Merge branch 'master' into feature/scale_to
This commit is contained in:
AUTOMATIC1111
GitHub
commit
dc1432e0dd
2
.github/ISSUE_TEMPLATE/feature_request.md
vendored
2
.github/ISSUE_TEMPLATE/feature_request.md
vendored
@ -2,7 +2,7 @@
|
||||
name: Feature request
|
||||
about: Suggest an idea for this project
|
||||
title: ''
|
||||
labels: ''
|
||||
labels: 'suggestion'
|
||||
assignees: ''
|
||||
|
||||
---
|
||||
|
||||
28
.github/PULL_REQUEST_TEMPLATE/pull_request_template.md
vendored
Normal file
28
.github/PULL_REQUEST_TEMPLATE/pull_request_template.md
vendored
Normal file
@ -0,0 +1,28 @@
|
||||
# Please read the [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) before submitting a pull request!
|
||||
|
||||
If you have a large change, pay special attention to this paragraph:
|
||||
|
||||
> Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.
|
||||
|
||||
Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.
|
||||
|
||||
**Describe what this pull request is trying to achieve.**
|
||||
|
||||
A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.
|
||||
|
||||
**Additional notes and description of your changes**
|
||||
|
||||
More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.
|
||||
|
||||
**Environment this was tested in**
|
||||
|
||||
List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.
|
||||
- OS: [e.g. Windows, Linux]
|
||||
- Browser [e.g. chrome, safari]
|
||||
- Graphics card [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]
|
||||
|
||||
**Screenshots or videos of your changes**
|
||||
|
||||
If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.
|
||||
|
||||
This is **required** for anything that touches the user interface.
|
||||
1
CODEOWNERS
Normal file
1
CODEOWNERS
Normal file
@ -0,0 +1 @@
|
||||
* @AUTOMATIC1111
|
||||
11
README.md
11
README.md
@ -28,10 +28,12 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
|
||||
- CodeFormer, face restoration tool as an alternative to GFPGAN
|
||||
- RealESRGAN, neural network upscaler
|
||||
- ESRGAN, neural network upscaler with a lot of third party models
|
||||
- SwinIR, neural network upscaler
|
||||
- SwinIR and Swin2SR([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
|
||||
- LDSR, Latent diffusion super resolution upscaling
|
||||
- Resizing aspect ratio options
|
||||
- Sampling method selection
|
||||
- Adjust sampler eta values (noise multiplier)
|
||||
- More advanced noise setting options
|
||||
- Interrupt processing at any time
|
||||
- 4GB video card support (also reports of 2GB working)
|
||||
- Correct seeds for batches
|
||||
@ -67,6 +69,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
|
||||
- also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
|
||||
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
|
||||
- DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args)
|
||||
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
|
||||
|
||||
## Installation and Running
|
||||
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
|
||||
@ -116,13 +119,17 @@ The documentation was moved from this README over to the project's [wiki](https:
|
||||
- CodeFormer - https://github.com/sczhou/CodeFormer
|
||||
- ESRGAN - https://github.com/xinntao/ESRGAN
|
||||
- SwinIR - https://github.com/JingyunLiang/SwinIR
|
||||
- Swin2SR - https://github.com/mv-lab/swin2sr
|
||||
- LDSR - https://github.com/Hafiidz/latent-diffusion
|
||||
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
|
||||
- Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
|
||||
- InvokeAI, lstein - Cross Attention layer optimization - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
|
||||
- Rinon Gal - Textual Inversion - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
|
||||
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
|
||||
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
|
||||
- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
|
||||
- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
|
||||
- xformers - https://github.com/facebookresearch/xformers
|
||||
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
|
||||
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
|
||||
- DeepDanbooru - interrogator for anime diffusors https://github.com/KichangKim/DeepDanbooru
|
||||
- (You)
|
||||
|
||||
@ -3,9 +3,9 @@ channels:
|
||||
- pytorch
|
||||
- defaults
|
||||
dependencies:
|
||||
- python=3.8.5
|
||||
- pip=20.3
|
||||
- python=3.10
|
||||
- pip=22.2.2
|
||||
- cudatoolkit=11.3
|
||||
- pytorch=1.11.0
|
||||
- torchvision=0.12.0
|
||||
- numpy=1.19.2
|
||||
- pytorch=1.12.1
|
||||
- torchvision=0.13.1
|
||||
- numpy=1.23.1
|
||||
@ -16,7 +16,7 @@ contextMenuInit = function(){
|
||||
oldMenu.remove()
|
||||
}
|
||||
|
||||
let tabButton = gradioApp().querySelector('button')
|
||||
let tabButton = uiCurrentTab
|
||||
let baseStyle = window.getComputedStyle(tabButton)
|
||||
|
||||
const contextMenu = document.createElement('nav')
|
||||
@ -123,48 +123,53 @@ contextMenuInit = function(){
|
||||
return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
|
||||
}
|
||||
|
||||
initResponse = contextMenuInit()
|
||||
appendContextMenuOption = initResponse[0]
|
||||
removeContextMenuOption = initResponse[1]
|
||||
addContextMenuEventListener = initResponse[2]
|
||||
initResponse = contextMenuInit();
|
||||
appendContextMenuOption = initResponse[0];
|
||||
removeContextMenuOption = initResponse[1];
|
||||
addContextMenuEventListener = initResponse[2];
|
||||
|
||||
|
||||
//Start example Context Menu Items
|
||||
generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forever',function(){
|
||||
let genbutton = gradioApp().querySelector('#txt2img_generate');
|
||||
let interruptbutton = gradioApp().querySelector('#txt2img_interrupt');
|
||||
if(!interruptbutton.offsetParent){
|
||||
genbutton.click();
|
||||
}
|
||||
clearInterval(window.generateOnRepeatInterval)
|
||||
window.generateOnRepeatInterval = setInterval(function(){
|
||||
(function(){
|
||||
//Start example Context Menu Items
|
||||
let generateOnRepeat = function(genbuttonid,interruptbuttonid){
|
||||
let genbutton = gradioApp().querySelector(genbuttonid);
|
||||
let interruptbutton = gradioApp().querySelector(interruptbuttonid);
|
||||
if(!interruptbutton.offsetParent){
|
||||
genbutton.click();
|
||||
}
|
||||
},
|
||||
500)}
|
||||
)
|
||||
|
||||
cancelGenerateForever = function(){
|
||||
clearInterval(window.generateOnRepeatInterval)
|
||||
let interruptbutton = gradioApp().querySelector('#txt2img_interrupt');
|
||||
if(interruptbutton.offsetParent){
|
||||
interruptbutton.click();
|
||||
clearInterval(window.generateOnRepeatInterval)
|
||||
window.generateOnRepeatInterval = setInterval(function(){
|
||||
if(!interruptbutton.offsetParent){
|
||||
genbutton.click();
|
||||
}
|
||||
},
|
||||
500)
|
||||
}
|
||||
}
|
||||
|
||||
appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
|
||||
appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever)
|
||||
appendContextMenuOption('#txt2img_generate','Generate forever',function(){
|
||||
generateOnRepeat('#txt2img_generate','#txt2img_interrupt');
|
||||
})
|
||||
appendContextMenuOption('#img2img_generate','Generate forever',function(){
|
||||
generateOnRepeat('#img2img_generate','#img2img_interrupt');
|
||||
})
|
||||
|
||||
|
||||
appendContextMenuOption('#roll','Roll three',
|
||||
function(){
|
||||
let rollbutton = gradioApp().querySelector('#roll');
|
||||
setTimeout(function(){rollbutton.click()},100)
|
||||
setTimeout(function(){rollbutton.click()},200)
|
||||
setTimeout(function(){rollbutton.click()},300)
|
||||
let cancelGenerateForever = function(){
|
||||
clearInterval(window.generateOnRepeatInterval)
|
||||
}
|
||||
)
|
||||
|
||||
appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
|
||||
appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever)
|
||||
appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever)
|
||||
appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever)
|
||||
|
||||
appendContextMenuOption('#roll','Roll three',
|
||||
function(){
|
||||
let rollbutton = get_uiCurrentTabContent().querySelector('#roll');
|
||||
setTimeout(function(){rollbutton.click()},100)
|
||||
setTimeout(function(){rollbutton.click()},200)
|
||||
setTimeout(function(){rollbutton.click()},300)
|
||||
}
|
||||
)
|
||||
})();
|
||||
//End example Context Menu Items
|
||||
|
||||
onUiUpdate(function(){
|
||||
|
||||
@ -25,6 +25,7 @@ addEventListener('keydown', (event) => {
|
||||
} else {
|
||||
end = target.value.slice(selectionEnd + 1).indexOf(")") + 1;
|
||||
weight = parseFloat(target.value.slice(selectionEnd + 1, selectionEnd + 1 + end));
|
||||
if (isNaN(weight)) return;
|
||||
if (event.key == minus) weight -= 0.1;
|
||||
if (event.key == plus) weight += 0.1;
|
||||
|
||||
@ -38,4 +39,7 @@ addEventListener('keydown', (event) => {
|
||||
target.selectionStart = selectionStart;
|
||||
target.selectionEnd = selectionEnd;
|
||||
}
|
||||
// Since we've modified a Gradio Textbox component manually, we need to simulate an `input` DOM event to ensure its
|
||||
// internal Svelte data binding remains in sync.
