kwargs = model_kwargs or {} + classifier_kwargs = classifier_kwargs or {} + def get_model_input_time(t_continuous): """ Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. @@ -342,7 +344,7 @@ def model_wrapper( t_in = torch.cat([t_continuous] * 2) if isinstance(condition, dict): assert isinstance(unconditional_condition, dict) - c_in = dict() + c_in = {} for k in condition: if isinstance(condition[k], list): c_in[k] = [torch.cat([ @@ -353,7 +355,7 @@ def model_wrapper( unconditional_condition[k], condition[k]]) elif isinstance(condition, list): - c_in = list() + c_in = [] assert isinstance(unconditional_condition, list) for i in range(len(condition)): c_in.append(torch.cat([unconditional_condition[i], condition[i]])) @@ -757,40 +759,44 @@ class UniPC: vec_t = timesteps[0].expand((x.shape[0])) model_prev_list = [self.model_fn(x, vec_t)] t_prev_list = [vec_t] - # Init the first `order` values by lower order multistep DPM-Solver. - for init_order in range(1, order): - vec_t = timesteps[init_order].expand(x.shape[0]) - x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, init_order, use_corrector=True) - if model_x is None: - model_x = self.model_fn(x, vec_t) - if self.after_update is not None: - self.after_update(x, model_x) - model_prev_list.append(model_x) - t_prev_list.append(vec_t) - for step in trange(order, steps + 1): - vec_t = timesteps[step].expand(x.shape[0]) - if lower_order_final: - step_order = min(order, steps + 1 - step) - else: - step_order = order - #print('this step order:', step_order) - if step == steps: - #print('do not run corrector at the last step') - use_corrector = False - else: - use_corrector = True - x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, step_order, use_corrector=use_corrector) - if self.after_update is not None: - self.after_update(x, model_x) - for i in range(order - 1): - t_prev_list[i] = t_prev_list[i + 1] - model_prev_list[i] = model_prev_list[i + 1] - t_prev_list[-1] = vec_t - # We do not need to evaluate the final model value. - if step < steps: + with tqdm.tqdm(total=steps) as pbar: + # Init the first `order` values by lower order multistep DPM-Solver. + for init_order in range(1, order): + vec_t = timesteps[init_order].expand(x.shape[0]) + x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, init_order, use_corrector=True) if model_x is None: model_x = self.model_fn(x, vec_t) - model_prev_list[-1] = model_x + if self.after_update is not None: + self.after_update(x, model_x) + model_prev_list.append(model_x) + t_prev_list.append(vec_t) + pbar.update() + + for step in range(order, steps + 1): + vec_t = timesteps[step].expand(x.shape[0]) + if lower_order_final: + step_order = min(order, steps + 1 - step) + else: + step_order = order + #print('this step order:', step_order) + if step == steps: + #print('do not run corrector at the last step') + use_corrector = False + else: + use_corrector = True + x, model_x = self.multistep_uni_pc_update(x, model_prev_list, t_prev_list, vec_t, step_order, use_corrector=use_corrector) + if self.after_update is not None: + self.after_update(x, model_x) + for i in range(order - 1): + t_prev_list[i] = t_prev_list[i + 1] + model_prev_list[i] = model_prev_list[i + 1] + t_prev_list[-1] = vec_t + # We do not need to evaluate the final model value. + if step < steps: + if model_x is None: + model_x = self.model_fn(x, vec_t) + model_prev_list[-1] = model_x + pbar.update() else: raise NotImplementedError() if denoise_to_zero: diff --git a/modules/ngrok.py b/modules/ngrok.py index 7a7b4b26..67a74e85 100644 --- a/modules/ngrok.py +++ b/modules/ngrok.py @@ -13,7 +13,7 @@ def connect(token, port, region): config = conf.PyngrokConfig( auth_token=token, region=region ) - + # Guard for existing tunnels existing = ngrok.get_tunnels(pyngrok_config=config) if existing: @@ -24,7 +24,7 @@ def connect(token, port, region): print(f'ngrok has already been connected to localhost:{port}! URL: {public_url}\n' 'You can use this link after the launch is complete.') return - + try: if account is None: public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url diff --git a/modules/paths.py b/modules/paths.py index acf1894b..5f6474c0 100644 --- a/modules/paths.py +++ b/modules/paths.py @@ -1,8 +1,8 @@ import os import sys -from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir +from modules.paths_internal import models_path, script_path, data_path, extensions_dir, extensions_builtin_dir # noqa: F401 -import modules.safe +import modules.safe # noqa: F401 # data_path = cmd_opts_pre.data diff --git a/modules/paths_internal.py b/modules/paths_internal.py index 6765bafe..005a9b0a 100644 --- a/modules/paths_internal.py +++ b/modules/paths_internal.py @@ -2,8 +2,14 @@ import argparse import os +import sys +import shlex -script_path = os.path.dirname(os.path.dirname(os.path.realpath(__file__))) +commandline_args = os.environ.get('COMMANDLINE_ARGS', "") +sys.argv += shlex.split(commandline_args) + +modules_path = os.path.dirname(os.path.realpath(__file__)) +script_path = os.path.dirname(modules_path) sd_configs_path = os.path.join(script_path, "configs") sd_default_config = os.path.join(sd_configs_path, "v1-inference.yaml") @@ -12,7 +18,7 @@ default_sd_model_file = sd_model_file # Parse the --data-dir flag first so we can use it as a base for our other argument default values parser_pre = argparse.ArgumentParser(add_help=False) -parser_pre.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored",) +parser_pre.add_argument("--data-dir", type=str, default=os.path.dirname(modules_path), help="base path where all user data is stored", ) cmd_opts_pre = parser_pre.parse_known_args()[0] data_path = cmd_opts_pre.data_dir @@ -21,3 +27,5 @@ models_path = os.path.join(data_path, "models") extensions_dir = os.path.join(data_path, "extensions") extensions_builtin_dir = os.path.join(script_path, "extensions-builtin") config_states_dir = os.path.join(script_path, "config_states") + +roboto_ttf_file = os.path.join(modules_path, 'Roboto-Regular.ttf') diff --git a/modules/processing.py b/modules/processing.py index 1a76e552..678c4468 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -2,7 +2,6 @@ import json import math import os import sys -import warnings import hashlib import torch @@ -11,10 +10,10 @@ from PIL import Image, ImageFilter, ImageOps import random import cv2 from skimage import exposure -from typing import Any, Dict, List, Optional +from typing import Any, Dict, List import modules.sd_hijack -from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks, extra_networks, sd_vae_approx, scripts +from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common from modules.sd_hijack import model_hijack from modules.shared import opts, cmd_opts, state import modules.shared as shared @@ -30,6 +29,13 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion from einops import repeat, rearrange from blendmodes.blend import blendLayers, BlendType +import tomesd + +# add a logger for the processing module +logger = logging.getLogger(__name__) +# manually set output level here since there is no option to do so yet through launch options +# logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)s %(name)s %(message)s') + # some of those options should not be changed at all because they would break the model, so I removed them from options. opt_C = 4 @@ -165,7 +171,7 @@ class StableDiffusionProcessing: self.all_subseeds = None self.iteration = 0 self.is_hr_pass = False - + @property def sd_model(self): @@ -472,6 +478,11 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter index = position_in_batch + iteration * p.batch_size clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers) + enable_hr = getattr(p, 'enable_hr', False) + + uses_ensd = opts.eta_noise_seed_delta != 0 + if uses_ensd: + uses_ensd = sd_samplers_common.is_sampler_using_eta_noise_seed_delta(p) generation_params = { "Steps": p.steps, @@ -489,15 +500,16 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Denoising strength": getattr(p, 'denoising_strength', None), "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None, "Clip skip": None if clip_skip <= 1 else clip_skip, - "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, + "ENSD": opts.eta_noise_seed_delta if uses_ensd else None, + "Token merging ratio": None if opts.token_merging_ratio == 0 else opts.token_merging_ratio, + "Token merging ratio hr": None if not enable_hr or opts.token_merging_ratio_hr == 0 else opts.token_merging_ratio_hr, "Init image hash": getattr(p, 'init_img_hash', None), "RNG": opts.randn_source if opts.randn_source != "GPU" else None, "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond, + **p.extra_generation_params, "Version": program_version() if opts.add_version_to_infotext else None, } - generation_params.update(p.extra_generation_params) - generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None]) negative_prompt_text = f"\nNegative prompt: {p.all_negative_prompts[index]}" if p.all_negative_prompts[index] else "" @@ -523,9 +535,18 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if k == 'sd_vae': sd_vae.reload_vae_weights() + if opts.token_merging_ratio > 0: + sd_models.apply_token_merging(sd_model=p.sd_model, hr=False) + logger.debug(f"Token merging applied to first pass. Ratio: '{opts.token_merging_ratio}'") + res = process_images_inner(p) finally: + # undo model optimizations made by tomesd + if opts.token_merging_ratio > 0: + tomesd.remove_patch(p.sd_model) + logger.debug('Token merging model optimizations removed') + # restore opts to original state if p.override_settings_restore_afterwards: for k, v in stored_opts.items(): @@ -660,12 +681,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: processed = Processed(p, [], p.seed, "") file.write(processed.infotext(p, 0)) - step_multiplier = 1 - if not shared.opts.dont_fix_second_order_samplers_schedule: - try: - step_multiplier = 2 if sd_samplers.all_samplers_map.get(p.sampler_name).aliases[0] in ['k_dpmpp_2s_a', 'k_dpmpp_2s_a_ka', 'k_dpmpp_sde', 'k_dpmpp_sde_ka', 'k_dpm_2', 'k_dpm_2_a', 'k_heun'] else 1 - except: - pass + sampler_config = sd_samplers.find_sampler_config(p.sampler_name) + step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1 uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc) c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps * step_multiplier, cached_c) @@ -978,8 +995,22 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() + # apply token merging optimizations from tomesd for high-res pass + if opts.token_merging_ratio_hr > 0: + # in case the user has used separate merge ratios + if opts.token_merging_ratio > 0: + tomesd.remove_patch(self.sd_model) + logger.debug('Adjusting token merging ratio for high-res pass') + + sd_models.apply_token_merging(sd_model=self.sd_model, hr=True) + logger.debug(f"Applied token merging for high-res pass. Ratio: '{opts.token_merging_ratio_hr}'") + samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning) + if opts.token_merging_ratio_hr > 0 or opts.token_merging_ratio > 0: + tomesd.remove_patch(self.sd_model) + logger.debug('Removed token merging optimizations from model') + self.is_hr_pass = False return samples diff --git a/modules/progress.py b/modules/progress.py index 948e6f00..269863c9 100644 --- a/modules/progress.py +++ b/modules/progress.py @@ -95,9 +95,16 @@ def progressapi(req: ProgressRequest): image = shared.state.current_image if image is not None: buffered = io.BytesIO() - image.save(buffered, format="png") + + if opts.live_previews_image_format == "png": + # using optimize for large images takes an enormous amount of time + save_kwargs = {"optimize": max(*image.size) > 256} + else: + save_kwargs = {} + + image.save(buffered, format=opts.live_previews_image_format, **save_kwargs) base64_image = base64.b64encode(buffered.getvalue()).decode('ascii') - live_preview = f"data:image/png;base64,{base64_image}" + live_preview = f"data:image/{opts.live_previews_image_format};base64,{base64_image}" id_live_preview = shared.state.id_live_preview else: live_preview = None diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index 69665372..b4aff704 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -54,18 +54,21 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): """ def collect_steps(steps, tree): - l = [steps] + res = [steps] + class CollectSteps(lark.Visitor): def scheduled(self, tree): tree.children[-1] = float(tree.children[-1]) if tree.children[-1] < 1: tree.children[-1] *= steps tree.children[-1] = min(steps, int(tree.children[-1])) - l.append(tree.children[-1]) + res.append(tree.children[-1]) + def alternate(self, tree): - l.extend(range(1, steps+1)) + res.extend(range(1, steps+1)) + CollectSteps().visit(tree) - return sorted(set(l)) + return sorted(set(res)) def at_step(step, tree): class AtStep(lark.Transformer): @@ -92,7 +95,7 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): def get_schedule(prompt): try: tree = schedule_parser.parse(prompt) - except lark.exceptions.LarkError as e: + except lark.exceptions.LarkError: if 0: import traceback traceback.print_exc() @@ -140,7 +143,7 @@ def get_learned_conditioning(model, prompts, steps): conds = model.get_learned_conditioning(texts) cond_schedule = [] - for i, (end_at_step, text) in enumerate(prompt_schedule): + for i, (end_at_step, _) in enumerate(prompt_schedule): cond_schedule.append(ScheduledPromptConditioning(end_at_step, conds[i])) cache[prompt] = cond_schedule @@ -216,8 +219,8 @@ def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_s res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype) for i, cond_schedule in enumerate(c): target_index = 0 - for current, (end_at, cond) in enumerate(cond_schedule): - if current_step <= end_at: + for current, entry in enumerate(cond_schedule): + if current_step <= entry.end_at_step: target_index = current break res[i] = cond_schedule[target_index].cond @@ -231,13 +234,13 @@ def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step): tensors = [] conds_list = [] - for batch_no, composable_prompts in enumerate(c.batch): + for composable_prompts in c.batch: conds_for_batch = [] - for cond_index, composable_prompt in enumerate(composable_prompts): + for composable_prompt in composable_prompts: target_index = 0 - for current, (end_at, cond) in enumerate(composable_prompt.schedules): - if current_step <= end_at: + for current, entry in enumerate(composable_prompt.schedules): + if current_step <= entry.end_at_step: target_index = current break diff --git a/modules/realesrgan_model.py b/modules/realesrgan_model.py index efd7fca5..c24d8dbb 100644 --- a/modules/realesrgan_model.py +++ b/modules/realesrgan_model.py @@ -17,9 +17,9 @@ class UpscalerRealESRGAN(Upscaler): self.user_path = path super().__init__() try: - from basicsr.archs.rrdbnet_arch import RRDBNet - from realesrgan import RealESRGANer - from realesrgan.archs.srvgg_arch import SRVGGNetCompact + from basicsr.archs.rrdbnet_arch import RRDBNet # noqa: F401 + from realesrgan import RealESRGANer # noqa: F401 + from realesrgan.archs.srvgg_arch import SRVGGNetCompact # noqa: F401 self.enable = True self.scalers = [] scalers = self.load_models(path) @@ -134,6 +134,6 @@ def get_realesrgan_models(scaler): ), ] return models - except Exception as e: + except Exception: print("Error making Real-ESRGAN models list:", file=sys.stderr) print(traceback.format_exc(), file=sys.stderr) diff --git a/modules/safe.py b/modules/safe.py index e6c2f2c0..e8f50774 100644 --- a/modules/safe.py +++ b/modules/safe.py @@ -40,7 +40,7 @@ class RestrictedUnpickler(pickle.Unpickler): return getattr(collections, name) if module == 'torch._utils' and name in ['_rebuild_tensor_v2', '_rebuild_parameter', '_rebuild_device_tensor_from_numpy']: return getattr(torch._utils, name) - if module == 'torch' and name in ['FloatStorage', 'HalfStorage', 'IntStorage', 'LongStorage', 'DoubleStorage', 'ByteStorage', 'float32']: + if module == 'torch' and name in ['FloatStorage', 'HalfStorage', 'IntStorage', 'LongStorage', 'DoubleStorage', 'ByteStorage', 'float32', 'BFloat16Storage']: return getattr(torch, name) if module == 'torch.nn.modules.container' and name in ['ParameterDict']: return getattr(torch.nn.modules.container, name) @@ -95,16 +95,16 @@ def check_pt(filename, extra_handler): except zipfile.BadZipfile: - # if it's not a zip file, it's an olf pytorch format, with five objects written to pickle + # if it's not a zip file, it's an old pytorch format, with five objects written to pickle with open(filename, "rb") as file: unpickler = RestrictedUnpickler(file) unpickler.extra_handler = extra_handler - for i in range(5): + for _ in range(5): unpickler.load() def load(filename, *args, **kwargs): - return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs) + return load_with_extra(filename, *args, extra_handler=global_extra_handler, **kwargs) def load_with_extra(filename, extra_handler=None, *args, **kwargs): diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index 17109732..3c21a362 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -32,27 +32,42 @@ class CFGDenoiserParams: def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond): self.x = x """Latent image representation in the process of being denoised""" - + self.image_cond = image_cond """Conditioning image""" - + self.sigma = sigma """Current sigma noise step value""" - + self.sampling_step = sampling_step """Current Sampling step number""" - + self.total_sampling_steps = total_sampling_steps """Total number of sampling steps planned""" - + self.text_cond = text_cond """ Encoder hidden states of text conditioning from prompt""" - + self.text_uncond = text_uncond """ Encoder hidden states of text conditioning from negative prompt""" class CFGDenoisedParams: + def __init__(self, x, sampling_step, total_sampling_steps, inner_model): + self.x = x + """Latent image representation in the process of being denoised""" + + self.sampling_step = sampling_step + """Current Sampling step number""" + + self.total_sampling_steps = total_sampling_steps + """Total number of sampling steps planned""" + + self.inner_model = inner_model + """Inner model reference used for denoising""" + + +class AfterCFGCallbackParams: def __init__(self, x, sampling_step, total_sampling_steps): self.x = x """Latent image representation in the process of being denoised""" @@ -87,6 +102,7 @@ callback_map = dict( callbacks_image_saved=[], callbacks_cfg_denoiser=[], callbacks_cfg_denoised=[], + callbacks_cfg_after_cfg=[], callbacks_before_component=[], callbacks_after_component=[], callbacks_image_grid=[], @@ -186,6 +202,14 @@ def cfg_denoised_callback(params: CFGDenoisedParams): report_exception(c, 'cfg_denoised_callback') +def cfg_after_cfg_callback(params: AfterCFGCallbackParams): + for c in callback_map['callbacks_cfg_after_cfg']: + try: + c.callback(params) + except Exception: + report_exception(c, 'cfg_after_cfg_callback') + + def before_component_callback(component, **kwargs): for c in callback_map['callbacks_before_component']: try: @@ -240,7 +264,7 @@ def add_callback(callbacks, fun): callbacks.append(ScriptCallback(filename, fun)) - + def remove_current_script_callbacks(): stack = [x for x in inspect.stack() if x.filename != __file__] filename = stack[0].filename if len(stack) > 0 else 'unknown file' @@ -332,6 +356,14 @@ def on_cfg_denoised(callback): add_callback(callback_map['callbacks_cfg_denoised'], callback) +def on_cfg_after_cfg(callback): + """register a function to be called in the kdiffussion cfg_denoiser method after cfg calculations are completed. + The callback is called with one argument: + - params: AfterCFGCallbackParams - parameters to be passed to the script for post-processing after cfg calculation. + """ + add_callback(callback_map['callbacks_cfg_after_cfg'], callback) + + def on_before_component(callback): """register a function to be called before a component is created. The callback is called with arguments: diff --git a/modules/script_loading.py b/modules/script_loading.py index a7d2203f..57b15862 100644 --- a/modules/script_loading.py +++ b/modules/script_loading.py @@ -2,7 +2,6 @@ import os import sys import traceback import importlib.util -from types import ModuleType def load_module(path): diff --git a/modules/scripts.py b/modules/scripts.py index d945b89f..0c12ebd5 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -231,7 +231,7 @@ def load_scripts(): syspath = sys.path def register_scripts_from_module(module): - for key, script_class in module.