|
||||
target.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
});
|
||||
|
||||
@ -79,6 +79,8 @@ titles = {
|
||||
"Highres. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition",
|
||||
"Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.",
|
||||
|
||||
"Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.",
|
||||
"Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -104,6 +104,7 @@ def prepare_enviroment():
|
||||
args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
|
||||
xformers = '--xformers' in args
|
||||
deepdanbooru = '--deepdanbooru' in args
|
||||
ngrok = '--ngrok' in args
|
||||
|
||||
try:
|
||||
commit = run(f"{git} rev-parse HEAD").strip()
|
||||
@ -127,13 +128,16 @@ def prepare_enviroment():
|
||||
|
||||
if not is_installed("xformers") and xformers and platform.python_version().startswith("3.10"):
|
||||
if platform.system() == "Windows":
|
||||
run_pip("install https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/a/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers")
|
||||
run_pip("install https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/c/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers")
|
||||
elif platform.system() == "Linux":
|
||||
run_pip("install xformers", "xformers")
|
||||
|
||||
if not is_installed("deepdanbooru") and deepdanbooru:
|
||||
run_pip("install git+https://github.com/KichangKim/DeepDanbooru.git@edf73df4cdaeea2cf00e9ac08bd8a9026b7a7b26#egg=deepdanbooru[tensorflow] tensorflow==2.10.0 tensorflow-io==0.27.0", "deepdanbooru")
|
||||
|
||||
if not is_installed("pyngrok") and ngrok:
|
||||
run_pip("install pyngrok", "ngrok")
|
||||
|
||||
os.makedirs(dir_repos, exist_ok=True)
|
||||
|
||||
git_clone("https://github.com/CompVis/stable-diffusion.git", repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash)
|
||||
|
||||
@ -1,21 +1,75 @@
|
||||
import os.path
|
||||
from concurrent.futures import ProcessPoolExecutor
|
||||
from multiprocessing import get_context
|
||||
import multiprocessing
|
||||
import time
|
||||
|
||||
def get_deepbooru_tags(pil_image):
|
||||
"""
|
||||
This method is for running only one image at a time for simple use. Used to the img2img interrogate.
|
||||
"""
|
||||
from modules import shared # prevents circular reference
|
||||
create_deepbooru_process(shared.opts.interrogate_deepbooru_score_threshold, shared.opts.deepbooru_sort_alpha)
|
||||
shared.deepbooru_process_return["value"] = -1
|
||||
shared.deepbooru_process_queue.put(pil_image)
|
||||
while shared.deepbooru_process_return["value"] == -1:
|
||||
time.sleep(0.2)
|
||||
tags = shared.deepbooru_process_return["value"]
|
||||
release_process()
|
||||
return tags
|
||||
|
||||
|
||||
def _load_tf_and_return_tags(pil_image, threshold):
|
||||
def deepbooru_process(queue, deepbooru_process_return, threshold, alpha_sort):
|
||||
model, tags = get_deepbooru_tags_model()
|
||||
while True: # while process is running, keep monitoring queue for new image
|
||||
pil_image = queue.get()
|
||||
if pil_image == "QUIT":
|
||||
break
|
||||
else:
|
||||
deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort)
|
||||
|
||||
|
||||
def create_deepbooru_process(threshold, alpha_sort):
|
||||
"""
|
||||
Creates deepbooru process. A queue is created to send images into the process. This enables multiple images
|
||||
to be processed in a row without reloading the model or creating a new process. To return the data, a shared
|
||||
dictionary is created to hold the tags created. To wait for tags to be returned, a value of -1 is assigned
|
||||
to the dictionary and the method adding the image to the queue should wait for this value to be updated with
|
||||
the tags.
|
||||
"""
|
||||
from modules import shared # prevents circular reference
|
||||
shared.deepbooru_process_manager = multiprocessing.Manager()
|
||||
shared.deepbooru_process_queue = shared.deepbooru_process_manager.Queue()
|
||||
shared.deepbooru_process_return = shared.deepbooru_process_manager.dict()
|
||||
shared.deepbooru_process_return["value"] = -1
|
||||
shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, alpha_sort))
|
||||
shared.deepbooru_process.start()
|
||||
|
||||
|
||||
def release_process():
|
||||
"""
|
||||
Stops the deepbooru process to return used memory
|
||||
"""
|
||||
from modules import shared # prevents circular reference
|
||||
shared.deepbooru_process_queue.put("QUIT")
|
||||
shared.deepbooru_process.join()
|
||||
shared.deepbooru_process_queue = None
|
||||
shared.deepbooru_process = None
|
||||
shared.deepbooru_process_return = None
|
||||
shared.deepbooru_process_manager = None
|
||||
|
||||
def get_deepbooru_tags_model():
|
||||
import deepdanbooru as dd
|
||||
import tensorflow as tf
|
||||
import numpy as np
|
||||
|
||||
this_folder = os.path.dirname(__file__)
|
||||
model_path = os.path.abspath(os.path.join(this_folder, '..', 'models', 'deepbooru'))
|
||||
if not os.path.exists(os.path.join(model_path, 'project.json')):
|
||||
# there is no point importing these every time
|
||||
import zipfile
|
||||
from basicsr.utils.download_util import load_file_from_url
|
||||
load_file_from_url(r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip",
|
||||
model_path)
|
||||
load_file_from_url(
|
||||
r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip",
|
||||
model_path)
|
||||
with zipfile.ZipFile(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"), "r") as zip_ref:
|
||||
zip_ref.extractall(model_path)
|
||||
os.remove(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"))
|
||||
@ -24,7 +78,13 @@ def _load_tf_and_return_tags(pil_image, threshold):
|
||||
model = dd.project.load_model_from_project(
|
||||
model_path, compile_model=True
|
||||
)
|
||||
return model, tags
|
||||
|
||||
|
||||
def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort):
|
||||
import deepdanbooru as dd
|
||||
import tensorflow as tf
|
||||
import numpy as np
|
||||
width = model.input_shape[2]
|
||||
height = model.input_shape[1]
|
||||
image = np.array(pil_image)
|
||||
@ -46,28 +106,27 @@ def _load_tf_and_return_tags(pil_image, threshold):
|
||||
|
||||
for i, tag in enumerate(tags):
|
||||
result_dict[tag] = y[i]
|
||||
result_tags_out = []
|
||||
|
||||
unsorted_tags_in_theshold = []
|
||||
result_tags_print = []
|
||||
for tag in tags:
|
||||
if result_dict[tag] >= threshold:
|
||||
if tag.startswith("rating:"):
|
||||
continue
|
||||
result_tags_out.append(tag)
|
||||
unsorted_tags_in_theshold.append((result_dict[tag], tag))
|
||||
result_tags_print.append(f'{result_dict[tag]} {tag}')
|
||||
|
||||
# sort tags
|
||||
result_tags_out = []
|
||||
sort_ndx = 0
|
||||
if alpha_sort:
|
||||
sort_ndx = 1
|
||||
|
||||
# sort by reverse by likelihood and normal for alpha
|
||||
unsorted_tags_in_theshold.sort(key=lambda y: y[sort_ndx], reverse=(not alpha_sort))
|
||||
for weight, tag in unsorted_tags_in_theshold:
|
||||
result_tags_out.append(tag)
|
||||
|
||||
print('\n'.join(sorted(result_tags_print, reverse=True)))
|
||||
|
||||
return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ')
|
||||
|
||||
|
||||
def subprocess_init_no_cuda():
|
||||
import os
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
|
||||
|
||||
|
||||
def get_deepbooru_tags(pil_image, threshold=0.5):
|
||||
context = get_context('spawn')
|
||||
with ProcessPoolExecutor(initializer=subprocess_init_no_cuda, mp_context=context) as executor:
|
||||
f = executor.submit(_load_tf_and_return_tags, pil_image, threshold, )
|
||||
ret = f.result() # will rethrow any exceptions
|
||||
return ret
|
||||
@ -36,6 +36,7 @@ errors.run(enable_tf32, "Enabling TF32")
|
||||
|
||||
device = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = get_optimal_device()
|
||||
dtype = torch.float16
|
||||
dtype_vae = torch.float16
|
||||
|
||||
def randn(seed, shape):
|
||||
# Pytorch currently doesn't handle setting randomness correctly when the metal backend is used.
|
||||
@ -59,9 +60,12 @@ def randn_without_seed(shape):
|
||||
return torch.randn(shape, device=device)
|
||||
|
||||
|
||||
def autocast():
|
||||
def autocast(disable=False):
|
||||
from modules import shared
|
||||
|
||||
if disable:
|
||||
return contextlib.nullcontext()
|
||||
|
||||
if dtype == torch.float32 or shared.cmd_opts.precision == "full":
|
||||
return contextlib.nullcontext()
|
||||
|
||||
|
||||
@ -1,98 +0,0 @@
|
||||
import glob
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import torch
|
||||
|
||||
from ldm.util import default
|
||||
from modules import devices, shared
|
||||
import torch
|
||||
from torch import einsum
|
||||
from einops import rearrange, repeat
|
||||
|
||||
|
||||
class HypernetworkModule(torch.nn.Module):
|
||||
def __init__(self, dim, state_dict):
|
||||
super().__init__()
|
||||
|
||||
self.linear1 = torch.nn.Linear(dim, dim * 2)
|
||||
self.linear2 = torch.nn.Linear(dim * 2, dim)
|
||||
|
||||
self.load_state_dict(state_dict, strict=True)
|
||||
self.to(devices.device)
|
||||
|
||||
def forward(self, x):
|
||||
return x + (self.linear2(self.linear1(x)))
|
||||
|
||||
|
||||
class Hypernetwork:
|
||||
filename = None
|
||||
name = None
|
||||
|
||||
def __init__(self, filename):
|
||||
self.filename = filename
|
||||
self.name = os.path.splitext(os.path.basename(filename))[0]
|
||||
self.layers = {}
|
||||
|
||||
state_dict = torch.load(filename, map_location='cpu')
|
||||
for size, sd in state_dict.items():
|
||||
self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
|
||||
|
||||
|
||||
def list_hypernetworks(path):
|
||||
res = {}
|
||||
for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
|
||||
name = os.path.splitext(os.path.basename(filename))[0]
|
||||
res[name] = filename
|
||||
return res
|
||||
|
||||
|
||||
def load_hypernetwork(filename):
|
||||
path = shared.hypernetworks.get(filename, None)
|
||||
if path is not None:
|
||||
print(f"Loading hypernetwork {filename}")
|
||||
try:
|
||||
shared.loaded_hypernetwork = Hypernetwork(path)
|
||||
except Exception:
|
||||
print(f"Error loading hypernetwork {path}", file=sys.stderr)
|
||||
print(traceback.format_exc(), file=sys.stderr)
|
||||
else:
|
||||
if shared.loaded_hypernetwork is not None:
|
||||
print(f"Unloading hypernetwork")
|
||||
|
||||
shared.loaded_hypernetwork = None
|
||||
|
||||
|
||||
def attention_CrossAttention_forward(self, x, context=None, mask=None):
|
||||
h = self.heads
|
||||
|
||||
q = self.to_q(x)
|
||||
context = default(context, x)
|
||||
|
||||
hypernetwork = shared.loaded_hypernetwork
|
||||
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
|
||||
|
||||
if hypernetwork_layers is not None:
|
||||
k = self.to_k(hypernetwork_layers[0](context))
|
||||
v = self.to_v(hypernetwork_layers[1](context))
|
||||
else:
|
||||
k = self.to_k(context)
|
||||
v = self.to_v(context)
|
||||
|
||||
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
|
||||
|
||||
sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
|
||||
|
||||
if mask is not None:
|
||||
mask = rearrange(mask, 'b ... -> b (...)')
|
||||
max_neg_value = -torch.finfo(sim.dtype).max
|
||||
mask = repeat(mask, 'b j -> (b h) () j', h=h)
|
||||
sim.masked_fill_(~mask, max_neg_value)
|
||||
|
||||
# attention, what we cannot get enough of
|
||||
attn = sim.softmax(dim=-1)
|
||||
|
||||
out = einsum('b i j, b j d -> b i d', attn, v)
|
||||
out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
|
||||
return self.to_out(out)
|
||||
305
modules/hypernetworks/hypernetwork.py
Normal file
305
modules/hypernetworks/hypernetwork.py
Normal file
@ -0,0 +1,305 @@
|
||||
import datetime
|
||||
import glob
|
||||
import html
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
import tqdm
|
||||
|
||||
import torch
|
||||
|
||||
from ldm.util import default
|
||||
from modules import devices, shared, processing, sd_models
|
||||
import torch
|
||||
from torch import einsum
|
||||
from einops import rearrange, repeat
|
||||
import modules.textual_inversion.dataset
|
||||
from modules.textual_inversion.learn_schedule import LearnSchedule
|
||||
|
||||
|
||||
class HypernetworkModule(torch.nn.Module):
|
||||
def __init__(self, dim, state_dict=None):
|
||||
super().__init__()
|
||||
|
||||
self.linear1 = torch.nn.Linear(dim, dim * 2)
|
||||
self.linear2 = torch.nn.Linear(dim * 2, dim)
|
||||
|
||||
if state_dict is not None:
|
||||
self.load_state_dict(state_dict, strict=True)
|
||||
else:
|
||||
|
||||
self.linear1.weight.data.normal_(mean=0.0, std=0.01)
|
||||
self.linear1.bias.data.zero_()
|
||||
self.linear2.weight.data.normal_(mean=0.0, std=0.01)
|
||||
self.linear2.bias.data.zero_()
|
||||
|
||||
self.to(devices.device)
|
||||
|
||||
def forward(self, x):
|
||||
return x + (self.linear2(self.linear1(x)))
|
||||
|
||||
|
||||
class Hypernetwork:
|
||||
filename = None
|
||||
name = None
|
||||
|
||||
def __init__(self, name=None, enable_sizes=None):
|
||||
self.filename = None
|
||||
self.name = name
|
||||
self.layers = {}
|
||||
self.step = 0
|
||||
self.sd_checkpoint = None
|
||||
self.sd_checkpoint_name = None
|
||||
|
||||
for size in enable_sizes or []:
|
||||
self.layers[size] = (HypernetworkModule(size), HypernetworkModule(size))
|
||||
|
||||
def weights(self):
|
||||
res = []
|
||||
|
||||
for k, layers in self.layers.items():
|
||||
for layer in layers:
|
||||
layer.train()
|
||||
res += [layer.linear1.weight, layer.linear1.bias, layer.linear2.weight, layer.linear2.bias]
|
||||
|
||||
return res
|
||||
|
||||
def save(self, filename):
|
||||
state_dict = {}
|
||||
|
||||
for k, v in self.layers.items():
|
||||
state_dict[k] = (v[0].state_dict(), v[1].state_dict())
|
||||
|
||||
state_dict['step'] = self.step
|
||||
state_dict['name'] = self.name
|
||||
state_dict['sd_checkpoint'] = self.sd_checkpoint
|
||||
state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name
|
||||
|
||||
torch.save(state_dict, filename)
|
||||
|
||||
def load(self, filename):
|
||||
self.filename = filename
|
||||
if self.name is None:
|
||||
self.name = os.path.splitext(os.path.basename(filename))[0]
|
||||
|
||||
state_dict = torch.load(filename, map_location='cpu')
|
||||
|
||||
for size, sd in state_dict.items():
|
||||
if type(size) == int:
|
||||
self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
|
||||
|
||||
self.name = state_dict.get('name', self.name)
|
||||
self.step = state_dict.get('step', 0)
|
||||
self.sd_checkpoint = state_dict.get('sd_checkpoint', None)
|
||||
self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None)
|
||||
|
||||
|
||||
def list_hypernetworks(path):
|
||||
res = {}
|
||||
for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
|
||||
name = os.path.splitext(os.path.basename(filename))[0]
|
||||
res[name] = filename
|
||||
return res
|
||||
|
||||
|
||||
def load_hypernetwork(filename):
|
||||
path = shared.hypernetworks.get(filename, None)
|
||||
if path is not None:
|
||||
print(f"Loading hypernetwork {filename}")
|
||||
try:
|
||||
shared.loaded_hypernetwork = Hypernetwork()
|
||||
shared.loaded_hypernetwork.load(path)
|
||||
|
||||
except Exception:
|
||||
print(f"Error loading hypernetwork {path}", file=sys.stderr)
|
||||
print(traceback.format_exc(), file=sys.stderr)
|
||||
else:
|
||||
if shared.loaded_hypernetwork is not None:
|
||||
print(f"Unloading hypernetwork")
|
||||
|
||||
shared.loaded_hypernetwork = None
|
||||
|
||||
|
||||
def apply_hypernetwork(hypernetwork, context, layer=None):
|
||||
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
|
||||
|
||||
if hypernetwork_layers is None:
|
||||
return context, context
|
||||
|
||||
if layer is not None:
|
||||
layer.hyper_k = hypernetwork_layers[0]
|
||||
layer.hyper_v = hypernetwork_layers[1]
|
||||
|
||||
context_k = hypernetwork_layers[0](context)
|
||||
context_v = hypernetwork_layers[1](context)
|
||||
return context_k, context_v
|
||||
|
||||
|
||||
def attention_CrossAttention_forward(self, x, context=None, mask=None):
|
||||
h = self.heads
|
||||
|
||||
q = self.to_q(x)
|
||||
context = default(context, x)
|
||||
|
||||
context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self)
|
||||
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))
|
||||
|
||||
sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
|
||||
|
||||
if mask is not None:
|
||||
mask = rearrange(mask, 'b ... -> b (...)')
|
||||
max_neg_value = -torch.finfo(sim.dtype).max
|
||||
mask = repeat(mask, 'b j -> (b h) () j', h=h)
|
||||
sim.masked_fill_(~mask, max_neg_value)
|
||||
|
||||
# attention, what we cannot get enough of
|
||||
attn = sim.softmax(dim=-1)
|
||||
|
||||
out = einsum('b i j, b j d -> b i d', attn, v)
|
||||
out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
|
||||
return self.to_out(out)
|
||||
|
||||
|
||||
def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt):
|
||||
assert hypernetwork_name, 'embedding not selected'
|
||||
|
||||
path = shared.hypernetworks.get(hypernetwork_name, None)
|
||||
shared.loaded_hypernetwork = Hypernetwork()
|
||||
shared.loaded_hypernetwork.load(path)
|
||||
|
||||
shared.state.textinfo = "Initializing hypernetwork training..."