__dict__.items(): + for script_class in module.__dict__.values(): if type(script_class) != type: continue @@ -295,9 +295,9 @@ class ScriptRunner: auto_processing_scripts = scripts_auto_postprocessing.create_auto_preprocessing_script_data() - for script_class, path, basedir, script_module in auto_processing_scripts + scripts_data: - script = script_class() - script.filename = path + for script_data in auto_processing_scripts + scripts_data: + script = script_data.script_class() + script.filename = script_data.path script.is_txt2img = not is_img2img script.is_img2img = is_img2img @@ -492,7 +492,7 @@ class ScriptRunner: module = script_loading.load_module(script.filename) cache[filename] = module - for key, script_class in module.__dict__.items(): + for script_class in module.__dict__.values(): if type(script_class) == type and issubclass(script_class, Script): self.scripts[si] = script_class() self.scripts[si].filename = filename diff --git a/modules/scripts_auto_postprocessing.py b/modules/scripts_auto_postprocessing.py index 30d6d658..d63078de 100644 --- a/modules/scripts_auto_postprocessing.py +++ b/modules/scripts_auto_postprocessing.py @@ -17,7 +17,7 @@ class ScriptPostprocessingForMainUI(scripts.Script): return self.postprocessing_controls.values() def postprocess_image(self, p, script_pp, *args): - args_dict = {k: v for k, v in zip(self.postprocessing_controls, args)} + args_dict = dict(zip(self.postprocessing_controls, args)) pp = scripts_postprocessing.PostprocessedImage(script_pp.image) pp.info = {} diff --git a/modules/scripts_postprocessing.py b/modules/scripts_postprocessing.py index b11568c0..bac1335d 100644 --- a/modules/scripts_postprocessing.py +++ b/modules/scripts_postprocessing.py @@ -66,9 +66,9 @@ class ScriptPostprocessingRunner: def initialize_scripts(self, scripts_data): self.scripts = [] - for script_class, path, basedir, script_module in scripts_data: - script: ScriptPostprocessing = script_class() - script.filename = path + for script_data in scripts_data: + script: ScriptPostprocessing = script_data.script_class() + script.filename = script_data.path if script.name == "Simple Upscale": continue @@ -124,7 +124,7 @@ class ScriptPostprocessingRunner: script_args = args[script.args_from:script.args_to] process_args = {} - for (name, component), value in zip(script.controls.items(), script_args): + for (name, _component), value in zip(script.controls.items(), script_args): process_args[name] = value script.process(pp, **process_args) diff --git a/modules/sd_disable_initialization.py b/modules/sd_disable_initialization.py index c4a09d15..9fc89dc6 100644 --- a/modules/sd_disable_initialization.py +++ b/modules/sd_disable_initialization.py @@ -61,7 +61,7 @@ class DisableInitialization: if res is None: res = original(url, *args, local_files_only=False, **kwargs) return res - except Exception as e: + except Exception: return original(url, *args, local_files_only=False, **kwargs) def transformers_utils_hub_get_from_cache(url, *args, local_files_only=False, **kwargs): diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index f4bb0266..14e7f799 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -3,7 +3,7 @@ from torch.nn.functional import silu from types import MethodType import modules.textual_inversion.textual_inversion -from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint +from modules import devices, sd_hijack_optimizations, shared from modules.hypernetworks import hypernetwork from modules.shared import cmd_opts from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr @@ -34,10 +34,10 @@ def apply_optimizations(): ldm.modules.diffusionmodules.model.nonlinearity = silu ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th - + optimization_method = None - can_use_sdp = hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(getattr(torch.nn.functional, "scaled_dot_product_attention")) # not everyone has torch 2.x to use sdp + can_use_sdp = hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(torch.nn.functional.scaled_dot_product_attention) # not everyone has torch 2.x to use sdp if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)): print("Applying xformers cross attention optimization.") @@ -92,12 +92,12 @@ def fix_checkpoint(): def weighted_loss(sd_model, pred, target, mean=True): #Calculate the weight normally, but ignore the mean loss = sd_model._old_get_loss(pred, target, mean=False) - + #Check if we have weights available weight = getattr(sd_model, '_custom_loss_weight', None) if weight is not None: loss *= weight - + #Return the loss, as mean if specified return loss.mean() if mean else loss @@ -105,7 +105,7 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs): try: #Temporarily append weights to a place accessible during loss calc sd_model._custom_loss_weight = w - + #Replace 'get_loss' with a weight-aware one. Otherwise we need to reimplement 'forward' completely #Keep 'get_loss', but don't overwrite the previous old_get_loss if it's already set if not hasattr(sd_model, '_old_get_loss'): @@ -118,9 +118,9 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs): try: #Delete temporary weights if appended del sd_model._custom_loss_weight - except AttributeError as e: + except AttributeError: pass - + #If we have an old loss function, reset the loss function to the original one if hasattr(sd_model, '_old_get_loss'): sd_model.get_loss = sd_model._old_get_loss @@ -133,7 +133,7 @@ def apply_weighted_forward(sd_model): def undo_weighted_forward(sd_model): try: del sd_model.weighted_forward - except AttributeError as e: + except AttributeError: pass @@ -184,7 +184,7 @@ class StableDiffusionModelHijack: def undo_hijack(self, m): if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation: - m.cond_stage_model = m.cond_stage_model.wrapped + m.cond_stage_model = m.cond_stage_model.wrapped elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords: m.cond_stage_model = m.cond_stage_model.wrapped @@ -216,6 +216,9 @@ class StableDiffusionModelHijack: self.comments = [] def get_prompt_lengths(self, text): + if self.clip is None: + return "-", "-" + _, token_count = self.clip.process_texts([text]) return token_count, self.clip.get_target_prompt_token_count(token_count) diff --git a/modules/sd_hijack_clip.py b/modules/sd_hijack_clip.py index 9fa5c5c5..cc6e8c21 100644 --- a/modules/sd_hijack_clip.py +++ b/modules/sd_hijack_clip.py @@ -223,7 +223,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module): self.hijack.fixes = [x.fixes for x in batch_chunk] for fixes in self.hijack.fixes: - for position, embedding in fixes: + for _position, embedding in fixes: used_embeddings[embedding.name] = embedding z = self.process_tokens(tokens, multipliers) diff --git a/modules/sd_hijack_inpainting.py b/modules/sd_hijack_inpainting.py index 55a2ce4d..c1977b19 100644 --- a/modules/sd_hijack_inpainting.py +++ b/modules/sd_hijack_inpainting.py @@ -1,16 +1,10 @@ -import os import torch -from einops import repeat -from omegaconf import ListConfig - import ldm.models.diffusion.ddpm import ldm.models.diffusion.ddim import ldm.models.diffusion.plms -from ldm.models.diffusion.ddpm import LatentDiffusion -from ldm.models.diffusion.plms import PLMSSampler -from ldm.models.diffusion.ddim import DDIMSampler, noise_like +from ldm.models.diffusion.ddim import noise_like from ldm.models.diffusion.sampling_util import norm_thresholding @@ -29,7 +23,7 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F if isinstance(c, dict): assert isinstance(unconditional_conditioning, dict) - c_in = dict() + c_in = {} for k in c: if isinstance(c[k], list): c_in[k] = [ diff --git a/modules/sd_hijack_ip2p.py b/modules/sd_hijack_ip2p.py index 3c727d3b..6fe6b6ff 100644 --- a/modules/sd_hijack_ip2p.py +++ b/modules/sd_hijack_ip2p.py @@ -1,8 +1,5 @@ -import collections import os.path -import sys -import gc -import time + def should_hijack_ip2p(checkpoint_info): from modules import sd_models_config @@ -10,4 +7,4 @@ def should_hijack_ip2p(checkpoint_info): ckpt_basename = os.path.basename(checkpoint_info.filename).lower() cfg_basename = os.path.basename(sd_models_config.find_checkpoint_config_near_filename(checkpoint_info)).lower() - return "pix2pix" in ckpt_basename and not "pix2pix" in cfg_basename + return "pix2pix" in ckpt_basename and "pix2pix" not in cfg_basename diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index f10865cd..f00fe55c 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -49,7 +49,7 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): v_in = self.to_v(context_v) del context, context_k, context_v, x - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in)) + q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q_in, k_in, v_in)) del q_in, k_in, v_in dtype = q.dtype @@ -62,10 +62,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): end = i + 2 s1 = einsum('b i d, b j d -> b i j', q[i:end], k[i:end]) s1 *= self.scale - + s2 = s1.softmax(dim=-1) del s1 - + r1[i:end] = einsum('b i j, b j d -> b i d', s2, v[i:end]) del s2 del q, k, v @@ -95,43 +95,43 @@ def split_cross_attention_forward(self, x, context=None, mask=None): with devices.without_autocast(disable=not shared.opts.upcast_attn): k_in = k_in * self.scale - + del context, x - - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in)) + + q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q_in, k_in, v_in)) del q_in, k_in, v_in - + r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype) - + mem_free_total = get_available_vram() - + gb = 1024 ** 3 tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size() modifier = 3 if q.element_size() == 2 else 2.5 mem_required = tensor_size * modifier steps = 1 - + if mem_required > mem_free_total: steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2))) # print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB " # f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}") - + if steps > 64: max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64 raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). ' f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free') - + slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1] for i in range(0, q.shape[1], slice_size): end = i + slice_size s1 = einsum('b i d, b j d -> b i j', q[:, i:end], k) - + s2 = s1.softmax(dim=-1, dtype=q.dtype) del s1 - + r1[:, i:end] = einsum('b i j, b j d -> b i d', s2, v) del s2 - + del q, k, v r1 = r1.to(dtype) @@ -228,8 +228,8 @@ def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None): with devices.without_autocast(disable=not shared.opts.upcast_attn): k = k * self.scale - - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) + + q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q, k, v)) r = einsum_op(q, k, v) r = r.to(dtype) return self.to_out(rearrange(r, '(b h) n d -> b n (h d)', h=h)) @@ -296,7 +296,6 @@ def sub_quad_attention(q, k, v, q_chunk_size=1024, kv_chunk_size=None, kv_chunk_ if chunk_threshold_bytes is not None and qk_matmul_size_bytes <= chunk_threshold_bytes: # the big matmul fits into our memory limit; do everything in 1 chunk, # i.e. send it down the unchunked fast-path - query_chunk_size = q_tokens kv_chunk_size = k_tokens with devices.without_autocast(disable=q.dtype == v.dtype): @@ -335,7 +334,7 @@ def xformers_attention_forward(self, x, context=None, mask=None): k_in = self.to_k(context_k) v_in = self.to_v(context_v) - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b n h d', h=h), (q_in, k_in, v_in)) + q, k, v = (rearrange(t, 'b n (h d) -> b n h d', h=h) for t in (q_in, k_in, v_in)) del q_in, k_in, v_in dtype = q.dtype @@ -370,7 +369,7 @@ def scaled_dot_product_attention_forward(self, x, context=None, mask=None): q = q_in.view(batch_size, -1, h, head_dim).transpose(1, 2) k = k_in.view(batch_size, -1, h, head_dim).transpose(1, 2) v = v_in.view(batch_size, -1, h, head_dim).transpose(1, 2) - + del q_in, k_in, v_in dtype = q.dtype @@ -452,7 +451,7 @@ def cross_attention_attnblock_forward(self, x): h3 += x return h3 - + def xformers_attnblock_forward(self, x): try: h_ = x @@ -461,7 +460,7 @@ def xformers_attnblock_forward(self, x): k = self.k(h_) v = self.v(h_) b, c, h, w = q.shape - q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v)) + q, k, v = (rearrange(t, 'b c h w -> b (h w) c') for t in (q, k, v)) dtype = q.dtype if shared.opts.upcast_attn: q, k = q.float(), k.float() @@ -483,7 +482,7 @@ def sdp_attnblock_forward(self, x): k = self.k(h_) v = self.v(h_) b, c, h, w = q.shape - q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v)) + q, k, v = (rearrange(t, 'b c h w -> b (h w) c') for t in (q, k, v)) dtype = q.dtype if shared.opts.upcast_attn: q, k = q.float(), k.float() @@ -507,7 +506,7 @@ def sub_quad_attnblock_forward(self, x): k = self.k(h_) v = self.v(h_) b, c, h, w = q.shape - q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v)) + q, k, v = (rearrange(t, 'b c h w -> b (h w) c') for t in (q, k, v)) q = q.contiguous() k = k.contiguous() v = v.contiguous() diff --git a/modules/sd_hijack_xlmr.py b/modules/sd_hijack_xlmr.py index 4ac51c38..28528329 100644 --- a/modules/sd_hijack_xlmr.py +++ b/modules/sd_hijack_xlmr.py @@ -1,8 +1,6 @@ -import open_clip.tokenizer import torch from modules import sd_hijack_clip, devices -from modules.shared import opts class FrozenXLMREmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords): diff --git a/modules/sd_models.py b/modules/sd_models.py index 36f643e1..e612be10 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -15,9 +15,9 @@ import ldm.modules.midas as midas from ldm.util import instantiate_from_config from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config -from modules.paths import models_path from modules.sd_hijack_inpainting import do_inpainting_hijack from modules.timer import Timer +import tomesd model_dir = "Stable-diffusion" model_path = os.path.abspath(os.path.join(paths.models_path, model_dir)) @@ -87,8 +87,7 @@ class CheckpointInfo: try: # this silences the annoying "Some weights of the model checkpoint were not used when initializing..." message at start. - - from transformers import logging, CLIPModel + from transformers import logging, CLIPModel # noqa: F401 logging.set_verbosity_error() except Exception: @@ -167,7 +166,7 @@ def model_hash(filename): def select_checkpoint(): model_checkpoint = shared.opts.sd_model_checkpoint - + checkpoint_info = checkpoint_alisases.get(model_checkpoint, None) if checkpoint_info is not None: return checkpoint_info @@ -239,7 +238,7 @@ def read_metadata_from_safetensors(filename): if isinstance(v, str) and v[0:1] == '{': try: res[k] = json.loads(v) - except Exception as e: + except Exception: pass return res @@ -374,7 +373,7 @@ def enable_midas_autodownload(): if not os.path.exists(path): if not os.path.exists(midas_path): mkdir(midas_path) - + print(f"Downloading midas model weights for {model_type} to {path}") request.urlretrieve(midas_urls[model_type], path) print(f"{model_type} downloaded") @@ -415,6 +414,9 @@ class SdModelData: def get_sd_model(self): if self.sd_model is None: with self.lock: + if self.sd_model is not None: + return self.sd_model + try: load_model() except Exception as e: @@ -467,7 +469,7 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None): try: with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd): sd_model = instantiate_from_config(sd_config.model) - except Exception as e: + except Exception: pass if sd_model is None: @@ -538,13 +540,12 @@ def reload_model_weights(sd_model=None, info=None): if sd_model is None or checkpoint_config != sd_model.used_config: del sd_model - checkpoints_loaded.clear() load_model(checkpoint_info, already_loaded_state_dict=state_dict) return model_data.sd_model try: load_model_weights(sd_model, checkpoint_info, state_dict, timer) - except Exception as e: + except Exception: print("Failed to load checkpoint, restoring previous") load_model_weights(sd_model, current_checkpoint_info, None, timer) raise @@ -565,7 +566,7 @@ def reload_model_weights(sd_model=None, info=None): def unload_model_weights(sd_model=None, info=None): - from modules import lowvram, devices, sd_hijack + from modules import devices, sd_hijack timer = Timer() if model_data.sd_model: @@ -580,3 +581,25 @@ def unload_model_weights(sd_model=None, info=None): print(f"Unloaded weights {timer.summary()}.") return sd_model + + +def apply_token_merging(sd_model, hr: bool): + """ + Applies speed and memory optimizations from tomesd. + + Args: + hr (bool): True if called in the context of a high-res pass + """ + + ratio = shared.opts.token_merging_ratio + if hr: + ratio = shared.opts.token_merging_ratio_hr + + tomesd.apply_patch( + sd_model, + ratio=ratio, + use_rand=False, # can cause issues with some samplers + merge_attn=True, + merge_crossattn=False, + merge_mlp=False + ) diff --git a/modules/sd_models_config.py b/modules/sd_models_config.py index 7a79925a..9bfe1237 100644 --- a/modules/sd_models_config.py +++ b/modules/sd_models_config.py @@ -1,4 +1,3 @@ -import re import os import torch diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index ff361f22..f22aad8f 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -1,7 +1,7 @@ from modules import sd_samplers_compvis, sd_samplers_kdiffusion, shared # imports for functions that previously were here and are used by other modules -from modules.sd_samplers_common import samples_to_image_grid, sample_to_image +from modules.sd_samplers_common import samples_to_image_grid, sample_to_image # noqa: F401 all_samplers = [ *sd_samplers_kdiffusion.samplers_data_k_diffusion, @@ -14,12 +14,18 @@ samplers_for_img2img = [] samplers_map = {} -def create_sampler(name, model): +def find_sampler_config(name): if name is not None: config = all_samplers_map.get(name, None) else: config = all_samplers[0] + return config + + +def create_sampler(name, model): + config = find_sampler_config(name) + assert config is not None, f'bad sampler name: {name}' sampler = config.constructor(model) diff --git a/modules/sd_samplers_common.py b/modules/sd_samplers_common.py index 20a9af20..ceda6a35 100644 --- a/modules/sd_samplers_common.py +++ b/modules/sd_samplers_common.py @@ -2,7 +2,7 @@ from collections import namedtuple import numpy as np import torch from PIL import Image -from modules import devices, processing, images, sd_vae_approx, sd_vae_taesd +from modules import devices, processing, images, sd_vae_approx, sd_samplers, sd_vae_taesd from modules.shared import opts, state import modules.shared as shared @@ -64,6 +64,25 @@ def store_latent(decoded): shared.state.assign_current_image(sample_to_image(decoded)) +def is_sampler_using_eta_noise_seed_delta(p): + """returns whether sampler from config will use eta noise seed delta for image creation""" + + sampler_config = sd_samplers.find_sampler_config(p.sampler_name) + + eta = p.eta + + if eta is None and p.sampler is not None: + eta = p.sampler.eta + + if eta is None and sampler_config is not None: + eta = 0 if sampler_config.options.get("default_eta_is_0", False) else 1.0 + + if eta == 0: + return False + + return sampler_config.options.get("uses_ensd", False) + + class InterruptedException(BaseException): pass diff --git a/modules/sd_samplers_compvis.py b/modules/sd_samplers_compvis.py index bfcc5574..bdae8b40 100644 --- a/modules/sd_samplers_compvis.py +++ b/modules/sd_samplers_compvis.py @@ -11,7 +11,7 @@ import modules.models.diffusion.uni_pc samplers_data_compvis = [ - sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}), + sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {"default_eta_is_0": True, "uses_ensd": True}), sd_samplers_common.SamplerData('PLMS', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}), sd_samplers_common.SamplerData('UniPC', lambda model: VanillaStableDiffusionSampler(modules.models.diffusion.uni_pc.UniPCSampler, model), [], {}), ] @@ -55,7 +55,7 @@ class VanillaStableDiffusionSampler: def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs): x_dec, ts, cond, unconditional_conditioning = self.before_sample(x_dec, ts, cond, unconditional_conditioning) - res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs) + res = self.orig_p_sample_ddim(x_dec, cond, ts, *args, unconditional_conditioning=unconditional_conditioning, **kwargs) x_dec, ts, cond, unconditional_conditioning, res = self.after_sample(x_dec, ts, cond, unconditional_conditioning, res) @@ -83,7 +83,7 @@ class VanillaStableDiffusionSampler: conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step) unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step) - assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers' + assert all(len(conds) == 1 for conds in conds_list), 'composition via AND is not supported for DDIM/PLMS samplers' cond = tensor # for DDIM, shapes must match, we can't just process cond and uncond independently; @@ -134,7 +134,11 @@ class VanillaStableDiffusionSampler: self.update_step(x) def initialize(self, p): - self.eta = p.eta if p.eta is not None else shared.opts.eta_ddim + if self.is_ddim: + self.eta = p.eta if p.eta is not None else shared.opts.eta_ddim + else: + self.eta = 0.0 + if self.eta != 0.0: p.extra_generation_params["Eta DDIM"] = self.eta diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 0fc9f456..552c6c64 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -1,7 +1,6 @@ from collections import deque import torch import inspect -import einops import k_diffusion.sampling from modules import prompt_parser, devices, sd_samplers_common @@ -9,25 +8,26 @@ from modules.shared import opts, state import modules.shared as shared from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback from modules.script_callbacks import CFGDenoisedParams, cfg_denoised_callback +from modules.script_callbacks import AfterCFGCallbackParams, cfg_after_cfg_callback samplers_k_diffusion = [ - ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}), + ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {"uses_ensd": True}), ('Euler', 'sample_euler', ['k_euler'], {}), ('LMS', 'sample_lms', ['k_lms'], {}), - ('Heun', 'sample_heun', ['k_heun'], {}), + ('Heun', 'sample_heun', ['k_heun'], {"second_order": True}), ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}), - ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True}), - ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), + ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True, "uses_ensd": True}), + ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {"uses_ensd": True, "second_order": True}), ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), - ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}), - ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}), - ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}), + ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {"second_order": True}), + ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {"uses_ensd": True}), + ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {"uses_ensd": True}), ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}), - ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}), - ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}), - ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), + ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}), + ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "uses_ensd": True, "second_order": True}), + ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras', "uses_ensd": True, "second_order": True}), ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), - ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}), + ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras', "second_order": True}), ] samplers_data_k_diffusion = [ @@ -87,17 +87,17 @@ class CFGDenoiser(torch.nn.Module): conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step) uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step) - assert not is_edit_model or all([len(conds) == 1 for conds in conds_list]), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)" + assert not is_edit_model or all(len(conds) == 1 for conds in conds_list), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)" batch_size = len(conds_list) repeats = [len(conds_list[i]) for i in range(batch_size)] if shared.sd_model.model.conditioning_key == "crossattn-adm": image_uncond = torch.zeros_like(image_cond) - make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm} + make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm} else: image_uncond = image_cond - make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]} + make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]} if not is_edit_model: x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x]) @@ -161,7 +161,7 @@ class CFGDenoiser(torch.nn.Module): fake_uncond = torch.cat([x_out[i:i+1] for i in denoised_image_indexes]) x_out = torch.cat([x_out, fake_uncond]) # we skipped uncond denoising, so we put cond-denoised image to where the uncond-denoised image should be - denoised_params = CFGDenoisedParams(x_out, state.sampling_step, state.sampling_steps) + denoised_params = CFGDenoisedParams(x_out, state.sampling_step, state.sampling_steps, self.inner_model) cfg_denoised_callback(denoised_params) devices.test_for_nans(x_out, "unet") @@ -181,6 +181,10 @@ class CFGDenoiser(torch.nn.Module): if self.mask is not None: denoised = self.init_latent * self.mask + self.nmask * denoised + after_cfg_callback_params = AfterCFGCallbackParams(denoised, state.sampling_step, state.sampling_steps) + cfg_after_cfg_callback(after_cfg_callback_params) + denoised = after_cfg_callback_params.x + self.step += 1 return denoised @@ -317,7 +321,7 @@ class KDiffusionSampler: sigma_sched = sigmas[steps - t_enc - 1:] xi = x + noise * sigma_sched[0] - + extra_params_kwargs = self.initialize(p) parameters = inspect.signature(self.func).parameters @@ -340,9 +344,9 @@ class KDiffusionSampler: self.model_wrap_cfg.init_latent = x self.last_latent = x extra_args={ - 'cond': conditioning, - 'image_cond': image_conditioning, - 'uncond': unconditional_conditioning, + 'cond': conditioning, + 'image_cond': image_conditioning, + 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale, 's_min_uncond': self.s_min_uncond } @@ -375,9 +379,9 @@ class KDiffusionSampler: self.last_latent = x samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={ - 'cond': conditioning, - 'image_cond': image_conditioning, - 'uncond': unconditional_conditioning, + 'cond': conditioning, + 'image_cond': image_conditioning, + 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale, 's_min_uncond': self.s_min_uncond }, disable=False, callback=self.callback_state, **extra_params_kwargs)) diff --git a/modules/sd_vae.py b/modules/sd_vae.py index 521e485a..e4ff2994 100644 --- a/modules/sd_vae.py +++ b/modules/sd_vae.py @@ -1,8 +1,5 @@ -import torch -import safetensors.torch import os import collections -from collections import namedtuple from modules import paths, shared, devices, script_callbacks, sd_models import glob from copy import deepcopy @@ -88,10 +85,10 @@ def refresh_vae_list(): def find_vae_near_checkpoint(checkpoint_file): - checkpoint_path = os.path.splitext(checkpoint_file)[0] - for vae_location in [f"{checkpoint_path}.vae.pt", f"{checkpoint_path}.vae.ckpt", f"{checkpoint_path}.vae.safetensors"]: - if os.path.isfile(vae_location): - return vae_location + checkpoint_path = os.path.basename(checkpoint_file).rsplit('.', 1)[0] + for vae_file in vae_dict.values(): + if os.path.basename(vae_file).startswith(checkpoint_path): + return vae_file return None diff --git a/modules/shared.py b/modules/shared.py index 96036d38..165509ea 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -1,12 +1,9 @@ -import argparse import datetime import json import os import sys import time -import requests -from PIL import Image import gradio as gr import tqdm @@ -15,7 +12,7 @@ import modules.memmon import modules.styles import modules.devices as devices from modules import localization, script_loading, errors, ui_components, shared_items, cmd_args -from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir +from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir # noqa: F401 from ldm.models.diffusion.ddpm import LatentDiffusion demo = None @@ -202,8 +199,9 @@ interrogator = modules.interrogate.InterrogateModels("interrogate") face_restorers = [] + class OptionInfo: - def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None): + def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after=''): self.default = default self.label = label self.component = component @@ -212,9 +210,33 @@ class OptionInfo: self.section = section self.refresh = refresh + self.comment_before = comment_before + """HTML text that will be added after label in UI""" + + self.comment_after = comment_after + """HTML text that will be added before label in UI""" + + def link(self, label, url): + self.comment_before += f"[{label}]" + return self + + def js(self, label, js_func): + self.comment_before += f"[{label}]" + return self + + def info(self, info): + self.comment_after += f"({info})" + return self + + def needs_restart(self): + self.comment_after += " (requires restart)" + return self + + + def options_section(section_identifier, options_dict): - for k, v in options_dict.items(): + for v in options_dict.values(): v.section = section_identifier return options_dict @@ -243,7 +265,7 @@ options_templates = {} options_templates.update(options_section(('saving-images', "Saving images/grids"), { "samples_save": OptionInfo(True, "Always save all generated images"), "samples_format": OptionInfo('png', 'File format for images'), - "samples_filename_pattern": OptionInfo("", "Images filename pattern", component_args=hide_dirs), + "samples_filename_pattern": OptionInfo("", "Images filename pattern", component_args=hide_dirs).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"), "save_images_add_number": OptionInfo(True, "Add number to filename when saving", component_args=hide_dirs), "grid_save": OptionInfo(True, "Always save all generated image grids"), @@ -262,10 +284,10 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "save_mask_composite": OptionInfo(False, "For inpainting, save a masked composite"), "jpeg_quality": OptionInfo(80, "Quality for saved jpeg images", gr.Slider, {"minimum": 1, "maximum": 100, "step": 1}), "webp_lossless": OptionInfo(False, "Use lossless compression for webp images"), - "export_for_4chan": OptionInfo(True, "If the saved image file size is above the limit, or its either width or height are above the limit, save a downscaled copy as JPG"), + "export_for_4chan": OptionInfo(True, "Save copy of large images as JPG").info("if the file size is above the limit, or either width or height are above the limit"), "img_downscale_threshold": OptionInfo(4.0, "File size limit for the above option, MB", gr.Number), "target_side_length": OptionInfo(4000, "Width/height limit for the above option, in pixels", gr.Number), - "img_max_size_mp": OptionInfo(200, "Maximum image size, in megapixels", gr.Number), + "img_max_size_mp": OptionInfo(200, "Maximum image size", gr.Number).info("in megapixels"), "use_original_name_batch": OptionInfo(True, "Use original name for output filename during batch process in extras tab"), "use_upscaler_name_as_suffix": OptionInfo(False, "Use upscaler name as filename suffix in the extras tab"), @@ -293,28 +315,26 @@ options_templates.update(options_section(('saving-to-dirs', "Saving to a directo "save_to_dirs": OptionInfo(True, "Save images to a subdirectory"), "grid_save_to_dirs": OptionInfo(True, "Save grids to a subdirectory"), "use_save_to_dirs_for_ui": OptionInfo(False, "When using \"Save\" button, save images to a subdirectory"), - "directories_filename_pattern": OptionInfo("[date]", "Directory name pattern", component_args=hide_dirs), + "directories_filename_pattern": OptionInfo("[date]", "Directory name pattern", component_args=hide_dirs).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"), "directories_max_prompt_words": OptionInfo(8, "Max prompt words for [prompt_words] pattern", gr.Slider, {"minimum": 1, "maximum": 20, "step": 1, **hide_dirs}), })) options_templates.update(options_section(('upscaling', "Upscaling"), { - "ESRGAN_tile": OptionInfo(192, "Tile size for ESRGAN upscalers. 0 = no tiling.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}), - "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}), - "realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": shared_items.realesrgan_models_names()}), + "ESRGAN_tile": OptionInfo(192, "Tile size for ESRGAN upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}).info("0 = no tiling"), + "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap for ESRGAN upscalers.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}).info("Low values = visible seam"), + "realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI.", gr.CheckboxGroup, lambda: {"choices": shared_items.realesrgan_models_names()}), "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in sd_upscalers]}), - "SCUNET_tile": OptionInfo(256, "Tile size for SCUNET upscalers. 0 = no tiling.