|
||||
shared.state.job_count = steps
|
||||
|
||||
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')
|
||||
|
||||
log_directory = os.path.join(log_directory, datetime.datetime.now().strftime("%Y-%m-%d"), hypernetwork_name)
|
||||
unload = shared.opts.unload_models_when_training
|
||||
|
||||
if save_hypernetwork_every > 0:
|
||||
hypernetwork_dir = os.path.join(log_directory, "hypernetworks")
|
||||
os.makedirs(hypernetwork_dir, exist_ok=True)
|
||||
else:
|
||||
hypernetwork_dir = None
|
||||
|
||||
if create_image_every > 0:
|
||||
images_dir = os.path.join(log_directory, "images")
|
||||
os.makedirs(images_dir, exist_ok=True)
|
||||
else:
|
||||
images_dir = None
|
||||
|
||||
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
|
||||
with torch.autocast("cuda"):
|
||||
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=1, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file, include_cond=True)
|
||||
|
||||
if unload:
|
||||
shared.sd_model.cond_stage_model.to(devices.cpu)
|
||||
shared.sd_model.first_stage_model.to(devices.cpu)
|
||||
|
||||
hypernetwork = shared.loaded_hypernetwork
|
||||
weights = hypernetwork.weights()
|
||||
for weight in weights:
|
||||
weight.requires_grad = True
|
||||
|
||||
losses = torch.zeros((32,))
|
||||
|
||||
last_saved_file = "<none>"
|
||||
last_saved_image = "<none>"
|
||||
|
||||
ititial_step = hypernetwork.step or 0
|
||||
if ititial_step > steps:
|
||||
return hypernetwork, filename
|
||||
|
||||
schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
|
||||
(learn_rate, end_step) = next(schedules)
|
||||
print(f'Training at rate of {learn_rate} until step {end_step}')
|
||||
|
||||
optimizer = torch.optim.AdamW(weights, lr=learn_rate)
|
||||
|
||||
pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
|
||||
for i, (x, text, cond) in pbar:
|
||||
hypernetwork.step = i + ititial_step
|
||||
|
||||
if hypernetwork.step > end_step:
|
||||
try:
|
||||
(learn_rate, end_step) = next(schedules)
|
||||
except Exception:
|
||||
break
|
||||
tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
|
||||
for pg in optimizer.param_groups:
|
||||
pg['lr'] = learn_rate
|
||||
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
|
||||
with torch.autocast("cuda"):
|
||||
cond = cond.to(devices.device)
|
||||
x = x.to(devices.device)
|
||||
loss = shared.sd_model(x.unsqueeze(0), cond)[0]
|
||||
del x
|
||||
del cond
|
||||
|
||||
losses[hypernetwork.step % losses.shape[0]] = loss.item()
|
||||
|
||||
optimizer.zero_grad()
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
pbar.set_description(f"loss: {losses.mean():.7f}")
|
||||
|
||||
if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0:
|
||||
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt')
|
||||
hypernetwork.save(last_saved_file)
|
||||
|
||||
if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0:
|
||||
last_saved_image = os.path.join(images_dir, f'{hypernetwork_name}-{hypernetwork.step}.png')
|
||||
|
||||
preview_text = text if preview_image_prompt == "" else preview_image_prompt
|
||||
|
||||
optimizer.zero_grad()
|
||||
shared.sd_model.cond_stage_model.to(devices.device)
|
||||
shared.sd_model.first_stage_model.to(devices.device)
|
||||
|
||||
p = processing.StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
prompt=preview_text,
|
||||
steps=20,
|
||||
do_not_save_grid=True,
|
||||
do_not_save_samples=True,
|
||||
)
|
||||
|
||||
processed = processing.process_images(p)
|
||||
image = processed.images[0]
|
||||
|
||||
if unload:
|
||||
shared.sd_model.cond_stage_model.to(devices.cpu)
|
||||
shared.sd_model.first_stage_model.to(devices.cpu)
|
||||
|
||||
shared.state.current_image = image
|
||||
image.save(last_saved_image)
|
||||
|
||||
last_saved_image += f", prompt: {preview_text}"
|
||||
|
||||
shared.state.job_no = hypernetwork.step
|
||||
|
||||
shared.state.textinfo = f"""
|
||||
<p>
|
||||
Loss: {losses.mean():.7f}<br/>
|
||||
Step: {hypernetwork.step}<br/>
|
||||
Last prompt: {html.escape(text)}<br/>
|
||||
Last saved embedding: {html.escape(last_saved_file)}<br/>
|
||||
Last saved image: {html.escape(last_saved_image)}<br/>
|
||||
</p>
|
||||
"""
|
||||
|
||||
checkpoint = sd_models.select_checkpoint()
|
||||
|
||||
hypernetwork.sd_checkpoint = checkpoint.hash
|
||||
hypernetwork.sd_checkpoint_name = checkpoint.model_name
|
||||
hypernetwork.save(filename)
|
||||
|
||||
return hypernetwork, filename
|
||||
|
||||
|
||||
47
modules/hypernetworks/ui.py
Normal file
47
modules/hypernetworks/ui.py
Normal file
@ -0,0 +1,47 @@
|
||||
import html
|
||||
import os
|
||||
|
||||
import gradio as gr
|
||||
|
||||
import modules.textual_inversion.textual_inversion
|
||||
import modules.textual_inversion.preprocess
|
||||
from modules import sd_hijack, shared, devices
|
||||
from modules.hypernetworks import hypernetwork
|
||||
|
||||
|
||||
def create_hypernetwork(name, enable_sizes):
|
||||
fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt")
|
||||
assert not os.path.exists(fn), f"file {fn} already exists"
|
||||
|
||||
hypernet = modules.hypernetworks.hypernetwork.Hypernetwork(name=name, enable_sizes=[int(x) for x in enable_sizes])
|
||||
hypernet.save(fn)
|
||||
|
||||
shared.reload_hypernetworks()
|
||||
|
||||
return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", ""
|
||||
|
||||
|
||||
def train_hypernetwork(*args):
|
||||
|
||||
initial_hypernetwork = shared.loaded_hypernetwork
|
||||
|
||||
assert not shared.cmd_opts.lowvram, 'Training models with lowvram is not possible'
|
||||
|
||||
try:
|
||||
sd_hijack.undo_optimizations()
|
||||
|
||||
hypernetwork, filename = modules.hypernetworks.hypernetwork.train_hypernetwork(*args)
|
||||
|
||||
res = f"""
|
||||
Training {'interrupted' if shared.state.interrupted else 'finished'} at {hypernetwork.step} steps.
|
||||
Hypernetwork saved to {html.escape(filename)}
|
||||
"""
|
||||
return res, ""
|
||||
except Exception:
|
||||
raise
|
||||
finally:
|
||||
shared.loaded_hypernetwork = initial_hypernetwork
|
||||
shared.sd_model.cond_stage_model.to(devices.device)
|
||||
shared.sd_model.first_stage_model.to(devices.device)
|
||||
sd_hijack.apply_optimizations()
|
||||
|
||||
15
modules/ngrok.py
Normal file
15
modules/ngrok.py
Normal file
@ -0,0 +1,15 @@
|
||||
from pyngrok import ngrok, conf, exception
|
||||
|
||||
|
||||
def connect(token, port):
|
||||
if token == None:
|
||||
token = 'None'
|
||||
conf.get_default().auth_token = token
|
||||
try:
|
||||
public_url = ngrok.connect(port).public_url
|
||||
except exception.PyngrokNgrokError:
|
||||
print(f'Invalid ngrok authtoken, ngrok connection aborted.\n'
|
||||
f'Your token: {token}, get the right one on https://dashboard.ngrok.com/get-started/your-authtoken')
|
||||
else:
|
||||
print(f'ngrok connected to localhost:{port}! URL: {public_url}\n'
|
||||
'You can use this link after the launch is complete.')
|
||||
@ -207,7 +207,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
|
||||
# enables the generation of additional tensors with noise that the sampler will use during its processing.
|
||||
# Using those pre-generated tensors instead of simple torch.randn allows a batch with seeds [100, 101] to
|
||||
# produce the same images as with two batches [100], [101].
|
||||
if p is not None and p.sampler is not None and len(seeds) > 1 and opts.enable_batch_seeds:
|
||||
if p is not None and p.sampler is not None and (len(seeds) > 1 and opts.enable_batch_seeds or opts.eta_noise_seed_delta > 0):
|
||||
sampler_noises = [[] for _ in range(p.sampler.number_of_needed_noises(p))]
|
||||
else:
|
||||
sampler_noises = None
|
||||
@ -247,6 +247,9 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
|
||||
if sampler_noises is not None:
|
||||
cnt = p.sampler.number_of_needed_noises(p)
|
||||
|
||||
if opts.eta_noise_seed_delta > 0:
|
||||
torch.manual_seed(seed + opts.eta_noise_seed_delta)
|
||||
|
||||
for j in range(cnt):
|
||||
sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape)))
|
||||
|
||||
@ -259,6 +262,13 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
|
||||
return x
|
||||
|
||||
|
||||
def decode_first_stage(model, x):
|
||||
with devices.autocast(disable=x.dtype == devices.dtype_vae):
|
||||
x = model.decode_first_stage(x)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def get_fixed_seed(seed):
|
||||
if seed is None or seed == '' or seed == -1:
|
||||
return int(random.randrange(4294967294))
|
||||
@ -294,6 +304,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration
|
||||
"Denoising strength": getattr(p, 'denoising_strength', None),
|
||||
"Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta),
|
||||
"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,
|
||||
}
|
||||
|
||||
generation_params.update(p.extra_generation_params)
|
||||
@ -398,9 +409,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
|
||||
# use the image collected previously in sampler loop
|
||||
samples_ddim = shared.state.current_latent
|
||||
|
||||
samples_ddim = samples_ddim.to(devices.dtype)
|
||||
|
||||
x_samples_ddim = p.sd_model.decode_first_stage(samples_ddim)
|
||||
samples_ddim = samples_ddim.to(devices.dtype_vae)
|
||||
x_samples_ddim = decode_first_stage(p.sd_model, samples_ddim)
|
||||
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
|
||||
|
||||
del samples_ddim
|
||||
@ -533,7 +543,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
|
||||
if self.scale_latent:
|
||||
samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
|
||||
else:
|
||||
decoded_samples = self.sd_model.decode_first_stage(samples)
|
||||
decoded_samples = decode_first_stage(self.sd_model, samples)
|
||||
|
||||
if opts.upscaler_for_img2img is None or opts.upscaler_for_img2img == "None":
|
||||
decoded_samples = torch.nn.functional.interpolate(decoded_samples, size=(self.height, self.width), mode="bilinear")
|
||||
|
||||
@ -10,6 +10,11 @@ import torch
|
||||
import numpy
|
||||
import _codecs
|
||||
import zipfile
|
||||
import re
|
||||
|
||||
|
||||
# PyTorch 1.13 and later have _TypedStorage renamed to TypedStorage
|
||||
TypedStorage = torch.storage.TypedStorage if hasattr(torch.storage, 'TypedStorage') else torch.storage._TypedStorage
|
||||
|
||||
|
||||
def encode(*args):
|
||||
@ -20,7 +25,7 @@ def encode(*args):
|
||||
class RestrictedUnpickler(pickle.Unpickler):
|
||||
def persistent_load(self, saved_id):
|
||||
assert saved_id[0] == 'storage'
|
||||
return torch.storage._TypedStorage()
|
||||
return TypedStorage()
|
||||
|
||||
def find_class(self, module, name):
|
||||
if module == 'collections' and name == 'OrderedDict':
|
||||
@ -50,11 +55,27 @@ class RestrictedUnpickler(pickle.Unpickler):
|
||||
raise pickle.UnpicklingError(f"global '{module}/{name}' is forbidden")
|
||||
|
||||
|
||||
allowed_zip_names = ["archive/data.pkl", "archive/version"]
|
||||
allowed_zip_names_re = re.compile(r"^archive/data/\d+$")
|
||||
|
||||
|
||||
def check_zip_filenames(filename, names):
|
||||
for name in names:
|
||||
if name in allowed_zip_names:
|
||||
continue
|
||||
if allowed_zip_names_re.match(name):
|
||||
continue
|
||||
|
||||
raise Exception(f"bad file inside {filename}: {name}")
|
||||
|
||||
|
||||
def check_pt(filename):
|
||||
try:
|
||||
|
||||
# new pytorch format is a zip file
|
||||
with zipfile.ZipFile(filename) as z:
|
||||
check_zip_filenames(filename, z.namelist())
|
||||
|
||||
with z.open('archive/data.pkl') as file:
|
||||
unpickler = RestrictedUnpickler(file)
|
||||
unpickler.load()
|
||||
|
||||
@ -8,8 +8,9 @@ from torch import einsum
|
||||
from torch.nn.functional import silu
|
||||
|
||||
import modules.textual_inversion.textual_inversion
|
||||
from modules import prompt_parser, devices, sd_hijack_optimizations, shared, hypernetwork
|
||||
from modules import prompt_parser, devices, sd_hijack_optimizations, shared
|
||||
from modules.shared import opts, device, cmd_opts
|
||||
from modules.sd_hijack_optimizations import invokeAI_mps_available
|
||||
|
||||
import ldm.modules.attention
|
||||
import ldm.modules.diffusionmodules.model
|
||||
@ -23,30 +24,37 @@ def apply_optimizations():
|
||||
|
||||
ldm.modules.diffusionmodules.model.nonlinearity = silu
|
||||
|
||||
if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and torch.cuda.get_device_capability(shared.device) == (8, 6)):
|
||||
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) <= (8, 6)):
|
||||
print("Applying xformers cross attention optimization.")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
|
||||
elif cmd_opts.opt_split_attention_v1:
|
||||
print("Applying v1 cross attention optimization.")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
|
||||
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not torch.cuda.is_available()):
|
||||
if not invokeAI_mps_available and shared.device.type == 'mps':
|
||||
print("The InvokeAI cross attention optimization for MPS requires the psutil package which is not installed.")
|
||||
print("Applying v1 cross attention optimization.")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
|
||||
else:
|
||||
print("Applying cross attention optimization (InvokeAI).")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
|
||||
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
|
||||
print("Applying cross attention optimization.")
|
||||
print("Applying cross attention optimization (Doggettx).")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
|
||||
|
||||
|
||||
def undo_optimizations():
|
||||
from modules.hypernetworks import hypernetwork
|
||||
|
||||
ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
|
||||
ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
|
||||
|
||||
|
||||
def get_target_prompt_token_count(token_count):
|
||||
if token_count < 75:
|
||||
return 75
|
||||
|
||||
return math.ceil(token_count / 10) * 10
|
||||
return math.ceil(max(token_count, 1) / 75) * 75
|
||||
|
||||
|
||||
class StableDiffusionModelHijack:
|
||||
@ -110,6 +118,8 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
self.tokenizer = wrapped.tokenizer
|
||||
self.token_mults = {}
|
||||
|
||||
self.comma_token = [v for k, v in self.tokenizer.get_vocab().items() if k == ',</w>'][0]
|
||||
|
||||
tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k]
|
||||
for text, ident in tokens_with_parens:
|
||||
mult = 1.0
|
||||
@ -127,7 +137,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
self.token_mults[ident] = mult
|
||||
|
||||
def tokenize_line(self, line, used_custom_terms, hijack_comments):
|
||||
id_start = self.wrapped.tokenizer.bos_token_id
|
||||
id_end = self.wrapped.tokenizer.eos_token_id
|
||||
|
||||
if opts.enable_emphasis:
|
||||
@ -140,6 +149,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
fixes = []
|
||||
remade_tokens = []
|
||||
multipliers = []
|
||||
last_comma = -1
|
||||
|
||||
for tokens, (text, weight) in zip(tokenized, parsed):
|
||||
i = 0
|
||||
@ -148,13 +158,33 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
|
||||
embedding, embedding_length_in_tokens = self.hijack.embedding_db.find_embedding_at_position(tokens, i)
|
||||
|
||||
if token == self.comma_token:
|
||||
last_comma = len(remade_tokens)
|
||||
elif opts.comma_padding_backtrack != 0 and max(len(remade_tokens), 1) % 75 == 0 and last_comma != -1 and len(remade_tokens) - last_comma <= opts.comma_padding_backtrack:
|
||||
last_comma += 1
|
||||
reloc_tokens = remade_tokens[last_comma:]
|
||||
reloc_mults = multipliers[last_comma:]
|
||||
|
||||
remade_tokens = remade_tokens[:last_comma]
|
||||
length = len(remade_tokens)
|
||||
|
||||
rem = int(math.ceil(length / 75)) * 75 - length
|
||||
remade_tokens += [id_end] * rem + reloc_tokens
|
||||
multipliers = multipliers[:last_comma] + [1.0] * rem + reloc_mults
|
||||
|
||||
if embedding is None:
|
||||
remade_tokens.append(token)
|
||||
multipliers.append(weight)
|
||||
i += 1
|
||||
else:
|
||||
emb_len = int(embedding.vec.shape[0])
|
||||
fixes.append((len(remade_tokens), embedding))
|
||||
iteration = len(remade_tokens) // 75
|
||||
if (len(remade_tokens) + emb_len) // 75 != iteration:
|
||||
rem = (75 * (iteration + 1) - len(remade_tokens))
|
||||
remade_tokens += [id_end] * rem
|
||||
multipliers += [1.0] * rem
|
||||
iteration += 1
|
||||
fixes.append((iteration, (len(remade_tokens) % 75, embedding)))
|
||||
remade_tokens += [0] * emb_len
|
||||
multipliers += [weight] * emb_len
|
||||
used_custom_terms.append((embedding.name, embedding.checksum()))
|
||||
@ -162,10 +192,10 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
|
||||
token_count = len(remade_tokens)
|
||||
prompt_target_length = get_target_prompt_token_count(token_count)
|
||||
tokens_to_add = prompt_target_length - len(remade_tokens) + 1
|
||||
tokens_to_add = prompt_target_length - len(remade_tokens)
|
||||
|
||||
remade_tokens = [id_start] + remade_tokens + [id_end] * tokens_to_add
|
||||
multipliers = [1.0] + multipliers + [1.0] * tokens_to_add
|
||||
remade_tokens = remade_tokens + [id_end] * tokens_to_add
|
||||
multipliers = multipliers + [1.0] * tokens_to_add
|
||||
|
||||
return remade_tokens, fixes, multipliers, token_count
|
||||
|
||||
@ -260,29 +290,55 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
hijack_fixes.append(fixes)
|
||||
batch_multipliers.append(multipliers)
|
||||
return batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count
|
||||
|
||||
|
||||
def forward(self, text):
|
||||
|
||||
if opts.use_old_emphasis_implementation:
|
||||
use_old = opts.use_old_emphasis_implementation
|
||||
if use_old:
|
||||
batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text_old(text)
|
||||
else:
|
||||
batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text(text)
|
||||
|
||||
self.hijack.fixes = hijack_fixes
|
||||
self.hijack.comments += hijack_comments
|
||||
|
||||
if len(used_custom_terms) > 0:
|
||||
self.hijack.comments.append("Used embeddings: " + ", ".join([f'{word} [{checksum}]' for word, checksum in used_custom_terms]))
|
||||
|
||||
if use_old:
|
||||
self.hijack.fixes = hijack_fixes
|
||||
return self.process_tokens(remade_batch_tokens, batch_multipliers)
|
||||
|
||||
z = None
|
||||
i = 0
|
||||
while max(map(len, remade_batch_tokens)) != 0:
|
||||
rem_tokens = [x[75:] for x in remade_batch_tokens]
|
||||
rem_multipliers = [x[75:] for x in batch_multipliers]
|
||||
|
||||
target_token_count = get_target_prompt_token_count(token_count) + 2
|
||||
self.hijack.fixes = []
|
||||
for unfiltered in hijack_fixes:
|
||||
fixes = []
|
||||
for fix in unfiltered:
|
||||
if fix[0] == i:
|
||||
fixes.append(fix[1])
|
||||
self.hijack.fixes.append(fixes)
|
||||
|
||||
z1 = self.process_tokens([x[:75] for x in remade_batch_tokens], [x[:75] for x in batch_multipliers])
|
||||
z = z1 if z is None else torch.cat((z, z1), axis=-2)
|
||||
|
||||
remade_batch_tokens = rem_tokens
|
||||
batch_multipliers = rem_multipliers
|
||||
i += 1
|
||||
|
||||
return z
|
||||
|
||||
|
||||
def process_tokens(self, remade_batch_tokens, batch_multipliers):
|
||||
if not opts.use_old_emphasis_implementation:
|
||||
remade_batch_tokens = [[self.wrapped.tokenizer.bos_token_id] + x[:75] + [self.wrapped.tokenizer.eos_token_id] for x in remade_batch_tokens]
|
||||
batch_multipliers = [[1.0] + x[:75] + [1.0] for x in batch_multipliers]
|
||||
|
||||
tokens = torch.asarray(remade_batch_tokens).to(device)
|
||||
outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
|
||||
|
||||
position_ids_array = [min(x, 75) for x in range(target_token_count-1)] + [76]