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}), - "SCUNET_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for SCUNET upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}), })) options_templates.update(options_section(('face-restoration', "Face restoration"), { "face_restoration_model": OptionInfo("CodeFormer", "Face restoration model", gr.Radio, lambda: {"choices": [x.name() for x in face_restorers]}), - "code_former_weight": OptionInfo(0.5, "CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), + "code_former_weight": OptionInfo(0.5, "CodeFormer weight", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}).info("0 = maximum effect; 1 = minimum effect"), "face_restoration_unload": OptionInfo(False, "Move face restoration model from VRAM into RAM after processing"), })) options_templates.update(options_section(('system', "System"), { "show_warnings": OptionInfo(False, "Show warnings in console."), - "memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation. Set to 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 40, "step": 1}), + "memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation.", gr.Slider, {"minimum": 0, "maximum": 40, "step": 1}).info("0 = disable"), "samples_log_stdout": OptionInfo(False, "Always print all generation info to standard output"), "multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job."), "print_hypernet_extra": OptionInfo(False, "Print extra hypernetwork information to console."), @@ -339,20 +359,22 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": list_checkpoint_tiles()}, refresh=refresh_checkpoints), "sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}), "sd_vae_checkpoint_cache": OptionInfo(0, "VAE Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}), - "sd_vae": OptionInfo("Automatic", "SD VAE", gr.Dropdown, lambda: {"choices": shared_items.sd_vae_items()}, refresh=shared_items.refresh_vae_list), + "sd_vae": OptionInfo("Automatic", "SD VAE", gr.Dropdown, lambda: {"choices": shared_items.sd_vae_items()}, refresh=shared_items.refresh_vae_list).info("choose VAE model: Automatic = use one with same filename as checkpoint; None = use VAE from checkpoint"), "sd_vae_as_default": OptionInfo(True, "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them"), "inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), "initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.5, "maximum": 1.5, "step": 0.01}), "img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."), - "img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."), + "img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies.").info("normally you'd do less with less denoising"), "img2img_background_color": OptionInfo("#ffffff", "With img2img, fill image's transparent parts with this color.", ui_components.FormColorPicker, {}), "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."), - "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"), + "enable_emphasis": OptionInfo(True, "Enable emphasis").info("use (text) to make model pay more attention to text and [text] to make it pay less attention"), "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"), - "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }), - "CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}), + "comma_padding_backtrack": OptionInfo(20, "Prompt word wrap length limit", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1}).info("in tokens - for texts shorter than specified, if they don't fit into 75 token limit, move them to the next 75 token chunk"), + "CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#clip-skip").info("ignore last layers of CLIP nrtwork; 1 ignores none, 2 ignores one layer"), "upcast_attn": OptionInfo(False, "Upcast cross attention layer to float32"), - "randn_source": OptionInfo("GPU", "Random number generator source. Changes seeds drastically. Use CPU to produce the same picture across different vidocard vendors.", gr.Radio, {"choices": ["GPU", "CPU"]}), + "randn_source": OptionInfo("GPU", "Random number generator source.", gr.Radio, {"choices": ["GPU", "CPU"]}).info("changes seeds drastically; use CPU to produce the same picture across different vidocard vendors"), + "token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"), + "token_merging_ratio_hr": OptionInfo(0.0, "Togen merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}), })) options_templates.update(options_section(('compatibility', "Compatibility"), { @@ -364,30 +386,32 @@ options_templates.update(options_section(('compatibility', "Compatibility"), { })) options_templates.update(options_section(('interrogate', "Interrogate Options"), { - "interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"), - "interrogate_return_ranks": OptionInfo(False, "Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators)."), - "interrogate_clip_num_beams": OptionInfo(1, "Interrogate: num_beams for BLIP", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}), - "interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}), - "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}), - "interrogate_clip_dict_limit": OptionInfo(1500, "CLIP: maximum number of lines in text file (0 = No limit)"), + "interrogate_keep_models_in_memory": OptionInfo(False, "Keep models in VRAM"), + "interrogate_return_ranks": OptionInfo(False, "Include ranks of model tags matches in results.").info("booru only"), + "interrogate_clip_num_beams": OptionInfo(1, "BLIP: num_beams", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}), + "interrogate_clip_min_length": OptionInfo(24, "BLIP: minimum description length", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}), + "interrogate_clip_max_length": OptionInfo(48, "BLIP: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}), + "interrogate_clip_dict_limit": OptionInfo(1500, "CLIP: maximum number of lines in text file").info("0 = No limit"), "interrogate_clip_skip_categories": OptionInfo([], "CLIP: skip inquire categories", gr.CheckboxGroup, lambda: {"choices": modules.interrogate.category_types()}, refresh=modules.interrogate.category_types), - "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), - "deepbooru_sort_alpha": OptionInfo(True, "Interrogate: deepbooru sort alphabetically"), - "deepbooru_use_spaces": OptionInfo(False, "use spaces for tags in deepbooru"), - "deepbooru_escape": OptionInfo(True, "escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)"), - "deepbooru_filter_tags": OptionInfo("", "filter out those tags from deepbooru output (separated by comma)"), + "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "deepbooru: score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), + "deepbooru_sort_alpha": OptionInfo(True, "deepbooru: sort tags alphabetically").info("if not: sort by score"), + "deepbooru_use_spaces": OptionInfo(True, "deepbooru: use spaces in tags").info("if not: use underscores"), + "deepbooru_escape": OptionInfo(True, "deepbooru: escape (\\) brackets").info("so they are used as literal brackets and not for emphasis"), + "deepbooru_filter_tags": OptionInfo("", "deepbooru: filter out those tags").info("separate by comma"), })) options_templates.update(options_section(('extra_networks', "Extra Networks"), { "extra_networks_default_view": OptionInfo("cards", "Default view for Extra Networks", gr.Dropdown, {"choices": ["cards", "thumbs"]}), "extra_networks_default_multiplier": OptionInfo(1.0, "Multiplier for extra networks", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), - "extra_networks_card_width": OptionInfo(0, "Card width for Extra Networks (px)"), - "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks (px)"), - "extra_networks_add_text_separator": OptionInfo(" ", "Extra text to add before <...> when adding extra network to prompt"), - "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks), + "extra_networks_card_width": OptionInfo(0, "Card width for Extra Networks").info("in pixels"), + "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks").info("in pixels"), + "extra_networks_add_text_separator": OptionInfo(" ", "Extra networks separator").info("extra text to add before <...> when adding extra network to prompt"), + "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": ["None", *hypernetworks]}, refresh=reload_hypernetworks), })) options_templates.update(options_section(('ui', "User interface"), { + "localization": OptionInfo("None", "Localization", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)).needs_restart(), + "gradio_theme": OptionInfo("Default", "Gradio theme", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + gradio_hf_hub_themes}).needs_restart(), "return_grid": OptionInfo(True, "Show grid in results for web"), "return_mask": OptionInfo(False, "For inpainting, include the greyscale mask in results for web"), "return_mask_composite": OptionInfo(False, "For inpainting, include masked composite in results for web"), @@ -400,17 +424,15 @@ options_templates.update(options_section(('ui', "User interface"), { "js_modal_lightbox_gamepad": OptionInfo(True, "Navigate image viewer with gamepad"), "js_modal_lightbox_gamepad_repeat": OptionInfo(250, "Gamepad repeat period, in milliseconds"), "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."), - "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group"), - "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row"), + "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group").needs_restart(), + "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row").needs_restart(), "keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}), "keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing ", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}), "keyedit_delimiters": OptionInfo(".,\\/!?%^*;:{}=`~()", "Ctrl+up/down word delimiters"), - "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(opts.data_labels.keys())}), - "hidden_tabs": OptionInfo([], "Hidden UI tabs (requires restart)", ui_components.DropdownMulti, lambda: {"choices": [x for x in tab_names]}), + "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_restart(), + "hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(tab_names)}).needs_restart(), "ui_reorder": OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order"), - "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order"), - "localization": OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)), - "gradio_theme": OptionInfo("Default", "Gradio theme (requires restart)", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + gradio_hf_hub_themes}) + "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order").needs_restart(), })) options_templates.update(options_section(('infotext', "Infotext"), { @@ -423,27 +445,28 @@ options_templates.update(options_section(('infotext', "Infotext"), { options_templates.update(options_section(('ui', "Live previews"), { "show_progressbar": OptionInfo(True, "Show progressbar"), "live_previews_enable": OptionInfo(True, "Show live previews of the created image"), + "live_previews_image_format": OptionInfo("png", "Live preview file format", gr.Radio, {"choices": ["jpeg", "png", "webp"]}), "show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"), - "show_progress_every_n_steps": OptionInfo(10, "Show new live preview image every N sampling steps. Set to -1 to show after completion of batch.", gr.Slider, {"minimum": -1, "maximum": 32, "step": 1}), - "show_progress_type": OptionInfo("Approx NN", "Image creation progress preview mode", gr.Radio, {"choices": ["Full", "Approx NN", "Approx cheap", "TAESD"]}), + "show_progress_every_n_steps": OptionInfo(10, "Live preview display period", gr.Slider, {"minimum": -1, "maximum": 32, "step": 1}).info("in sampling steps - show new live preview image every N sampling steps; -1 = only show after completion of batch"), + "show_progress_type": OptionInfo("Approx NN", "Live preview method", gr.Radio, {"choices": ["Full", "Approx NN", "Approx cheap", "TAESD"]}).info("Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise"), "live_preview_content": OptionInfo("Prompt", "Live preview subject", gr.Radio, {"choices": ["Combined", "Prompt", "Negative prompt"]}), - "live_preview_refresh_period": OptionInfo(1000, "Progressbar/preview update period, in milliseconds") + "live_preview_refresh_period": OptionInfo(1000, "Progressbar and preview update period").info("in milliseconds"), })) options_templates.update(options_section(('sampler-params', "Sampler parameters"), { - "hide_samplers": OptionInfo([], "Hide samplers in user interface (requires restart)", gr.CheckboxGroup, lambda: {"choices": [x.name for x in list_samplers()]}), - "eta_ddim": OptionInfo(0.0, "eta (noise multiplier) for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), - "eta_ancestral": OptionInfo(1.0, "eta (noise multiplier) for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), + "hide_samplers": OptionInfo([], "Hide samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in list_samplers()]}).needs_restart(), + "eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}).info("noise multiplier; higher = more unperdictable results"), + "eta_ancestral": OptionInfo(1.0, "Eta for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}).info("noise multiplier; applies to Euler a and other samplers that have a in them"), "ddim_discretize": OptionInfo('uniform', "img2img DDIM discretize", gr.Radio, {"choices": ['uniform', 'quad']}), + 's_min_uncond': OptionInfo(0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 4.0, "step": 0.01}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"), 's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), - 's_min_uncond': OptionInfo(0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 4.0, "step": 0.01}), 's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), - 'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}), - 'always_discard_next_to_last_sigma': OptionInfo(False, "Always discard next-to-last sigma"), + 'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}).info("ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images"), + 'always_discard_next_to_last_sigma': OptionInfo(False, "Always discard next-to-last sigma").link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/6044"), 'uni_pc_variant': OptionInfo("bh1", "UniPC variant", gr.Radio, {"choices": ["bh1", "bh2", "vary_coeff"]}), 'uni_pc_skip_type': OptionInfo("time_uniform", "UniPC skip type", gr.Radio, {"choices": ["time_uniform", "time_quadratic", "logSNR"]}), - 'uni_pc_order': OptionInfo(3, "UniPC order (must be < sampling steps)", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}), + 'uni_pc_order': OptionInfo(3, "UniPC order", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}).info("must be < sampling steps"), 'uni_pc_lower_order_final': OptionInfo(True, "UniPC lower order final"), })) @@ -460,6 +483,7 @@ options_templates.update(options_section((None, "Hidden options"), { "sd_checkpoint_hash": OptionInfo("", "SHA256 hash of the current checkpoint"), })) + options_templates.update() @@ -571,7 +595,9 @@ class Options: func() def dumpjson(self): - d = {k: self.data.get(k, self.data_labels.get(k).default) for k in self.data_labels.keys()} + d = {k: self.data.get(k, v.default) for k, v in self.data_labels.items()} + d["_comments_before"] = {k: v.comment_before for k, v in self.data_labels.items() if v.comment_before is not None} + d["_comments_after"] = {k: v.comment_after for k, v in self.data_labels.items() if v.comment_after is not None} return json.dumps(d) def add_option(self, key, info): @@ -582,11 +608,11 @@ class Options: section_ids = {} settings_items = self.data_labels.items() - for k, item in settings_items: + for _, item in settings_items: if item.section not in section_ids: section_ids[item.section] = len(section_ids) - self.data_labels = {k: v for k, v in sorted(settings_items, key=lambda x: section_ids[x[1].section])} + self.data_labels = dict(sorted(settings_items, key=lambda x: section_ids[x[1].section])) def cast_value(self, key, value): """casts an arbitrary to the same type as this setting's value with key @@ -667,14 +693,19 @@ def reload_gradio_theme(theme_name=None): if not theme_name: theme_name = opts.gradio_theme + default_theme_args = dict( + font=["Source Sans Pro", 'ui-sans-serif', 'system-ui', 'sans-serif'], + font_mono=['IBM Plex Mono', 'ui-monospace', 'Consolas', 'monospace'], + ) + if theme_name == "Default": - gradio_theme = gr.themes.Default() + gradio_theme = gr.themes.Default(**default_theme_args) else: try: gradio_theme = gr.themes.ThemeClass.from_hub(theme_name) except Exception as e: errors.display(e, "changing gradio theme") - gradio_theme = gr.themes.Default() + gradio_theme = gr.themes.Default(**default_theme_args) @@ -743,7 +774,7 @@ def walk_files(path, allowed_extensions=None): if allowed_extensions is not None: allowed_extensions = set(allowed_extensions) - for root, dirs, files in os.walk(path): + for root, _, files in os.walk(path, followlinks=True): for filename in files: if allowed_extensions is not None: _, ext = os.path.splitext(filename) diff --git a/modules/styles.py b/modules/styles.py index 11642075..c22769cf 100644 --- a/modules/styles.py +++ b/modules/styles.py @@ -1,18 +1,9 @@ -# We need this so Python doesn't complain about the unknown StableDiffusionProcessing-typehint at runtime -from __future__ import annotations - import csv import os import os.path import typing -import collections.abc as abc -import tempfile import shutil -if typing.TYPE_CHECKING: - # Only import this when code is being type-checked, it doesn't have any effect at runtime - from .processing import StableDiffusionProcessing - class PromptStyle(typing.NamedTuple): name: str diff --git a/modules/sub_quadratic_attention.py b/modules/sub_quadratic_attention.py index 05595323..497568eb 100644 --- a/modules/sub_quadratic_attention.py +++ b/modules/sub_quadratic_attention.py @@ -179,7 +179,7 @@ def efficient_dot_product_attention( chunk_idx, min(query_chunk_size, q_tokens) ) - + summarize_chunk: SummarizeChunk = partial(_summarize_chunk, scale=scale) summarize_chunk: SummarizeChunk = partial(checkpoint, summarize_chunk) if use_checkpoint else summarize_chunk compute_query_chunk_attn: ComputeQueryChunkAttn = partial( @@ -201,14 +201,15 @@ def efficient_dot_product_attention( key=key, value=value, ) - - # TODO: maybe we should use torch.empty_like(query) to allocate storage in-advance, - # and pass slices to be mutated, instead of torch.cat()ing the returned slices - res = torch.cat([ - compute_query_chunk_attn( + + res = torch.zeros_like(query) + for i in range(math.ceil(q_tokens / query_chunk_size)): + attn_scores = compute_query_chunk_attn( query=get_query_chunk(i * query_chunk_size), key=key, value=value, - ) for i in range(math.ceil(q_tokens / query_chunk_size)) - ], dim=1) + ) + + res[:, i * query_chunk_size:i * query_chunk_size + attn_scores.shape[1], :] = attn_scores + return res diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index ba1bdcd4..8e667a4d 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -1,10 +1,8 @@ import cv2 import requests import os -from collections import defaultdict -from math import log, sqrt import numpy as np -from PIL import Image, ImageDraw +from PIL import ImageDraw GREEN = "#0F0" BLUE = "#00F" @@ -12,63 +10,64 @@ RED = "#F00" def crop_image(im, settings): - """ Intelligently crop an image to the subject matter """ + """ Intelligently crop an image to the subject matter """ - scale_by = 1 - if is_landscape(im.width, im.height): - scale_by = settings.crop_height / im.height - elif is_portrait(im.width, im.height): - scale_by = settings.crop_width / im.width - elif is_square(im.width, im.height): - if is_square(settings.crop_width, settings.crop_height): - scale_by = settings.crop_width / im.width - elif is_landscape(settings.crop_width, settings.crop_height): - scale_by = settings.crop_width / im.width - elif is_portrait(settings.crop_width, settings.crop_height): - scale_by = settings.crop_height / im.height + scale_by = 1 + if is_landscape(im.width, im.height): + scale_by = settings.crop_height / im.height + elif is_portrait(im.width, im.height): + scale_by = settings.crop_width / im.width + elif is_square(im.width, im.height): + if is_square(settings.crop_width, settings.crop_height): + scale_by = settings.crop_width / im.width + elif is_landscape(settings.crop_width, settings.crop_height): + scale_by = settings.crop_width / im.width + elif is_portrait(settings.crop_width, settings.crop_height): + scale_by = settings.crop_height / im.height - im = im.resize((int(im.width * scale_by), int(im.height * scale_by))) - im_debug = im.copy() - focus = focal_point(im_debug, settings) + im = im.resize((int(im.width * scale_by), int(im.height * scale_by))) + im_debug = im.copy() - # take the focal point and turn it into crop coordinates that try to center over the focal - # point but then get adjusted back into the frame - y_half = int(settings.crop_height / 2) - x_half = int(settings.crop_width / 2) + focus = focal_point(im_debug, settings) - x1 = focus.x - x_half - if x1 < 0: - x1 = 0 - elif x1 + settings.crop_width > im.width: - x1 = im.width - settings.crop_width + # take the focal point and turn it into crop coordinates that try to center over the focal + # point but then get adjusted back into the frame + y_half = int(settings.crop_height / 2) + x_half = int(settings.crop_width / 2) - y1 = focus.y - y_half - if y1 < 0: - y1 = 0 - elif y1 + settings.crop_height > im.height: - y1 = im.height - settings.crop_height + x1 = focus.x - x_half + if x1 < 0: + x1 = 0 + elif x1 + settings.crop_width > im.width: + x1 = im.width - settings.crop_width - x2 = x1 + settings.crop_width - y2 = y1 + settings.crop_height + y1 = focus.y - y_half + if y1 < 0: + y1 = 0 + elif y1 + settings.crop_height > im.height: + y1 = im.height - settings.crop_height - crop = [x1, y1, x2, y2] + x2 = x1 + settings.crop_width + y2 = y1 + settings.crop_height - results = [] + crop = [x1, y1, x2, y2] - results.append(im.crop(tuple(crop))) + results = [] - if settings.annotate_image: - d = ImageDraw.Draw(im_debug) - rect = list(crop) - rect[2] -= 1 - rect[3] -= 1 - d.rectangle(rect, outline=GREEN) - results.append(im_debug) - if settings.destop_view_image: - im_debug.show() + results.append(im.crop(tuple(crop))) - return results + if settings.annotate_image: + d = ImageDraw.Draw(im_debug) + rect = list(crop) + rect[2] -= 1 + rect[3] -= 1 + d.rectangle(rect, outline=GREEN) + results.append(im_debug) + if settings.destop_view_image: + im_debug.show() + + return results def focal_point(im, settings): corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else [] @@ -88,7 +87,7 @@ def focal_point(im, settings): corner_centroid = None if len(corner_points) > 0: corner_centroid = centroid(corner_points) - corner_centroid.weight = settings.corner_points_weight / weight_pref_total + corner_centroid.weight = settings.corner_points_weight / weight_pref_total pois.append(corner_centroid) entropy_centroid = None @@ -100,7 +99,7 @@ def focal_point(im, settings): face_centroid = None if len(face_points) > 0: face_centroid = centroid(face_points) - face_centroid.weight = settings.face_points_weight / weight_pref_total + face_centroid.weight = settings.face_points_weight / weight_pref_total pois.append(face_centroid) average_point = poi_average(pois, settings) @@ -134,7 +133,7 @@ def focal_point(im, settings): d.rectangle(f.bounding(4), outline=color) d.ellipse(average_point.bounding(max_size), outline=GREEN) - + return average_point @@ -185,7 +184,7 @@ def image_face_points(im, settings): try: faces = classifier.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) - except: + except Exception: continue if len(faces) > 0: @@ -262,10 +261,11 @@ def image_entropy(im): hist = hist[hist > 0] return -np.log2(hist / hist.sum()).sum() + def centroid(pois): - x = [poi.x for poi in pois] - y = [poi.y for poi in pois] - return PointOfInterest(sum(x)/len(pois), sum(y)/len(pois)) + x = [poi.x for poi in pois] + y = [poi.y for poi in pois] + return PointOfInterest(sum(x) / len(pois), sum(y) / len(pois)) def poi_average(pois, settings): @@ -283,59 +283,59 @@ def poi_average(pois, settings): def is_landscape(w, h): - return w > h + return w > h def is_portrait(w, h): - return h > w + return h > w def is_square(w, h): - return w == h + return w == h def download_and_cache_models(dirname): - download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true' - model_file_name = 'face_detection_yunet.onnx' + download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true' + model_file_name = 'face_detection_yunet.onnx' - if not os.path.exists(dirname): - os.makedirs(dirname) + if not os.path.exists(dirname): + os.makedirs(dirname) - cache_file = os.path.join(dirname, model_file_name) - if not os.path.exists(cache_file): - print(f"downloading face detection model from '{download_url}' to '{cache_file}'") - response = requests.get(download_url) - with open(cache_file, "wb") as f: - f.write(response.content) + cache_file = os.path.join(dirname, model_file_name) + if not os.path.exists(cache_file): + print(f"downloading face detection model from '{download_url}' to '{cache_file}'") + response = requests.get(download_url) + with open(cache_file, "wb") as f: + f.write(response.content) - if os.path.exists(cache_file): - return cache_file - return None + if os.path.exists(cache_file): + return cache_file + return None class PointOfInterest: - def __init__(self, x, y, weight=1.0, size=10): - self.x = x - self.y = y - self.weight = weight - self.size = size + def __init__(self, x, y, weight=1.0, size=10): + self.x = x + self.y = y + self.weight = weight + self.size = size - def bounding(self, size): - return [ - self.x - size//2, - self.y - size//2, - self.x + size//2, - self.y + size//2 - ] + def bounding(self, size): + return [ + self.x - size // 2, + self.y - size // 2, + self.x + size // 2, + self.y + size // 2 + ] class Settings: - def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False, dnn_model_path=None): - self.crop_width = crop_width - self.crop_height = crop_height - self.corner_points_weight = corner_points_weight - self.entropy_points_weight = entropy_points_weight - self.face_points_weight = face_points_weight - self.annotate_image = annotate_image - self.destop_view_image = False - self.dnn_model_path = dnn_model_path + def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False, dnn_model_path=None): + self.crop_width = crop_width + self.crop_height = crop_height + self.corner_points_weight = corner_points_weight + self.entropy_points_weight = entropy_points_weight + self.face_points_weight = face_points_weight + self.annotate_image = annotate_image + self.destop_view_image = False + self.dnn_model_path = dnn_model_path diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index 41610e03..b9621fc9 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -118,7 +118,7 @@ class PersonalizedBase(Dataset): weight = torch.ones(latent_sample.shape) else: weight = None - + if latent_sampling_method == "random": entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist, weight=weight) else: @@ -243,4 +243,4 @@ class BatchLoaderRandom(BatchLoader): return self def collate_wrapper_random(batch): - return BatchLoaderRandom(batch) \ No newline at end of file + return BatchLoaderRandom(batch) diff --git a/modules/textual_inversion/image_embedding.py b/modules/textual_inversion/image_embedding.py index 5593f88c..5858a55f 100644 --- a/modules/textual_inversion/image_embedding.py +++ b/modules/textual_inversion/image_embedding.py @@ -2,10 +2,8 @@ import base64 import json import numpy as np import zlib -from PIL import Image, PngImagePlugin, ImageDraw, ImageFont -from fonts.ttf import Roboto +from PIL import Image, ImageDraw, ImageFont import torch -from modules.shared import opts class EmbeddingEncoder(json.JSONEncoder): @@ -17,7 +15,7 @@ class EmbeddingEncoder(json.JSONEncoder): class EmbeddingDecoder(json.JSONDecoder): def __init__(self, *args, **kwargs): - json.JSONDecoder.__init__(self, object_hook=self.object_hook, *args, **kwargs) + json.JSONDecoder.__init__(self, *args, object_hook=self.object_hook, **kwargs) def object_hook(self, d): if 'TORCHTENSOR' in d: @@ -136,11 +134,8 @@ def caption_image_overlay(srcimage, title, footerLeft, footerMid, footerRight, t image = srcimage.copy() fontsize = 32 if textfont is None: - try: - textfont = ImageFont.truetype(opts.font or Roboto, fontsize) - textfont = opts.font or Roboto - except Exception: - textfont = Roboto + from modules.images import get_font + textfont = get_font(fontsize) factor = 1.5 gradient = Image.new('RGBA', (1, image.size[1]), color=(0, 0, 0, 0)) diff --git a/modules/textual_inversion/learn_schedule.py b/modules/textual_inversion/learn_schedule.py index f63fc72f..c56bea45 100644 --- a/modules/textual_inversion/learn_schedule.py +++ b/modules/textual_inversion/learn_schedule.py @@ -12,7 +12,7 @@ class LearnScheduleIterator: self.it = 0 self.maxit = 0 try: - for i, pair in enumerate(pairs): + for pair in pairs: if not pair.strip(): continue tmp = pair.split(':') @@ -32,8 +32,8 @@ class LearnScheduleIterator: self.maxit += 1 return assert self.rates - except (ValueError, AssertionError): - raise Exception('Invalid learning rate schedule. It should be a number or, for example, like "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000.') + except (ValueError, AssertionError) as e: + raise Exception('Invalid learning rate schedule. It should be a number or, for example, like "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000.') from e def __iter__(self): diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index da0bcb26..a009d8e8 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -1,13 +1,9 @@ import os from PIL import Image, ImageOps import math -import platform -import sys import tqdm -import time from modules import paths, shared, images, deepbooru -from modules.shared import opts, cmd_opts from modules.textual_inversion import autocrop @@ -129,7 +125,7 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr default=None ) return wh and center_crop(image, *wh) - + def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): width = process_width diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 4368eb63..d489ed1e 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -1,7 +1,6 @@ import os import sys import traceback -import inspect from collections import namedtuple import torch @@ -30,7 +29,7 @@ textual_inversion_templates = {} def list_textual_inversion_templates(): textual_inversion_templates.clear() - for root, dirs, fns in os.walk(shared.cmd_opts.textual_inversion_templates_dir): + for root, _, fns in os.walk(shared.cmd_opts.textual_inversion_templates_dir): for fn in fns: path = os.path.join(root, fn) @@ -167,8 +166,7 @@ class EmbeddingDatabase: # textual inversion embeddings if 'string_to_param' in data: param_dict = data['string_to_param'] - if hasattr(param_dict, '_parameters'): - param_dict = getattr(param_dict, '_parameters') # fix for torch 1.12.1 loading saved file from torch 1.11 + param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11 assert len(param_dict) == 1, 'embedding file has multiple terms in it' emb = next(iter(param_dict.items()))[1] # diffuser concepts @@ -199,7 +197,7 @@ class EmbeddingDatabase: if not os.path.isdir(embdir.path): return - for root, dirs, fns in os.walk(embdir.path, followlinks=True): + for root, _, fns in os.walk(embdir.path, followlinks=True): for fn in fns: try: fullfn = os.path.join(root, fn) @@ -216,7 +214,7 @@ class EmbeddingDatabase: def load_textual_inversion_embeddings(self, force_reload=False): if not force_reload: need_reload = False - for path, embdir in self.embedding_dirs.items(): + for embdir in self.embedding_dirs.values(): if embdir.has_changed(): need_reload = True break @@ -229,7 +227,7 @@ class EmbeddingDatabase: self.skipped_embeddings.clear() self.expected_shape = self.get_expected_shape() - for path, embdir in self.embedding_dirs.items(): + for embdir in self.embedding_dirs.values(): self.load_from_dir(embdir) embdir.update() @@ -325,16 +323,16 @@ def tensorboard_add(tensorboard_writer, loss, global_step, step, learn_rate, epo tensorboard_add_scaler(tensorboard_writer, f"Learn rate/train/epoch-{epoch_num}", learn_rate, step) def tensorboard_add_scaler(tensorboard_writer, tag, value, step): - tensorboard_writer.add_scalar(tag=tag, + tensorboard_writer.add_scalar(tag=tag, scalar_value=value, global_step=step) def tensorboard_add_image(tensorboard_writer, tag, pil_image, step): # Convert a pil image to a torch tensor img_tensor = torch.as_tensor(np.array(pil_image, copy=True)) - img_tensor = img_tensor.view(pil_image.size[1], pil_image.size[0], + img_tensor = img_tensor.view(pil_image.size[1], pil_image.size[0], len(pil_image.getbands())) img_tensor = img_tensor.permute((2, 0, 1)) - + tensorboard_writer.add_image(tag, img_tensor, global_step=step) def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, data_root, template_file, template_filename, steps, save_model_every, create_image_every, log_directory, name="embedding"): @@ -404,7 +402,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st if initial_step >= steps: shared.state.textinfo = "Model has already been trained beyond specified max steps" return embedding, filename - + scheduler = LearnRateScheduler(learn_rate, steps, initial_step) clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else \ torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else \ @@ -414,7 +412,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st # dataset loading may take a while, so input validations and early returns should be done before this shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." old_parallel_processing_allowed = shared.parallel_processing_allowed - + if shared.opts.training_enable_tensorboard: tensorboard_writer = tensorboard_setup(log_directory) @@ -441,7 +439,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st optimizer_saved_dict = torch.load(f"{filename}.optim", map_location='cpu') if embedding.checksum() == optimizer_saved_dict.get('hash', None): optimizer_state_dict = optimizer_saved_dict.get('optimizer_state_dict', None) - + if optimizer_state_dict is not None: optimizer.load_state_dict(optimizer_state_dict) print("Loaded existing optimizer from checkpoint") @@ -470,7 +468,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st try: sd_hijack_checkpoint.add() - for i in range((steps-initial_step) * gradient_step): + for _ in range((steps-initial_step) * gradient_step): if scheduler.finished: break if shared.state.interrupted: @@ -487,7 +485,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st if clip_grad: clip_grad_sched.step(embedding.step) - + with devices.autocast(): x = batch.latent_sample.to(devices.device, non_blocking=pin_memory) if use_weight: @@ -515,7 +513,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st # go back until we reach gradient accumulation steps if (j + 1) % gradient_step != 0: continue - + if clip_grad: clip_grad(embedding.vec, clip_grad_sched.learn_rate) @@ -603,7 +601,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st try: vectorSize = list(data['string_to_param'].values())[0].shape[0] - except Exception as e: + except Exception: vectorSize = '?' checkpoint = sd_models.select_checkpoint() diff --git a/modules/txt2img.py b/modules/txt2img.py index 16841d0f..f022381c 100644 --- a/modules/txt2img.py +++ b/modules/txt2img.py @@ -1,18 +1,15 @@ import modules.scripts -from modules import sd_samplers +from modules import sd_samplers, processing from modules.generation_parameters_copypaste import create_override_settings_dict -from modules.processing import StableDiffusionProcessing, Processed, StableDiffusionProcessingTxt2Img, \ - StableDiffusionProcessingImg2Img, process_images from modules.shared import opts, cmd_opts import modules.shared as shared -import modules.processing as processing from modules.ui import plaintext_to_html def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, override_settings_texts, *args): override_settings = create_override_settings_dict(override_settings_texts) - p = StableDiffusionProcessingTxt2Img( + p = processing.StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples, outpath_grids=opts.outdir_grids or opts.outdir_txt2img_grids, @@ -53,7 +50,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step processed = modules.scripts.scripts_txt2img.run(p, *args) if processed is None: - processed = process_images(p) + processed = processing.process_images(p) p.close() diff --git a/modules/ui.py b/modules/ui.py index d02f6e82..8e51e782 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1,29 +1,23 @@ -import html import json -import math import mimetypes import os -import platform -import random import sys -import tempfile -import time import traceback -from functools import partial, reduce +from functools import reduce import warnings import gradio as gr import gradio.routes import gradio.utils import numpy as np -from PIL import Image, PngImagePlugin +from PIL import Image, PngImagePlugin # noqa: F401 from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call -from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks, postprocessing, ui_components, ui_common, ui_postprocessing, progress -from modules.ui_components import FormRow, FormColumn, FormGroup, ToolButton, FormHTML +from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks, ui_common, ui_postprocessing, progress, ui_loadsave +from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML from modules.paths import script_path, data_path -from modules.shared import opts, cmd_opts, restricted_opts +from modules.shared import opts, cmd_opts import modules.codeformer_model import modules.generation_parameters_copypaste as parameters_copypaste @@ -34,7 +28,6 @@ import modules.shared as shared import modules.styles import modules.textual_inversion.ui from modules import prompt_parser -from modules.images import save_image from modules.sd_hijack import model_hijack from modules.sd_samplers import samplers, samplers_for_img2img from modules.textual_inversion import textual_inversion @@ -93,16 +86,6 @@ def send_gradio_gallery_to_image(x): return None return image_from_url_text(x[0]) -def visit(x, func, path=""): - if hasattr(x, 'children'): - if isinstance(x, gr.Tabs) and x.elem_id is not None: - # Tabs element can't have a label, have to use elem_id instead - func(f"{path}/Tabs@{x.elem_id}", x) - for c in x.children: - visit(c, func, path) - elif x.label is not None: - func(f"{path}/{x.label}", x) - def add_style(name: str, prompt: str, negative_prompt: str): if name is None: @@ -246,7 +229,7 @@ def connect_reuse_seed(seed: gr.Number, reuse_seed: gr.Button, generation_info: all_seeds = gen_info.get('all_seeds', [-1]) res = all_seeds[index if 0 <= index < len(all_seeds) else 0] - except json.decoder.JSONDecodeError as e: + except json.decoder.JSONDecodeError: if gen_info_string != '': print("Error parsing JSON generation info:", file=sys.stderr) print(gen_info_string, file=sys.stderr) @@ -423,7 +406,7 @@ def create_sampler_and_steps_selection(choices, tabname): def ordered_ui_categories(): user_order = {x.strip(): i * 2 + 1 for i, x in enumerate(shared.opts.ui_reorder.split(","))} - for i, category in sorted(enumerate(shared.ui_reorder_categories), key=lambda x: user_order.get(x[1], x[0] * 2 + 0)): + for _, category in sorted(enumerate(shared.ui_reorder_categories), key=lambda x: user_order.get(x[1], x[0] * 2 + 0)): yield category @@ -736,8 +719,8 @@ def create_ui(): with gr.TabItem('Batch', id='batch', elem_id="img2img_batch_tab") as tab_batch: hidden = '
Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else '' gr.HTML( - f"

Process images in a directory on the same machine where the server is running." + - f"
Use an empty output directory to save pictures normally instead of writing to the output directory." + + "

Process images in a directory on the same machine where the server is running." + + "
Use an empty output directory to save pictures normally instead of writing to the output directory." + f"
Add inpaint batch mask directory to enable inpaint batch processing." f"{hidden}

" ) @@ -746,7 +729,6 @@ def create_ui(): img2img_batch_inpaint_mask_dir = gr.Textbox(label="Inpaint batch mask directory (required for inpaint batch processing only)", **shared.hide_dirs, elem_id="img2img_batch_inpaint_mask_dir") img2img_tabs = [tab_img2img, tab_sketch, tab_inpaint, tab_inpaint_color, tab_inpaint_upload, tab_batch] - img2img_image_inputs = [init_img, sketch, init_img_with_mask, inpaint_color_sketch] for i, tab in enumerate(img2img_tabs): tab.select(fn=lambda tabnum=i: tabnum, inputs=[], outputs=[img2img_selected_tab]) @@ -1189,7 +1171,7 @@ def create_ui(): process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight") process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight") process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug") - + with gr.Column(visible=False) as process_multicrop_col: gr.Markdown('Each image is center-cropped with an automatically chosen width and height.') with gr.Row(): @@ -1201,7 +1183,7 @@ def create_ui(): with gr.Row(): process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective") process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold") - + with gr.Row(): with gr.Column(scale=3): gr.HTML(value="") @@ -1230,7 +1212,7 @@ def create_ui(): ) def get_textual_inversion_template_names(): - return sorted([x for x in textual_inversion.textual_inversion_templates]) + return sorted(textual_inversion.textual_inversion_templates) with gr.Tab(label="Train", id="train"): gr.HTML(value="

Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images [wiki]

") @@ -1238,13 +1220,13 @@ def create_ui(): train_embedding_name = gr.Dropdown(label='Embedding', elem_id="train_embedding", choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())) create_refresh_button(train_embedding_name, sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings, lambda: {"choices": sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())}, "refresh_train_embedding_name") - train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', elem_id="train_hypernetwork", choices=[x for x in shared.hypernetworks.keys()]) - create_refresh_button(train_hypernetwork_name, shared.reload_hypernetworks, lambda: {"choices": sorted([x for x in shared.hypernetworks.keys()])}, "refresh_train_hypernetwork_name") + train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', elem_id="train_hypernetwork", choices=sorted(shared.hypernetworks)) + create_refresh_button(train_hypernetwork_name, shared.reload_hypernetworks, lambda: {"choices": sorted(shared.hypernetworks)}, "refresh_train_hypernetwork_name") with FormRow(): embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005", elem_id="train_embedding_learn_rate") hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001", elem_id="train_hypernetwork_learn_rate") - + with FormRow(): clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"]) clip_grad_value = gr.Textbox(placeholder="Gradient clip value", value="0.1", show_label=False) @@ -1290,8 +1272,8 @@ def create_ui(): with gr.Column(elem_id='ti_gallery_container'): ti_output = gr.Text(elem_id="ti_output", value="", show_label=False) - ti_gallery = gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery').style(columns=4) - ti_progress = gr.HTML(elem_id="ti_progress", value="") + gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery').style(columns=4) + gr.HTML(elem_id="ti_progress", value="") ti_outcome = gr.HTML(elem_id="ti_error", value="") create_embedding.click( @@ -1479,6 +1461,8 @@ def create_ui(): return res + loadsave = ui_loadsave.UiLoadsave(cmd_opts.ui_config_file) + components = [] component_dict = {} shared.settings_components = component_dict @@ -1566,6 +1550,9 @@ def create_ui(): current_row.__exit__() current_tab.__exit__() + with gr.TabItem("Defaults", id="defaults", elem_id="settings_tab_defaults"): + loadsave.create_ui() + with gr.TabItem("Actions", id="actions", elem_id="settings_tab_actions"): request_notifications = gr.Button(value='Request browser notifications', elem_id="request_notifications") download_localization = gr.Button(value='Download localization template', elem_id="download_localization") @@ -1578,7 +1565,7 @@ def create_ui(): gr.HTML(shared.html("licenses.html"), elem_id="licenses") gr.Button(value="Show all pages", elem_id="settings_show_all_pages") - + def unload_sd_weights(): modules.sd_models.unload_model_weights() @@ -1639,7 +1626,7 @@ def create_ui(): (extras_interface, "Extras", "extras"), (pnginfo_interface, "PNG Info", "pnginfo"), (modelmerger_interface, "Checkpoint Merger", "modelmerger"), - (train_interface, "Train", "ti"), + (train_interface, "Train", "train"), ] interfaces += script_callbacks.ui_tabs_callback() @@ -1654,7 +1641,7 @@ def create_ui(): with gr.Blocks(theme=shared.gradio_theme, analytics_enabled=False, title="Stable Diffusion") as demo: with gr.Row(elem_id="quicksettings", variant="compact"): - for i, k, item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])): + for _i, k, _item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])): component = create_setting_component(k, is_quicksettings=True) component_dict[k] = component @@ -1667,8 +1654,18 @@ def create_ui(): with gr.TabItem(label, id=ifid, elem_id=f"tab_{ifid}"): interface.render() + for interface, _label, ifid in interfaces: + if ifid in ["extensions", "settings"]: + continue + + loadsave.add_block(interface, ifid) + + loadsave.add_component(f"webui/Tabs@{tabs.elem_id}", tabs) + + loadsave.setup_ui() + if os.path.exists(os.path.join(script_path, "notification.mp3")): - audio_notification = gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False) + gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False) footer = shared.html("footer.html") footer = footer.format(versions=versions_html()) @@ -1681,7 +1678,7 @@ def create_ui(): outputs=[text_settings, result], ) - for i, k, item in quicksettings_list: + for _i, k, _item in quicksettings_list: component = component_dict[k] info = opts.data_labels[k] @@ -1755,97 +1752,8 @@ def create_ui(): ] ) - ui_config_file = cmd_opts.ui_config_file - ui_settings = {} - settings_count = len(ui_settings) - error_loading = False - - try: - if os.path.exists(ui_config_file): - with open(ui_config_file, "r", encoding="utf8") as file: - ui_settings = json.load(file) - except Exception: - error_loading = True - print("Error loading settings:", file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - - def loadsave(path, x): - def apply_field(obj, field, condition=None, init_field=None): - key = f"{path}/{field}" - - if getattr(obj, 'custom_script_source', None) is not None: - key = f"customscript/{obj.custom_script_source}/{key}" - - if getattr(obj, 'do_not_save_to_config', False): - return - - saved_value = ui_settings.get(key, None) - if saved_value is None: - ui_settings[key] = getattr(obj, field) - elif condition and not condition(saved_value): - pass - - # this warning is generally not useful; - # print(f'Warning: Bad ui setting value: {key}: {saved_value}; Default value "{getattr(obj, field)}" will be used instead.') - else: - setattr(obj, field, saved_value) - if init_field is not None: - init_field(saved_value) - - if type(x) in [gr.Slider, gr.Radio, gr.Checkbox, gr.Textbox, gr.Number, gr.Dropdown, ToolButton] and x.visible: - apply_field(x, 'visible') - - if type(x) == gr.Slider: - apply_field(x, 'value') - apply_field(x, 'minimum') - apply_field(x, 'maximum') - apply_field(x, 'step') - - if type(x) == gr.Radio: - apply_field(x, 'value', lambda val: val in x.choices) - - if type(x) == gr.Checkbox: - apply_field(x, 'value') - - if type(x) == gr.Textbox: - apply_field(x, 'value') - - if type(x) == gr.Number: - apply_field(x, 'value') - - if type(x) == gr.Dropdown: - def check_dropdown(val): - if getattr(x, 'multiselect', False): - return all([value in x.choices for value in val]) - else: - return val in x.choices - - apply_field(x, 'value', check_dropdown, getattr(x, 'init_field', None)) - - def check_tab_id(tab_id): - tab_items = list(filter(lambda e: isinstance(e, gr.TabItem), x.children)) - if type(tab_id) == str: - tab_ids = [t.id for t in tab_items] - return tab_id in tab_ids - elif type(tab_id) == int: - return tab_id >= 0 and tab_id < len(tab_items) - else: - return False - - if type(x) == gr.Tabs: - apply_field(x, 'selected', check_tab_id) - - visit(txt2img_interface, loadsave, "txt2img") - visit(img2img_interface, loadsave, "img2img") - visit(extras_interface, loadsave, "extras") - visit(modelmerger_interface, loadsave, "modelmerger") - visit(train_interface, loadsave, "train") - - loadsave(f"webui/Tabs@{tabs.elem_id}", tabs) - - if not error_loading and (not os.path.exists(ui_config_file) or settings_count != len(ui_settings)): - with open(ui_config_file, "w", encoding="utf8") as file: - json.dump(ui_settings, file, indent=4) + loadsave.dump_defaults() + demo.ui_loadsave = loadsave # Required as a workaround for change() event not triggering when loading values from ui-config.json interp_description.value = update_interp_description(interp_method.value) @@ -1863,12 +1771,11 @@ def webpath(fn): def javascript_html(): - script_js = os.path.join(script_path, "script.js") - head = f'\n' + # Ensure localization is in `window` before scripts + head = f'\n' - inline = f"{localization.localization_js(shared.opts.localization)};" - if cmd_opts.theme is not None: - inline += f"set_theme('{cmd_opts.theme}');" + script_js = os.path.join(script_path, "script.js") + head += f'\n' for script in modules.scripts.list_scripts("javascript", ".js"): head += f'\n' @@ -1876,7 +1783,8 @@ def javascript_html(): for script in modules.scripts.list_scripts("javascript", ".mjs"): head += f'\n' - head += f'\n' + if cmd_opts.theme: + head += f'\n' return head @@ -1933,15 +1841,15 @@ def versions_html(): return f""" version: {tag} - •  + •  python: {python_version} - •  + •  torch: {getattr(torch, '__long_version__',torch.__version__)} - •  + •  xformers: {xformers_version} - •  + •  gradio: {gr.__version__} - •  + •  checkpoint: N/A """ diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index d9faf85a..d7a0f685 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -1,6 +1,7 @@ import json import os.path import sys +import threading import time from datetime import datetime import traceback @@ -140,7 +141,9 @@ def extension_table(): Extension URL - Version + Branch + Version + Date Update @@ -148,6 +151,7 @@ def extension_table(): """ for ext in extensions.extensions: + ext: extensions.Extension ext.read_info_from_repo() remote = f"""{html.escape("built-in" if ext.is_builtin else ext.remote or '')}""" @@ -169,7 +173,9 @@ def extension_table(): {html.escape(ext.name)} {remote} + {ext.branch} {version_link} + {time.asctime(time.gmtime(ext.commit_date))} {ext_status} """ @@ -467,7 +473,7 @@ def refresh_available_extensions_from_data(hide_tags, sort_column, filter_text=" {html.escape(description)}

Added: {html.escape(added)}