|
||||
position_ids = torch.asarray(position_ids_array, device=devices.device).expand((1, -1))
|
||||
|
||||
remade_batch_tokens_of_same_length = [x + [self.wrapped.tokenizer.eos_token_id] * (target_token_count - len(x)) for x in remade_batch_tokens]
|
||||
tokens = torch.asarray(remade_batch_tokens_of_same_length).to(device)
|
||||
|
||||
outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids, output_hidden_states=-opts.CLIP_stop_at_last_layers)
|
||||
if opts.CLIP_stop_at_last_layers > 1:
|
||||
z = outputs.hidden_states[-opts.CLIP_stop_at_last_layers]
|
||||
z = self.wrapped.transformer.text_model.final_layer_norm(z)
|
||||
@ -290,7 +346,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
|
||||
z = outputs.last_hidden_state
|
||||
|
||||
# restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
|
||||
batch_multipliers_of_same_length = [x + [1.0] * (target_token_count - len(x)) for x in batch_multipliers]
|
||||
batch_multipliers_of_same_length = [x + [1.0] * (75 - len(x)) for x in batch_multipliers]
|
||||
batch_multipliers = torch.asarray(batch_multipliers_of_same_length).to(device)
|
||||
original_mean = z.mean()
|
||||
z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
import math
|
||||
import sys
|
||||
import traceback
|
||||
import importlib
|
||||
|
||||
import torch
|
||||
from torch import einsum
|
||||
@ -9,12 +10,12 @@ from ldm.util import default
|
||||
from einops import rearrange
|
||||
|
||||
from modules import shared
|
||||
from modules.hypernetworks import hypernetwork
|
||||
|
||||
|
||||
if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers:
|
||||
try:
|
||||
import xformers.ops
|
||||
import functorch
|
||||
xformers._is_functorch_available = True
|
||||
shared.xformers_available = True
|
||||
except Exception:
|
||||
print("Cannot import xformers", file=sys.stderr)
|
||||
@ -28,16 +29,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
|
||||
q_in = self.to_q(x)
|
||||
context = default(context, x)
|
||||
|
||||
hypernetwork = shared.loaded_hypernetwork
|
||||
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
|
||||
|
||||
if hypernetwork_layers is not None:
|
||||
k_in = self.to_k(hypernetwork_layers[0](context))
|
||||
v_in = self.to_v(hypernetwork_layers[1](context))
|
||||
else:
|
||||
k_in = self.to_k(context)
|
||||
v_in = self.to_v(context)
|
||||
del context, x
|
||||
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
|
||||
k_in = self.to_k(context_k)
|
||||
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))
|
||||
del q_in, k_in, v_in
|
||||
@ -61,22 +56,16 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
|
||||
return self.to_out(r2)
|
||||
|
||||
|
||||
# taken from https://github.com/Doggettx/stable-diffusion
|
||||
# taken from https://github.com/Doggettx/stable-diffusion and modified
|
||||
def split_cross_attention_forward(self, x, context=None, mask=None):
|
||||
h = self.heads
|
||||
|
||||
q_in = self.to_q(x)
|
||||
context = default(context, x)
|
||||
|
||||
hypernetwork = shared.loaded_hypernetwork
|
||||
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
|
||||
|
||||
if hypernetwork_layers is not None:
|
||||
k_in = self.to_k(hypernetwork_layers[0](context))
|
||||
v_in = self.to_v(hypernetwork_layers[1](context))
|
||||
else:
|
||||
k_in = self.to_k(context)
|
||||
v_in = self.to_v(context)
|
||||
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
|
||||
k_in = self.to_k(context_k)
|
||||
v_in = self.to_v(context_v)
|
||||
|
||||
k_in *= self.scale
|
||||
|
||||
@ -128,18 +117,111 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
|
||||
|
||||
return self.to_out(r2)
|
||||
|
||||
|
||||
def check_for_psutil():
|
||||
try:
|
||||
spec = importlib.util.find_spec('psutil')
|
||||
return spec is not None
|
||||
except ModuleNotFoundError:
|
||||
return False
|
||||
|
||||
invokeAI_mps_available = check_for_psutil()
|
||||
|
||||
# -- Taken from https://github.com/invoke-ai/InvokeAI --
|
||||
if invokeAI_mps_available:
|
||||
import psutil
|
||||
mem_total_gb = psutil.virtual_memory().total // (1 << 30)
|
||||
|
||||
def einsum_op_compvis(q, k, v):
|
||||
s = einsum('b i d, b j d -> b i j', q, k)
|
||||
s = s.softmax(dim=-1, dtype=s.dtype)
|
||||
return einsum('b i j, b j d -> b i d', s, v)
|
||||
|
||||
def einsum_op_slice_0(q, k, v, slice_size):
|
||||
r = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
|
||||
for i in range(0, q.shape[0], slice_size):
|
||||
end = i + slice_size
|
||||
r[i:end] = einsum_op_compvis(q[i:end], k[i:end], v[i:end])
|
||||
return r
|
||||
|
||||
def einsum_op_slice_1(q, k, v, slice_size):
|
||||
r = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
|
||||
for i in range(0, q.shape[1], slice_size):
|
||||
end = i + slice_size
|
||||
r[:, i:end] = einsum_op_compvis(q[:, i:end], k, v)
|
||||
return r
|
||||
|
||||
def einsum_op_mps_v1(q, k, v):
|
||||
if q.shape[1] <= 4096: # (512x512) max q.shape[1]: 4096
|
||||
return einsum_op_compvis(q, k, v)
|
||||
else:
|
||||
slice_size = math.floor(2**30 / (q.shape[0] * q.shape[1]))
|
||||
return einsum_op_slice_1(q, k, v, slice_size)
|
||||
|
||||
def einsum_op_mps_v2(q, k, v):
|
||||
if mem_total_gb > 8 and q.shape[1] <= 4096:
|
||||
return einsum_op_compvis(q, k, v)
|
||||
else:
|
||||
return einsum_op_slice_0(q, k, v, 1)
|
||||
|
||||
def einsum_op_tensor_mem(q, k, v, max_tensor_mb):
|
||||
size_mb = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size() // (1 << 20)
|
||||
if size_mb <= max_tensor_mb:
|
||||
return einsum_op_compvis(q, k, v)
|
||||
div = 1 << int((size_mb - 1) / max_tensor_mb).bit_length()
|
||||
if div <= q.shape[0]:
|
||||
return einsum_op_slice_0(q, k, v, q.shape[0] // div)
|
||||
return einsum_op_slice_1(q, k, v, max(q.shape[1] // div, 1))
|
||||
|
||||
def einsum_op_cuda(q, k, v):
|
||||
stats = torch.cuda.memory_stats(q.device)
|
||||
mem_active = stats['active_bytes.all.current']
|
||||
mem_reserved = stats['reserved_bytes.all.current']
|
||||
mem_free_cuda, _ = torch.cuda.mem_get_info(q.device)
|
||||
mem_free_torch = mem_reserved - mem_active
|
||||
mem_free_total = mem_free_cuda + mem_free_torch
|
||||
# Divide factor of safety as there's copying and fragmentation
|
||||
return self.einsum_op_tensor_mem(q, k, v, mem_free_total / 3.3 / (1 << 20))
|
||||
|
||||
def einsum_op(q, k, v):
|
||||
if q.device.type == 'cuda':
|
||||
return einsum_op_cuda(q, k, v)
|
||||
|
||||
if q.device.type == 'mps':
|
||||
if mem_total_gb >= 32:
|
||||
return einsum_op_mps_v1(q, k, v)
|
||||
return einsum_op_mps_v2(q, k, v)
|
||||
|
||||
# Smaller slices are faster due to L2/L3/SLC caches.
|
||||
# Tested on i7 with 8MB L3 cache.
|
||||
return einsum_op_tensor_mem(q, k, v, 32)
|
||||
|
||||
def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None):
|
||||
h = self.heads
|
||||
|
||||
q = self.to_q(x)
|
||||
context = default(context, x)
|
||||
|
||||
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
|
||||
k = self.to_k(context_k) * self.scale
|
||||
v = 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, k, v))
|
||||
r = einsum_op(q, k, v)
|
||||
return self.to_out(rearrange(r, '(b h) n d -> b n (h d)', h=h))
|
||||
|
||||
# -- End of code from https://github.com/invoke-ai/InvokeAI --
|
||||
|
||||
def xformers_attention_forward(self, x, context=None, mask=None):
|
||||
h = self.heads
|
||||
q_in = self.to_q(x)
|
||||
context = default(context, x)
|
||||
hypernetwork = shared.loaded_hypernetwork
|
||||
hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
|
||||
if hypernetwork_layers is not None:
|
||||
k_in = self.to_k(hypernetwork_layers[0](context))
|
||||
v_in = self.to_v(hypernetwork_layers[1](context))
|
||||
else:
|
||||
k_in = self.to_k(context)
|
||||
v_in = self.to_v(context)
|
||||
|
||||
context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
|
||||
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))
|
||||
del q_in, k_in, v_in
|
||||
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)
|
||||
|
||||
@ -149,8 +149,13 @@ def load_model_weights(model, checkpoint_info):
|
||||
model.half()
|
||||
|
||||
devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16
|
||||
devices.dtype_vae = torch.float32 if shared.cmd_opts.no_half or shared.cmd_opts.no_half_vae else torch.float16
|
||||
|
||||
vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt"
|
||||
|
||||
if not os.path.exists(vae_file) and shared.cmd_opts.vae_path is not None:
|
||||
vae_file = shared.cmd_opts.vae_path
|
||||
|
||||
if os.path.exists(vae_file):
|
||||
print(f"Loading VAE weights from: {vae_file}")
|
||||
vae_ckpt = torch.load(vae_file, map_location="cpu")
|
||||
@ -158,6 +163,8 @@ def load_model_weights(model, checkpoint_info):
|
||||
|
||||
model.first_stage_model.load_state_dict(vae_dict)
|
||||
|
||||
model.first_stage_model.to(devices.dtype_vae)
|
||||
|
||||
model.sd_model_hash = sd_model_hash
|
||||
model.sd_model_checkpoint = checkpoint_file
|
||||
model.sd_checkpoint_info = checkpoint_info
|
||||
|
||||
@ -7,7 +7,7 @@ import inspect
|
||||
import k_diffusion.sampling
|
||||
import ldm.models.diffusion.ddim
|
||||
import ldm.models.diffusion.plms
|
||||
from modules import prompt_parser
|
||||
from modules import prompt_parser, devices, processing
|
||||
|
||||
from modules.shared import opts, cmd_opts, state
|
||||
import modules.shared as shared
|
||||
@ -57,7 +57,7 @@ def set_samplers():
|
||||
global samplers, samplers_for_img2img
|
||||
|
||||
hidden = set(opts.hide_samplers)
|
||||
hidden_img2img = set(opts.hide_samplers + ['PLMS', 'DPM fast', 'DPM adaptive'])
|
||||
hidden_img2img = set(opts.hide_samplers + ['PLMS'])
|
||||
|
||||
samplers = [x for x in all_samplers if x.name not in hidden]
|
||||
samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]
|
||||
@ -83,7 +83,7 @@ def setup_img2img_steps(p, steps=None):
|
||||
|
||||
|
||||
def sample_to_image(samples):
|
||||
x_sample = shared.sd_model.decode_first_stage(samples[0:1].type(shared.sd_model.dtype))[0]
|
||||
x_sample = processing.decode_first_stage(shared.sd_model, samples[0:1])[0]
|
||||
x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
|
||||
x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
|
||||
x_sample = x_sample.astype(np.uint8)
|
||||
@ -365,16 +365,26 @@ class KDiffusionSampler:
|
||||
else:
|
||||
sigmas = self.model_wrap.get_sigmas(steps)
|
||||
|
||||
noise = noise * sigmas[steps - t_enc - 1]
|
||||
xi = x + noise
|
||||
|
||||
extra_params_kwargs = self.initialize(p)
|
||||
|
||||
sigma_sched = sigmas[steps - t_enc - 1:]
|
||||
xi = x + noise * sigma_sched[0]
|
||||
|
||||
extra_params_kwargs = self.initialize(p)
|
||||
if 'sigma_min' in inspect.signature(self.func).parameters:
|
||||
## last sigma is zero which isn't allowed by DPM Fast & Adaptive so taking value before last
|
||||
extra_params_kwargs['sigma_min'] = sigma_sched[-2]
|
||||
if 'sigma_max' in inspect.signature(self.func).parameters:
|
||||
extra_params_kwargs['sigma_max'] = sigma_sched[0]
|
||||
if 'n' in inspect.signature(self.func).parameters:
|
||||
extra_params_kwargs['n'] = len(sigma_sched) - 1
|
||||
if 'sigma_sched' in inspect.signature(self.func).parameters:
|
||||
extra_params_kwargs['sigma_sched'] = sigma_sched
|
||||
if 'sigmas' in inspect.signature(self.func).parameters:
|
||||
extra_params_kwargs['sigmas'] = sigma_sched
|
||||
|
||||
self.model_wrap_cfg.init_latent = x
|
||||
|
||||
return self.func(self.model_wrap_cfg, xi, sigma_sched, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs)
|
||||
return self.func(self.model_wrap_cfg, xi, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs)
|
||||
|
||||
|
||||
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None):
|
||||
steps = steps or p.steps
|
||||
|
||||
@ -13,7 +13,8 @@ import modules.memmon
|
||||
import modules.sd_models
|
||||
import modules.styles
|
||||
import modules.devices as devices
|
||||
from modules import sd_samplers, hypernetwork
|
||||
from modules import sd_samplers
|
||||
from modules.hypernetworks import hypernetwork
|
||||
from modules.paths import models_path, script_path, sd_path
|
||||
|
||||
sd_model_file = os.path.join(script_path, 'model.ckpt')
|
||||
@ -25,9 +26,11 @@ parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to director
|
||||
parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
|
||||
parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default=None)
|
||||
parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")
|
||||
parser.add_argument("--no-half-vae", action='store_true', help="do not switch the VAE model to 16-bit floats")
|
||||
parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
|
||||
parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
|
||||
parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
|
||||
parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
|
||||
parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
|
||||
parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
|
||||
parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage")
|
||||
@ -35,6 +38,7 @@ parser.add_argument("--always-batch-cond-uncond", action='store_true', help="dis
|
||||
parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
|
||||
parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
|
||||
parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)")
|
||||
parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)
|
||||
parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
|
||||
parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
|
||||
parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
|
||||
@ -46,9 +50,10 @@ parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with
|
||||
parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
|
||||
parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
|
||||
parser.add_argument("--deepdanbooru", action='store_true', help="enable deepdanbooru interrogator")
|
||||
parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
|
||||
parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
|
||||
parser.add_argument("--opt-split-attention", action='store_true', help="force-enables Doggettx's cross-attention layer optimization. By default, it's on for torch cuda.")
|
||||
parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
|
||||
parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
|
||||
parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
|
||||
parser.add_argument("--use-cpu", nargs='+',choices=['SD', 'GFPGAN', 'BSRGAN', 'ESRGAN', 'SCUNet', 'CodeFormer'], help="use CPU as torch device for specified modules", default=[])
|
||||
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
|
||||
parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
|
||||
@ -65,6 +70,7 @@ parser.add_argument("--autolaunch", action='store_true', help="open the webui UR
|
||||
parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
|
||||
parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
|
||||
parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False)
|
||||
parser.add_argument('--vae-path', type=str, help='Path to Variational Autoencoders model', default=None)
|
||||
parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
|
||||
|
||||
|
||||
@ -80,10 +86,18 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
|
||||
xformers_available = False
|
||||
config_filename = cmd_opts.ui_settings_file
|
||||
|
||||
hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks'))
|
||||
os.makedirs(cmd_opts.hypernetwork_dir, exist_ok=True)
|
||||
hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
|
||||
loaded_hypernetwork = None
|
||||
|
||||
|
||||
def reload_hypernetworks():
|
||||
global hypernetworks
|
||||
|
||||
hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
|
||||
hypernetwork.load_hypernetwork(opts.sd_hypernetwork)
|
||||
|
||||
|
||||
class State:
|
||||
skipped = False
|
||||
interrupted = False
|
||||
@ -171,6 +185,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
|
||||
|
||||
"use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"),
|
||||
"save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"),
|
||||
"do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"),
|
||||
}))
|
||||
|
||||
options_templates.update(options_section(('saving-paths', "Paths for saving"), {
|
||||
@ -214,6 +229,10 @@ options_templates.update(options_section(('system', "System"), {
|
||||
"multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job."),
|
||||
}))
|
||||
|
||||
options_templates.update(options_section(('training', "Training"), {
|
||||
"unload_models_when_training": OptionInfo(False, "Unload VAE and CLIP from VRAM when training"),
|
||||
}))
|
||||
|
||||
options_templates.update(options_section(('sd', "Stable Diffusion"), {
|
||||
"sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, show_on_main_page=True),
|
||||
"sd_hypernetwork": OptionInfo("None", "Stable Diffusion finetune hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}),
|
||||
@ -224,6 +243,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
|
||||
"enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),
|
||||
"use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
|
||||
"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 }),
|
||||
"filter_nsfw": OptionInfo(False, "Filter NSFW content"),
|
||||
'CLIP_stop_at_last_layers': OptionInfo(1, "Stop At last layers of CLIP model", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
|
||||
"random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
|
||||
@ -235,7 +255,8 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
|
||||
"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, "Interrogate: maximum number of lines in text file (0 = No limit)"),
|
||||
"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"),
|
||||
}))
|
||||
|
||||
options_templates.update(options_section(('ui', "User interface"), {
|
||||
@ -259,6 +280,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
|
||||
's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "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}),
|
||||
}))
|
||||
|
||||
|
||||
|
||||
@ -10,6 +10,7 @@ from tqdm import tqdm
|
||||
from modules import modelloader
|
||||
from modules.shared import cmd_opts, opts, device
|
||||
from modules.swinir_model_arch import SwinIR as net
|
||||
from modules.swinir_model_arch_v2 import Swin2SR as net2
|
||||
from modules.upscaler import Upscaler, UpscalerData
|
||||
|
||||
precision_scope = (
|
||||
@ -57,22 +58,42 @@ class UpscalerSwinIR(Upscaler):
|
||||
filename = path
|
||||
if filename is None or not os.path.exists(filename):
|
||||
return None
|
||||
model = net(
|
||||
if filename.endswith(".v2.pth"):
|
||||
model = net2(
|
||||
upscale=scale,
|
||||
in_chans=3,
|
||||
img_size=64,
|
||||
window_size=8,
|
||||
img_range=1.0,
|
||||
depths=[6, 6, 6, 6, 6, 6, 6, 6, 6],
|
||||
embed_dim=240,
|
||||
num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8],
|
||||
depths=[6, 6, 6, 6, 6, 6],
|
||||
embed_dim=180,
|
||||
num_heads=[6, 6, 6, 6, 6, 6],
|
||||
mlp_ratio=2,
|
||||
upsampler="nearest+conv",
|
||||
resi_connection="3conv",
|
||||
)
|
||||
resi_connection="1conv",
|
||||
)
|
||||
params = None
|
||||
else:
|
||||
model = net(
|
||||
upscale=scale,
|
||||
in_chans=3,
|
||||
img_size=64,
|
||||
window_size=8,
|
||||
img_range=1.0,
|
||||
depths=[6, 6, 6, 6, 6, 6, 6, 6, 6],
|
||||
embed_dim=240,
|
||||
num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8],
|
||||
mlp_ratio=2,
|
||||
upsampler="nearest+conv",
|
||||
resi_connection="3conv",
|
||||
)
|
||||
params = "params_ema"
|
||||
|
||||
pretrained_model = torch.load(filename)
|
||||
model.load_state_dict(pretrained_model["params_ema"], strict=True)
|
||||
if params is not None:
|
||||
model.load_state_dict(pretrained_model[params], strict=True)
|
||||
else:
|
||||
model.load_state_dict(pretrained_model, strict=True)
|
||||
if not cmd_opts.no_half:
|
||||
model = model.half()
|
||||
return model
|
||||
|
||||
1017
modules/swinir_model_arch_v2.py
Normal file
1017
modules/swinir_model_arch_v2.py
Normal file
File diff suppressed because it is too large
Load Diff
@ -8,18 +8,17 @@ from torchvision import transforms
|
||||
|
||||
import random
|
||||
import tqdm
|
||||
from modules import devices
|
||||
from modules import devices, shared
|
||||
import re
|
||||
|
||||
re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
|
||||
|
||||
|
||||
class PersonalizedBase(Dataset):
|
||||
def __init__(self, data_root, size=None, repeats=100, flip_p=0.5, placeholder_token="*", width=512, height=512, model=None, device=None, template_file=None):
|
||||
def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False):
|
||||
|
||||
self.placeholder_token = placeholder_token
|
||||
|
||||
self.size = size
|
||||
self.width = width
|
||||
self.height = height
|
||||
self.flip = transforms.RandomHorizontalFlip(p=flip_p)
|
||||
@ -33,12 +32,15 @@ class PersonalizedBase(Dataset):
|
||||
|
||||
assert data_root, 'dataset directory not specified'
|
||||
|
||||
cond_model = shared.sd_model.cond_stage_model
|
||||
|
||||
self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)]
|
||||
print("Preparing dataset...")