{install_code} - + """ for tag in [x for x in extension_tags if x not in tags]: @@ -484,13 +490,20 @@ def refresh_available_extensions_from_data(hide_tags, sort_column, filter_text=" return code, list(tags) +def preload_extensions_git_metadata(): + for extension in extensions.extensions: + extension.read_info_from_repo() + + def create_ui(): import modules.ui config_states.list_config_states() + threading.Thread(target=preload_extensions_git_metadata).start() + with gr.Blocks(analytics_enabled=False) as ui: - with gr.Tabs(elem_id="tabs_extensions") as tabs: + with gr.Tabs(elem_id="tabs_extensions"): with gr.TabItem("Installed", id="installed"): with gr.Row(elem_id="extensions_installed_top"): @@ -508,7 +521,8 @@ def create_ui(): """ info = gr.HTML(html) - extensions_table = gr.HTML(lambda: extension_table()) + extensions_table = gr.HTML('Loading...') + ui.load(fn=extension_table, inputs=[], outputs=[extensions_table]) apply.click( fn=apply_and_restart, @@ -535,9 +549,9 @@ def create_ui(): hide_tags = gr.CheckboxGroup(value=["ads", "localization", "installed"], label="Hide extensions with tags", choices=["script", "ads", "localization", "installed"]) sort_column = gr.Radio(value="newest first", label="Order", choices=["newest first", "oldest first", "a-z", "z-a", "internal order", ], type="index") - with gr.Row(): + with gr.Row(): search_extensions_text = gr.Text(label="Search").style(container=False) - + install_result = gr.HTML() available_extensions_table = gr.HTML() @@ -579,9 +593,9 @@ def create_ui(): install_result = gr.HTML(elem_id="extension_install_result") install_button.click( - fn=modules.ui.wrap_gradio_call(install_extension_from_url, extra_outputs=[gr.update()]), + fn=modules.ui.wrap_gradio_call(lambda *args: [gr.update(), *install_extension_from_url(*args)], extra_outputs=[gr.update(), gr.update()]), inputs=[install_dirname, install_url, install_branch], - outputs=[extensions_table, install_result], + outputs=[install_url, extensions_table, install_result], ) with gr.TabItem("Backup/Restore"): @@ -595,7 +609,8 @@ def create_ui(): config_save_button = gr.Button(value="Save Current Config") config_states_info = gr.HTML("") - config_states_table = gr.HTML(lambda: update_config_states_table("Current")) + config_states_table = gr.HTML("Loading...") + ui.load(fn=update_config_states_table, inputs=[config_states_list], outputs=[config_states_table]) config_save_button.click(fn=save_config_state, inputs=[config_save_name], outputs=[config_states_list, config_states_info]) @@ -608,4 +623,5 @@ def create_ui(): outputs=[config_states_table], ) + return ui diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index 8c3dea56..752cf2b8 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -1,4 +1,3 @@ -import glob import os.path import urllib.parse from pathlib import Path @@ -27,11 +26,11 @@ def register_page(page): def fetch_file(filename: str = ""): from starlette.responses import FileResponse - if not any([Path(x).absolute() in Path(filename).absolute().parents for x in allowed_dirs]): + if not any(Path(x).absolute() in Path(filename).absolute().parents for x in allowed_dirs): raise ValueError(f"File cannot be fetched: {filename}. Must be in one of directories registered by extra pages.") ext = os.path.splitext(filename)[1].lower() - if ext not in (".png", ".jpg", ".webp"): + if ext not in (".png", ".jpg", ".jpeg", ".webp"): raise ValueError(f"File cannot be fetched: {filename}. Only png and jpg and webp.") # would profit from returning 304 @@ -91,7 +90,7 @@ class ExtraNetworksPage: subdirs = {} for parentdir in [os.path.abspath(x) for x in self.allowed_directories_for_previews()]: - for root, dirs, files in os.walk(parentdir): + for root, dirs, _ in os.walk(parentdir, followlinks=True): for dirname in dirs: x = os.path.join(root, dirname) @@ -195,7 +194,7 @@ class ExtraNetworksPage: Find a preview PNG for a given path (without extension) and call link_preview on it. """ - preview_extensions = ["png", "jpg", "webp"] + preview_extensions = ["png", "jpg", "jpeg", "webp"] if shared.opts.samples_format not in preview_extensions: preview_extensions.append(shared.opts.samples_format) @@ -263,13 +262,13 @@ def create_ui(container, button, tabname): ui.stored_extra_pages = pages_in_preferred_order(extra_pages.copy()) ui.tabname = tabname - with gr.Tabs(elem_id=tabname+"_extra_tabs") as tabs: + with gr.Tabs(elem_id=tabname+"_extra_tabs"): for page in ui.stored_extra_pages: page_id = page.title.lower().replace(" ", "_") with gr.Tab(page.title, id=page_id): elem_id = f"{tabname}_{page_id}_cards_html" - page_elem = gr.HTML('', elem_id=elem_id) + page_elem = gr.HTML('Loading...', elem_id=elem_id) ui.pages.append(page_elem) page_elem.change(fn=lambda: None, _js='function(){applyExtraNetworkFilter(' + json.dumps(tabname) + '); return []}', inputs=[], outputs=[]) @@ -283,13 +282,24 @@ def create_ui(container, button, tabname): def toggle_visibility(is_visible): is_visible = not is_visible - if is_visible and not ui.pages_contents: + return is_visible, gr.update(visible=is_visible), gr.update(variant=("secondary-down" if is_visible else "secondary")) + + def fill_tabs(is_empty): + """Creates HTML for extra networks' tabs when the extra networks button is clicked for the first time.""" + + if not ui.pages_contents: refresh() - return is_visible, gr.update(visible=is_visible), gr.update(variant=("secondary-down" if is_visible else "secondary")), *ui.pages_contents + if is_empty: + return True, *ui.pages_contents + + return True, *[gr.update() for _ in ui.pages_contents] state_visible = gr.State(value=False) - button.click(fn=toggle_visibility, inputs=[state_visible], outputs=[state_visible, container, button, *ui.pages]) + button.click(fn=toggle_visibility, inputs=[state_visible], outputs=[state_visible, container, button], show_progress=False) + + state_empty = gr.State(value=True) + button.click(fn=fill_tabs, inputs=[state_empty], outputs=[state_empty, *ui.pages], show_progress=False) def refresh(): for pg in ui.stored_extra_pages: @@ -327,7 +337,7 @@ def setup_ui(ui, gallery): is_allowed = False for extra_page in ui.stored_extra_pages: - if any([path_is_parent(x, filename) for x in extra_page.allowed_directories_for_previews()]): + if any(path_is_parent(x, filename) for x in extra_page.allowed_directories_for_previews()): is_allowed = True break diff --git a/modules/ui_loadsave.py b/modules/ui_loadsave.py new file mode 100644 index 00000000..728fec9e --- /dev/null +++ b/modules/ui_loadsave.py @@ -0,0 +1,208 @@ +import json +import os + +import gradio as gr + +from modules import errors +from modules.ui_components import ToolButton + + +class UiLoadsave: + """allows saving and restorig default values for gradio components""" + + def __init__(self, filename): + self.filename = filename + self.ui_settings = {} + self.component_mapping = {} + self.error_loading = False + self.finalized_ui = False + + self.ui_defaults_view = None + self.ui_defaults_apply = None + self.ui_defaults_review = None + + try: + if os.path.exists(self.filename): + self.ui_settings = self.read_from_file() + except Exception as e: + self.error_loading = True + errors.display(e, "loading settings") + + def add_component(self, path, x): + """adds component to the registry of tracked components""" + + assert not self.finalized_ui + + def apply_field(obj, field, condition=None, init_field=None): + key = f"{path}/{field}" + + if getattr(obj, 'custom_script_source', None) is not None: + key = f"customscript/{obj.custom_script_source}/{key}" + + if getattr(obj, 'do_not_save_to_config', False): + return + + saved_value = self.ui_settings.get(key, None) + if saved_value is None: + self.ui_settings[key] = getattr(obj, field) + elif condition and not condition(saved_value): + pass + else: + setattr(obj, field, saved_value) + if init_field is not None: + init_field(saved_value) + + if field == 'value' and key not in self.component_mapping: + self.component_mapping[key] = x + + if type(x) in [gr.Slider, gr.Radio, gr.Checkbox, gr.Textbox, gr.Number, gr.Dropdown, ToolButton] and x.visible: + apply_field(x, 'visible') + + if type(x) == gr.Slider: + apply_field(x, 'value') + apply_field(x, 'minimum') + apply_field(x, 'maximum') + apply_field(x, 'step') + + if type(x) == gr.Radio: + apply_field(x, 'value', lambda val: val in x.choices) + + if type(x) == gr.Checkbox: + apply_field(x, 'value') + + if type(x) == gr.Textbox: + apply_field(x, 'value') + + if type(x) == gr.Number: + apply_field(x, 'value') + + if type(x) == gr.Dropdown: + def check_dropdown(val): + if getattr(x, 'multiselect', False): + return all(value in x.choices for value in val) + else: + return val in x.choices + + apply_field(x, 'value', check_dropdown, getattr(x, 'init_field', None)) + + def check_tab_id(tab_id): + tab_items = list(filter(lambda e: isinstance(e, gr.TabItem), x.children)) + if type(tab_id) == str: + tab_ids = [t.id for t in tab_items] + return tab_id in tab_ids + elif type(tab_id) == int: + return 0 <= tab_id < len(tab_items) + else: + return False + + if type(x) == gr.Tabs: + apply_field(x, 'selected', check_tab_id) + + def add_block(self, x, path=""): + """adds all components inside a gradio block x to the registry of tracked components""" + + if hasattr(x, 'children'): + if isinstance(x, gr.Tabs) and x.elem_id is not None: + # Tabs element can't have a label, have to use elem_id instead + self.add_component(f"{path}/Tabs@{x.elem_id}", x) + for c in x.children: + self.add_block(c, path) + elif x.label is not None: + self.add_component(f"{path}/{x.label}", x) + + def read_from_file(self): + with open(self.filename, "r", encoding="utf8") as file: + return json.load(file) + + def write_to_file(self, current_ui_settings): + with open(self.filename, "w", encoding="utf8") as file: + json.dump(current_ui_settings, file, indent=4) + + def dump_defaults(self): + """saves default values to a file unless tjhe file is present and there was an error loading default values at start""" + + if self.error_loading and os.path.exists(self.filename): + return + + self.write_to_file(self.ui_settings) + + def iter_changes(self, current_ui_settings, values): + """ + given a dictionary with defaults from a file and current values from gradio elements, returns + an iterator over tuples of values that are not the same between the file and the current; + tuple contents are: path, old value, new value + """ + + for (path, component), new_value in zip(self.component_mapping.items(), values): + old_value = current_ui_settings.get(path) + + choices = getattr(component, 'choices', None) + if isinstance(new_value, int) and choices: + if new_value >= len(choices): + continue + + new_value = choices[new_value] + + if new_value == old_value: + continue + + if old_value is None and new_value == '' or new_value == []: + continue + + yield path, old_value, new_value + + def ui_view(self, *values): + text = [""] + + for path, old_value, new_value in self.iter_changes(self.read_from_file(), values): + if old_value is None: + old_value = "None" + + text.append(f"") + + if len(text) == 1: + text.append("") + + text.append("") + return "".join(text) + + def ui_apply(self, *values): + num_changed = 0 + + current_ui_settings = self.read_from_file() + + for path, _, new_value in self.iter_changes(current_ui_settings.copy(), values): + num_changed += 1 + current_ui_settings[path] = new_value + + if num_changed == 0: + return "No changes." + + self.write_to_file(current_ui_settings) + + return f"Wrote {num_changed} changes." + + def create_ui(self): + """creates ui elements for editing defaults UI, without adding any logic to them""" + + gr.HTML( + f"This page allows you to change default values in UI elements on other tabs.
" + f"Make your changes, press 'View changes' to review the changed default values,
" + f"then press 'Apply' to write them to {self.filename}.
" + f"New defaults will apply after you restart the UI.
" + ) + + with gr.Row(): + self.ui_defaults_view = gr.Button(value='View changes', elem_id="ui_defaults_view", variant="secondary") + self.ui_defaults_apply = gr.Button(value='Apply', elem_id="ui_defaults_apply", variant="primary") + + self.ui_defaults_review = gr.HTML("") + + def setup_ui(self): + """adds logic to elements created with create_ui; all add_block class must be made before this""" + + assert not self.finalized_ui + self.finalized_ui = True + + self.ui_defaults_view.click(fn=self.ui_view, inputs=list(self.component_mapping.values()), outputs=[self.ui_defaults_review]) + self.ui_defaults_apply.click(fn=self.ui_apply, inputs=list(self.component_mapping.values()), outputs=[self.ui_defaults_review]) diff --git a/modules/ui_postprocessing.py b/modules/ui_postprocessing.py index f25639e5..c7dc1154 100644 --- a/modules/ui_postprocessing.py +++ b/modules/ui_postprocessing.py @@ -1,5 +1,5 @@ import gradio as gr -from modules import scripts_postprocessing, scripts, shared, gfpgan_model, codeformer_model, ui_common, postprocessing, call_queue +from modules import scripts, shared, ui_common, postprocessing, call_queue import modules.generation_parameters_copypaste as parameters_copypaste diff --git a/modules/ui_tempdir.py b/modules/ui_tempdir.py index 46fa9cb0..f05049e1 100644 --- a/modules/ui_tempdir.py +++ b/modules/ui_tempdir.py @@ -23,7 +23,7 @@ def register_tmp_file(gradio, filename): def check_tmp_file(gradio, filename): if hasattr(gradio, 'temp_file_sets'): - return any([filename in fileset for fileset in gradio.temp_file_sets]) + return any(filename in fileset for fileset in gradio.temp_file_sets) if hasattr(gradio, 'temp_dirs'): return any(Path(temp_dir).resolve() in Path(filename).resolve().parents for temp_dir in gradio.temp_dirs) @@ -72,7 +72,7 @@ def cleanup_tmpdr(): if temp_dir == "" or not os.path.isdir(temp_dir): return - for root, dirs, files in os.walk(temp_dir, topdown=False): + for root, _, files in os.walk(temp_dir, topdown=False): for name in files: _, extension = os.path.splitext(name) if extension != ".png": diff --git a/modules/upscaler.py b/modules/upscaler.py index e2eaa730..8acb6e96 100644 --- a/modules/upscaler.py +++ b/modules/upscaler.py @@ -2,8 +2,6 @@ import os from abc import abstractmethod import PIL -import numpy as np -import torch from PIL import Image import modules.shared @@ -43,9 +41,9 @@ class Upscaler: os.makedirs(self.model_path, exist_ok=True) try: - import cv2 + import cv2 # noqa: F401 self.can_tile = True - except: + except Exception: pass @abstractmethod @@ -57,7 +55,7 @@ class Upscaler: dest_w = int(img.width * scale) dest_h = int(img.height * scale) - for i in range(3): + for _ in range(3): shape = (img.width, img.height) img = self.do_upscale(img, selected_model) diff --git a/modules/xlmr.py b/modules/xlmr.py index beab3fdf..a407a3ca 100644 --- a/modules/xlmr.py +++ b/modules/xlmr.py @@ -1,4 +1,4 @@ -from transformers import BertPreTrainedModel,BertModel,BertConfig +from transformers import BertPreTrainedModel, BertConfig import torch.nn as nn import torch from transformers.models.xlm_roberta.configuration_xlm_roberta import XLMRobertaConfig @@ -28,7 +28,7 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): config_class = BertSeriesConfig def __init__(self, config=None, **kargs): - # modify initialization for autoloading + # modify initialization for autoloading if config is None: config = XLMRobertaConfig() config.attention_probs_dropout_prob= 0.1 @@ -74,7 +74,7 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): text["attention_mask"] = torch.tensor( text['attention_mask']).to(device) features = self(**text) - return features['projection_state'] + return features['projection_state'] def forward( self, @@ -134,4 +134,4 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): class RobertaSeriesModelWithTransformation(BertSeriesModelWithTransformation): base_model_prefix = 'roberta' - config_class= RobertaSeriesConfig \ No newline at end of file + config_class= RobertaSeriesConfig diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 00000000..d4a1bbf4 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,32 @@ +[tool.ruff] + +target-version = "py39" + +extend-select = [ + "B", + "C", + "I", + "W", +] + +exclude = [ + "extensions", + "extensions-disabled", +] + +ignore = [ + "E501", # Line too long + "E731", # Do not assign a `lambda` expression, use a `def` + + "I001", # Import block is un-sorted or un-formatted + "C901", # Function is too complex + "C408", # Rewrite as a literal + "W605", # invalid escape sequence, messes with some docstrings +] + +[tool.ruff.per-file-ignores] +"webui.py" = ["E402"] # Module level import not at top of file + +[tool.ruff.flake8-bugbear] +# Allow default arguments like, e.g., `data: List[str] = fastapi.Query(None)`. +extend-immutable-calls = ["fastapi.Depends", "fastapi.security.HTTPBasic"] diff --git a/requirements.txt b/requirements.txt index 35987a13..302b3dab 100644 --- a/requirements.txt +++ b/requirements.txt @@ -2,8 +2,6 @@ astunparse blendmodes accelerate basicsr -fonts -font-roboto gfpgan gradio==3.29.0 numpy @@ -31,3 +29,4 @@ torchsde safetensors psutil rich +tomesd diff --git a/requirements_versions.txt b/requirements_versions.txt index 7bce02e5..17ae9484 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -5,19 +5,17 @@ basicsr==1.4.2 gfpgan==1.3.8 gradio==3.29.0 numpy==1.23.5 -Pillow==9.4.0 +Pillow==9.5.0 realesrgan==0.3.0 torch omegaconf==2.2.3 pytorch_lightning==1.9.4 -scikit-image==0.19.2 -fonts -font-roboto +scikit-image==0.20.0 timm==0.6.7 piexif==1.1.3 einops==0.4.1 jsonmerge==1.8.0 -clean-fid==0.1.29 +clean-fid==0.1.35 resize-right==0.0.2 torchdiffeq==0.2.3 kornia==0.6.7 @@ -28,3 +26,4 @@ torchsde==0.2.5 safetensors==0.3.1 httpcore<=0.15 fastapi==0.94.0 +tomesd==0.1.2 diff --git a/scripts/custom_code.py b/scripts/custom_code.py index f36a3675..cc6f0d49 100644 --- a/scripts/custom_code.py +++ b/scripts/custom_code.py @@ -4,7 +4,7 @@ import ast import copy from modules.processing import Processed -from modules.shared import opts, cmd_opts, state +from modules.shared import cmd_opts def convertExpr2Expression(expr): diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py index bb00fb3f..1e833fa8 100644 --- a/scripts/img2imgalt.py +++ b/scripts/img2imgalt.py @@ -149,9 +149,9 @@ class Script(scripts.Script): sigma_adjustment = gr.Checkbox(label="Sigma adjustment for finding noise for image", value=False, elem_id=self.elem_id("sigma_adjustment")) return [ - info, + info, override_sampler, - override_prompt, original_prompt, original_negative_prompt, + override_prompt, original_prompt, original_negative_prompt, override_steps, st, override_strength, cfg, randomness, sigma_adjustment, @@ -191,17 +191,17 @@ class Script(scripts.Script): self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt, sigma_adjustment) rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, seed_resize_from_h=p.seed_resize_from_h, seed_resize_from_w=p.seed_resize_from_w, p=p) - + combined_noise = ((1 - randomness) * rec_noise + randomness * rand_noise) / ((randomness**2 + (1-randomness)**2) ** 0.5) - + sampler = sd_samplers.create_sampler(p.sampler_name, p.sd_model) sigmas = sampler.model_wrap.get_sigmas(p.steps) - + noise_dt = combined_noise - (p.init_latent / sigmas[0]) - + p.seed = p.seed + 1 - + return sampler.sample_img2img(p, p.init_latent, noise_dt, conditioning, unconditional_conditioning, image_conditioning=p.image_conditioning) p.sample = sample_extra diff --git a/scripts/loopback.py b/scripts/loopback.py index ad6609be..2d5feaf9 100644 --- a/scripts/loopback.py +++ b/scripts/loopback.py @@ -14,7 +14,7 @@ class Script(scripts.Script): def show(self, is_img2img): return is_img2img - def ui(self, is_img2img): + def ui(self, is_img2img): loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4, elem_id=self.elem_id("loops")) final_denoising_strength = gr.Slider(minimum=0, maximum=1, step=0.01, label='Final denoising strength', value=0.5, elem_id=self.elem_id("final_denoising_strength")) denoising_curve = gr.Dropdown(label="Denoising strength curve", choices=["Aggressive", "Linear", "Lazy"], value="Linear") @@ -104,7 +104,7 @@ class Script(scripts.Script): p.seed = processed.seed + 1 p.denoising_strength = calculate_denoising_strength(i + 1) - + if state.skipped: break @@ -121,7 +121,7 @@ class Script(scripts.Script): all_images.append(last_image) p.inpainting_fill = original_inpainting_fill - + if state.interrupted: break @@ -132,7 +132,7 @@ class Script(scripts.Script): if opts.return_grid: grids.append(grid) - + all_images = grids + all_images processed = Processed(p, all_images, initial_seed, initial_info) diff --git a/scripts/outpainting_mk_2.py b/scripts/outpainting_mk_2.py index 670bb8ac..665dbe89 100644 --- a/scripts/outpainting_mk_2.py +++ b/scripts/outpainting_mk_2.py @@ -7,9 +7,9 @@ import modules.scripts as scripts import gradio as gr from PIL import Image, ImageDraw -from modules import images, processing, devices +from modules import images from modules.processing import Processed, process_images -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state # this function is taken from https://github.com/parlance-zz/g-diffuser-bot @@ -72,7 +72,7 @@ def get_matched_noise(_np_src_image, np_mask_rgb, noise_q=1, color_variation=0.0 height = _np_src_image.shape[1] num_channels = _np_src_image.shape[2] - np_src_image = _np_src_image[:] * (1. - np_mask_rgb) + _np_src_image[:] * (1. - np_mask_rgb) np_mask_grey = (np.sum(np_mask_rgb, axis=2) / 3.) img_mask = np_mask_grey > 1e-6 ref_mask = np_mask_grey < 1e-3 diff --git a/scripts/poor_mans_outpainting.py b/scripts/poor_mans_outpainting.py index ddcbd2d3..ea0632b6 100644 --- a/scripts/poor_mans_outpainting.py +++ b/scripts/poor_mans_outpainting.py @@ -4,9 +4,9 @@ import modules.scripts as scripts import gradio as gr from PIL import Image, ImageDraw -from modules import images, processing, devices +from modules import images, devices from modules.processing import Processed, process_images -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state class Script(scripts.Script): @@ -19,7 +19,7 @@ class Script(scripts.Script): def ui(self, is_img2img): if not is_img2img: return None - + pixels = gr.Slider(label="Pixels to expand", minimum=8, maximum=256, step=8, value=128, elem_id=self.elem_id("pixels")) mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id=self.elem_id("mask_blur")) inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='fill', type="index", elem_id=self.elem_id("inpainting_fill")) diff --git a/scripts/postprocessing_upscale.py b/scripts/postprocessing_upscale.py index ef1186ac..edb70ac0 100644 --- a/scripts/postprocessing_upscale.py +++ b/scripts/postprocessing_upscale.py @@ -98,13 +98,13 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing): assert upscaler2 or (upscaler_2_name is None), f'could not find upscaler named {upscaler_2_name}' upscaled_image = self.upscale(pp.image, pp.info, upscaler1, upscale_mode, upscale_by, upscale_to_width, upscale_to_height, upscale_crop) - pp.info[f"Postprocess upscaler"] = upscaler1.name + pp.info["Postprocess upscaler"] = upscaler1.name if upscaler2 and upscaler_2_visibility > 0: second_upscale = self.upscale(pp.image, pp.info, upscaler2, upscale_mode, upscale_by, upscale_to_width, upscale_to_height, upscale_crop) upscaled_image = Image.blend(upscaled_image, second_upscale, upscaler_2_visibility) - pp.info[f"Postprocess upscaler 2"] = upscaler2.name + pp.info["Postprocess upscaler 2"] = upscaler2.name pp.image = upscaled_image @@ -134,4 +134,4 @@ class ScriptPostprocessingUpscaleSimple(ScriptPostprocessingUpscale): assert upscaler1, f'could not find upscaler named {upscaler_name}' pp.image = self.upscale(pp.image, pp.info, upscaler1, 0, upscale_by, 0, 0, False) - pp.info[f"Postprocess upscaler"] = upscaler1.name + pp.info["Postprocess upscaler"] = upscaler1.name diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index e9b11517..88324fe6 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -1,14 +1,11 @@ import math -from collections import namedtuple -from copy import copy -import random import modules.scripts as scripts import gradio as gr from modules import images -from modules.processing import process_images, Processed -from modules.shared import opts, cmd_opts, state +from modules.processing import process_images +from modules.shared import opts, state import modules.sd_samplers @@ -99,7 +96,7 @@ class Script(scripts.Script): p.prompt_for_display = positive_prompt processed = process_images(p) - grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2)) + grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2)) grid = images.draw_prompt_matrix(grid, processed.images[0].width, processed.images[0].height, prompt_matrix_parts, margin_size) processed.images.insert(0, grid) processed.index_of_first_image = 1 diff --git a/scripts/prompts_from_file.py b/scripts/prompts_from_file.py index f168389c..b918a764 100644 --- a/scripts/prompts_from_file.py +++ b/scripts/prompts_from_file.py @@ -1,6 +1,4 @@ import copy -import math -import os import random import sys import traceback @@ -11,8 +9,7 @@ import gradio as gr from modules import sd_samplers from modules.processing import Processed, process_images -from PIL import Image -from modules.shared import opts, cmd_opts, state +from modules.shared import state def process_string_tag(tag): @@ -158,7 +155,7 @@ class Script(scripts.Script): images = [] all_prompts = [] infotexts = [] - for n, args in enumerate(jobs): + for args in jobs: state.job = f"{state.job_no + 1} out of {state.job_count}" copy_p = copy.copy(p) @@ -167,7 +164,7 @@ class Script(scripts.Script): proc = process_images(copy_p) images += proc.images - + if checkbox_iterate: p.seed = p.seed + (p.batch_size * p.n_iter) all_prompts += proc.all_prompts diff --git a/scripts/sd_upscale.py b/scripts/sd_upscale.py index 332d76d9..e614c23b 100644 --- a/scripts/sd_upscale.py +++ b/scripts/sd_upscale.py @@ -4,9 +4,9 @@ import modules.scripts as scripts import gradio as gr from PIL import Image -from modules import processing, shared, sd_samplers, images, devices +from modules import processing, shared, images, devices from modules.processing import Processed -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state class Script(scripts.Script): @@ -16,7 +16,7 @@ class Script(scripts.Script): def show(self, is_img2img): return is_img2img - def ui(self, is_img2img): + def ui(self, is_img2img): info = gr.HTML("

Will upscale the image by the selected scale factor; use width and height sliders to set tile size

") overlap = gr.Slider(minimum=0, maximum=256, step=16, label='Tile overlap', value=64, elem_id=self.elem_id("overlap")) scale_factor = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label='Scale Factor', value=2.0, elem_id=self.elem_id("scale_factor")) @@ -56,7 +56,7 @@ class Script(scripts.Script): work = [] - for y, h, row in grid.tiles: + for _y, _h, row in grid.tiles: for tiledata in row: work.append(tiledata[2]) @@ -85,7 +85,7 @@ class Script(scripts.Script): work_results += processed.images image_index = 0 - for y, h, row in grid.tiles: + for _y, _h, row in grid.tiles: for tiledata in row: tiledata[2] = work_results[image_index] if image_index < len(work_results) else Image.new("RGB", (p.width, p.height)) image_index += 1 diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py index a725d74a..5672267d 100644 --- a/scripts/xyz_grid.py +++ b/scripts/xyz_grid.py @@ -10,15 +10,13 @@ import numpy as np import modules.scripts as scripts import gradio as gr -from modules import images, paths, sd_samplers, processing, sd_models, sd_vae +from modules import images, sd_samplers, processing, sd_models, sd_vae from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img -from modules.shared import opts, cmd_opts, state +from modules.shared import opts, state import modules.shared as shared import modules.sd_samplers import modules.sd_models import modules.sd_vae -import glob -import os import re from modules.ui_components import ToolButton @@ -86,7 +84,7 @@ def apply_checkpoint(p, x, xs): info = modules.sd_models.get_closet_checkpoint_match(x) if info is None: raise RuntimeError(f"Unknown checkpoint: {x}") - p.override_settings['sd_model_checkpoint'] = info.hash + p.override_settings['sd_model_checkpoint'] = info.name def confirm_checkpoints(p, xs): @@ -316,7 +314,7 @@ def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend return Processed(p, []) z_count = len(zs) - sub_grids = [None] * z_count + for i in range(z_count): start_index = (i * len(xs) * len(ys)) + i end_index = start_index + len(xs) * len(ys) @@ -706,7 +704,7 @@ class Script(scripts.Script): if not include_sub_grids: # Done with sub-grids, drop all related information: - for sg in range(z_count): + for _ in range(z_count): del processed.images[1] del processed.all_prompts[1] del processed.all_seeds[1] diff --git a/style.css b/style.css index b823c7dd..f8ffbd8d 100644 --- a/style.css +++ b/style.css @@ -1,3 +1,6 @@ +/* temporary fix to load default gradio font in frontend instead of backend */ + +@import url('https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600&display=swap'); /* general gradio fixes */ @@ -360,12 +363,10 @@ div#extras_scale_to_tab div.form{ /* settings */ #quicksettings { - width: fit-content; align-items: end; } #quicksettings > div, #quicksettings > fieldset{ - max-width: 24em; min-width: 24em; padding: 0; border: none; @@ -414,6 +415,30 @@ table.settings-value-table td{ max-width: 36em; } +.ui-defaults-none{ + color: #aaa !important; +} + +#settings span{ + color: var(--body-text-color); +} + +#settings .gradio-textbox, #settings .gradio-slider, #settings .gradio-number, #settings .gradio-dropdown, #settings .gradio-checkboxgroup, #settings .gradio-radio{ + margin-top: 0.75em; +} + +#settings span .settings-comment { + display: inline +} + +.settings-comment a{ + text-decoration: underline; +} + +.settings-comment .info{ + opacity: 0.75; +} + /* live preview */ .progressDiv{ position: relative; diff --git a/test/basic_features/utils_test.py b/test/basic_features/utils_test.py index 0bfc28a0..d9e46b5e 100644 --- a/test/basic_features/utils_test.py +++ b/test/basic_features/utils_test.py @@ -1,62 +1,64 @@ import unittest import requests + class UtilsTests(unittest.TestCase): - def setUp(self): - self.url_options = "http://localhost:7860/sdapi/v1/options" - self.url_cmd_flags = "http://localhost:7860/sdapi/v1/cmd-flags" - self.url_samplers = "http://localhost:7860/sdapi/v1/samplers" - self.url_upscalers = "http://localhost:7860/sdapi/v1/upscalers" - self.url_sd_models = "http://localhost:7860/sdapi/v1/sd-models" - self.url_hypernetworks = "http://localhost:7860/sdapi/v1/hypernetworks" - self.url_face_restorers = "http://localhost:7860/sdapi/v1/face-restorers" - self.url_realesrgan_models = "http://localhost:7860/sdapi/v1/realesrgan-models" - self.url_prompt_styles = "http://localhost:7860/sdapi/v1/prompt-styles" - self.url_embeddings = "http://localhost:7860/sdapi/v1/embeddings" + def setUp(self): + self.url_options = "http://localhost:7860/sdapi/v1/options" + self.url_cmd_flags = "http://localhost:7860/sdapi/v1/cmd-flags" + self.url_samplers = "http://localhost:7860/sdapi/v1/samplers" + self.url_upscalers = "http://localhost:7860/sdapi/v1/upscalers" + self.url_sd_models = "http://localhost:7860/sdapi/v1/sd-models" + self.url_hypernetworks = "http://localhost:7860/sdapi/v1/hypernetworks" + self.url_face_restorers = "http://localhost:7860/sdapi/v1/face-restorers" + self.url_realesrgan_models = "http://localhost:7860/sdapi/v1/realesrgan-models" + self.url_prompt_styles = "http://localhost:7860/sdapi/v1/prompt-styles" + self.url_embeddings = "http://localhost:7860/sdapi/v1/embeddings" - def test_options_get(self): - self.assertEqual(requests.get(self.url_options).status_code, 200) + def test_options_get(self): + self.assertEqual(requests.get(self.url_options).status_code, 200) - def test_options_write(self): - response = requests.get(self.url_options) - self.assertEqual(response.status_code, 200) + def test_options_write(self): + response = requests.get(self.url_options) + self.assertEqual(response.status_code, 200) - pre_value = response.json()["send_seed"] + pre_value = response.json()["send_seed"] - self.assertEqual(requests.post(self.url_options, json={"send_seed":not pre_value}).status_code, 200) + self.assertEqual(requests.post(self.url_options, json={"send_seed": not pre_value}).status_code, 200) - response = requests.get(self.url_options) - self.assertEqual(response.status_code, 200) - self.assertEqual(response.json()["send_seed"], not pre_value) + response = requests.get(self.url_options) + self.assertEqual(response.status_code, 200) + self.assertEqual(response.json()["send_seed"], not pre_value) - requests.post(self.url_options, json={"send_seed": pre_value}) + requests.post(self.url_options, json={"send_seed": pre_value}) - def test_cmd_flags(self): - self.assertEqual(requests.get(self.url_cmd_flags).status_code, 200) + def test_cmd_flags(self): + self.assertEqual(requests.get(self.url_cmd_flags).status_code, 200) - def test_samplers(self): - self.assertEqual(requests.get(self.url_samplers).status_code, 200) + def test_samplers(self): + self.assertEqual(requests.get(self.url_samplers).status_code, 200) - def test_upscalers(self): - self.assertEqual(requests.get(self.url_upscalers).status_code, 200) + def test_upscalers(self): + self.assertEqual(requests.get(self.url_upscalers).status_code, 200) - def test_sd_models(self): - self.assertEqual(requests.get(self.url_sd_models).status_code, 200) + def test_sd_models(self): + self.assertEqual(requests.get(self.url_sd_models).status_code, 200) - def test_hypernetworks(self): - self.assertEqual(requests.get(self.url_hypernetworks).status_code, 200) + def test_hypernetworks(self): + self.assertEqual(requests.get(self.url_hypernetworks).status_code, 200) - def test_face_restorers(self): - self.assertEqual(requests.get(self.url_face_restorers).status_code, 200) - - def test_realesrgan_models(self): - self.assertEqual(requests.get(self.url_realesrgan_models).status_code, 200) - - def test_prompt_styles(self): - self.assertEqual(requests.get(self.url_prompt_styles).status_code, 200) + def test_face_restorers(self): + self.assertEqual(requests.get(self.url_face_restorers).status_code, 200) + + def test_realesrgan_models(self): + self.assertEqual(requests.get(self.url_realesrgan_models).status_code, 200) + + def test_prompt_styles(self): + self.assertEqual(requests.get(self.url_prompt_styles).status_code, 200) + + def test_embeddings(self): + self.assertEqual(requests.get(self.url_embeddings).status_code, 200) - def test_embeddings(self): - self.assertEqual(requests.get(self.url_embeddings).status_code, 200) if __name__ == "__main__": unittest.main() diff --git a/webui-macos-env.sh b/webui-macos-env.sh index 10ab81c9..6354e73b 100644 --- a/webui-macos-env.sh +++ b/webui-macos-env.sh @@ -11,7 +11,7 @@ fi export install_dir="$HOME" export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate" -export TORCH_COMMAND="pip install torch torchvision" +export TORCH_COMMAND="pip install torch==2.0.1 torchvision==0.15.2" export K_DIFFUSION_REPO="https://github.com/brkirch/k-diffusion.git" export K_DIFFUSION_COMMIT_HASH="51c9778f269cedb55a4d88c79c0246d35bdadb71" export PYTORCH_ENABLE_MPS_FALLBACK=1 diff --git a/webui.py b/webui.py index 727ebd31..293a16cc 100644 --- a/webui.py +++ b/webui.py @@ -16,12 +16,12 @@ from packaging import version import logging logging.getLogger("xformers").addFilter(lambda record: 'A matching Triton is not available' not in record.getMessage()) -from modules import paths, timer, import_hook, errors +from modules import paths, timer, import_hook, errors # noqa: F401 startup_timer = timer.Timer() import torch -import pytorch_lightning # pytorch_lightning should be imported after torch, but it re-enables warnings on import so import once to disable them +import pytorch_lightning # noqa: F401 # pytorch_lightning should be imported after torch, but it re-enables warnings on import so import once to disable them warnings.filterwarnings(action="ignore", category=DeprecationWarning, module="pytorch_lightning") warnings.filterwarnings(action="ignore", category=UserWarning, module="torchvision") @@ -31,19 +31,19 @@ startup_timer.record("import torch") import gradio startup_timer.record("import gradio") -import ldm.modules.encoders.modules +import ldm.modules.encoders.modules # noqa: F401 startup_timer.record("import ldm") from modules import extra_networks, ui_extra_networks_checkpoints from modules import extra_networks_hypernet, ui_extra_networks_hypernets, ui_extra_networks_textual_inversion -from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call +from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, queue_lock # noqa: F401 # Truncate version number of nightly/local build of PyTorch to not cause exceptions with CodeFormer or Safetensors if ".dev" in torch.__version__ or "+git" in torch.__version__: torch.__long_version__ = torch.__version__ torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0) -from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks, config_states +from modules import shared, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks, config_states import modules.codeformer_model as codeformer import modules.face_restoration import modules.gfpgan_model as gfpgan @@ -181,14 +181,11 @@ def initialize(): gfpgan.setup_model(cmd_opts.gfpgan_models_path) startup_timer.record("setup gfpgan") - modelloader.list_builtin_upscalers() - startup_timer.record("list builtin upscalers") - modules.scripts.load_scripts() startup_timer.record("load scripts") modelloader.load_upscalers() - #startup_timer.record("load upscalers") #Is this necessary? I don't know. + startup_timer.record("load upscalers") modules.sd_vae.refresh_vae_list() startup_timer.record("refresh VAE") @@ -360,7 +357,7 @@ def webui(): if cmd_opts.subpath: redirector = FastAPI() redirector.get("/") - mounted_app = gradio.mount_gradio_app(redirector, shared.demo, path=f"/{cmd_opts.subpath}") + gradio.mount_gradio_app(redirector, shared.demo, path=f"/{cmd_opts.subpath}") wait_on_server(shared.demo) print('Restarting UI...') @@ -388,7 +385,6 @@ def webui(): localization.list_localizations(cmd_opts.localizations_dir) - modelloader.forbid_loaded_nonbuiltin_upscalers() modules.scripts.reload_scripts() startup_timer.record("load scripts")
PathOld valueNew value
{path}{old_value}{new_value}
No changes