|
||||
for path in tqdm.tqdm(self.image_paths):
|
||||
image = Image.open(path)
|
||||
image = image.convert('RGB')
|
||||
image = image.resize((self.width, self.height), PIL.Image.BICUBIC)
|
||||
try:
|
||||
image = Image.open(path).convert('RGB').resize((self.width, self.height), PIL.Image.BICUBIC)
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
filename = os.path.basename(path)
|
||||
filename_tokens = os.path.splitext(filename)[0]
|
||||
@ -53,7 +55,13 @@ class PersonalizedBase(Dataset):
|
||||
init_latent = model.get_first_stage_encoding(model.encode_first_stage(torchdata.unsqueeze(dim=0))).squeeze()
|
||||
init_latent = init_latent.to(devices.cpu)
|
||||
|
||||
self.dataset.append((init_latent, filename_tokens))
|
||||
if include_cond:
|
||||
text = self.create_text(filename_tokens)
|
||||
cond = cond_model([text]).to(devices.cpu)
|
||||
else:
|
||||
cond = None
|
||||
|
||||
self.dataset.append((init_latent, filename_tokens, cond))
|
||||
|
||||
self.length = len(self.dataset) * repeats
|
||||
|
||||
@ -64,6 +72,12 @@ class PersonalizedBase(Dataset):
|
||||
def shuffle(self):
|
||||
self.indexes = self.initial_indexes[torch.randperm(self.initial_indexes.shape[0])]
|
||||
|
||||
def create_text(self, filename_tokens):
|
||||
text = random.choice(self.lines)
|
||||
text = text.replace("[name]", self.placeholder_token)
|
||||
text = text.replace("[filewords]", ' '.join(filename_tokens))
|
||||
return text
|
||||
|
||||
def __len__(self):
|
||||
return self.length
|
||||
|
||||
@ -72,10 +86,7 @@ class PersonalizedBase(Dataset):
|
||||
self.shuffle()
|
||||
|
||||
index = self.indexes[i % len(self.indexes)]
|
||||
x, filename_tokens = self.dataset[index]
|
||||
x, filename_tokens, cond = self.dataset[index]
|
||||
|
||||
text = random.choice(self.lines)
|
||||
text = text.replace("[name]", self.placeholder_token)
|
||||
text = text.replace("[filewords]", ' '.join(filename_tokens))
|
||||
|
||||
return x, text
|
||||
text = self.create_text(filename_tokens)
|
||||
return x, text, cond
|
||||
|
||||
34
modules/textual_inversion/learn_schedule.py
Normal file
34
modules/textual_inversion/learn_schedule.py
Normal file
@ -0,0 +1,34 @@
|
||||
|
||||
class LearnSchedule:
|
||||
def __init__(self, learn_rate, max_steps, cur_step=0):
|
||||
pairs = learn_rate.split(',')
|
||||
self.rates = []
|
||||
self.it = 0
|
||||
self.maxit = 0
|
||||
for i, pair in enumerate(pairs):
|
||||
tmp = pair.split(':')
|
||||
if len(tmp) == 2:
|
||||
step = int(tmp[1])
|
||||
if step > cur_step:
|
||||
self.rates.append((float(tmp[0]), min(step, max_steps)))
|
||||
self.maxit += 1
|
||||
if step > max_steps:
|
||||
return
|
||||
elif step == -1:
|
||||
self.rates.append((float(tmp[0]), max_steps))
|
||||
self.maxit += 1
|
||||
return
|
||||
else:
|
||||
self.rates.append((float(tmp[0]), max_steps))
|
||||
self.maxit += 1
|
||||
return
|
||||
|
||||
def __iter__(self):
|
||||
return self
|
||||
|
||||
def __next__(self):
|
||||
if self.it < self.maxit:
|
||||
self.it += 1
|
||||
return self.rates[self.it - 1]
|
||||
else:
|
||||
raise StopIteration
|
||||
@ -3,12 +3,16 @@ from PIL import Image, ImageOps
|
||||
import platform
|
||||
import sys
|
||||
import tqdm
|
||||
import time
|
||||
|
||||
from modules import shared, images
|
||||
from modules.shared import opts, cmd_opts
|
||||
if cmd_opts.deepdanbooru:
|
||||
import modules.deepbooru as deepbooru
|
||||
|
||||
|
||||
def preprocess(process_src, process_dst, process_flip, process_split, process_caption):
|
||||
size = 512
|
||||
def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
|
||||
width = process_width
|
||||
height = process_height
|
||||
src = os.path.abspath(process_src)
|
||||
dst = os.path.abspath(process_dst)
|
||||
|
||||
@ -24,10 +28,21 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
|
||||
if process_caption:
|
||||
shared.interrogator.load()
|
||||
|
||||
if process_caption_deepbooru:
|
||||
deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, opts.deepbooru_sort_alpha)
|
||||
|
||||
def save_pic_with_caption(image, index):
|
||||
if process_caption:
|
||||
caption = "-" + shared.interrogator.generate_caption(image)
|
||||
caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
|
||||
elif process_caption_deepbooru:
|
||||
shared.deepbooru_process_return["value"] = -1
|
||||
shared.deepbooru_process_queue.put(image)
|
||||
while shared.deepbooru_process_return["value"] == -1:
|
||||
time.sleep(0.2)
|
||||
caption = "-" + shared.deepbooru_process_return["value"]
|
||||
caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
|
||||
shared.deepbooru_process_return["value"] = -1
|
||||
else:
|
||||
caption = filename
|
||||
caption = os.path.splitext(caption)[0]
|
||||
@ -45,7 +60,10 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
|
||||
for index, imagefile in enumerate(tqdm.tqdm(files)):
|
||||
subindex = [0]
|
||||
filename = os.path.join(src, imagefile)
|
||||
img = Image.open(filename).convert("RGB")
|
||||
try:
|
||||
img = Image.open(filename).convert("RGB")
|
||||
except Exception:
|
||||
continue
|
||||
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
@ -55,23 +73,23 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
|
||||
is_wide = ratio < 1 / 1.35
|
||||
|
||||
if process_split and is_tall:
|
||||
img = img.resize((size, size * img.height // img.width))
|
||||
img = img.resize((width, height * img.height // img.width))
|
||||
|
||||
top = img.crop((0, 0, size, size))
|
||||
top = img.crop((0, 0, width, height))
|
||||
save_pic(top, index)
|
||||
|
||||
bot = img.crop((0, img.height - size, size, img.height))
|
||||
bot = img.crop((0, img.height - height, width, img.height))
|
||||
save_pic(bot, index)
|
||||
elif process_split and is_wide:
|
||||
img = img.resize((size * img.width // img.height, size))
|
||||
img = img.resize((width * img.width // img.height, height))
|
||||
|
||||
left = img.crop((0, 0, size, size))
|
||||
left = img.crop((0, 0, width, height))
|
||||
save_pic(left, index)
|
||||
|
||||
right = img.crop((img.width - size, 0, img.width, size))
|
||||
right = img.crop((img.width - width, 0, img.width, height))
|
||||
save_pic(right, index)
|
||||
else:
|
||||
img = images.resize_image(1, img, size, size)
|
||||
img = images.resize_image(1, img, width, height)
|
||||
save_pic(img, index)
|
||||
|
||||
shared.state.nextjob()
|
||||
@ -79,6 +97,10 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
|
||||
if process_caption:
|
||||
shared.interrogator.send_blip_to_ram()
|
||||
|
||||
if process_caption_deepbooru:
|
||||
deepbooru.release_process()
|
||||
|
||||
|
||||
def sanitize_caption(base_path, original_caption, suffix):
|
||||
operating_system = platform.system().lower()
|
||||
if (operating_system == "windows"):
|
||||
|
||||
@ -10,6 +10,7 @@ import datetime
|
||||
|
||||
from modules import shared, devices, sd_hijack, processing, sd_models
|
||||
import modules.textual_inversion.dataset
|
||||
from modules.textual_inversion.learn_schedule import LearnSchedule
|
||||
|
||||
|
||||
class Embedding:
|
||||
@ -156,7 +157,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
|
||||
return fn
|
||||
|
||||
|
||||
def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps, create_image_every, save_embedding_every, template_file):
|
||||
def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file, preview_image_prompt):
|
||||
assert embedding_name, 'embedding not selected'
|
||||
|
||||
shared.state.textinfo = "Initializing textual inversion training..."
|
||||
@ -182,15 +183,13 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
|
||||
|
||||
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
|
||||
with torch.autocast("cuda"):
|
||||
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
|
||||
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
|
||||
|
||||
hijack = sd_hijack.model_hijack
|
||||
|
||||
embedding = hijack.embedding_db.word_embeddings[embedding_name]
|
||||
embedding.vec.requires_grad = True
|
||||
|
||||
optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
|
||||
|
||||
losses = torch.zeros((32,))
|
||||
|
||||
last_saved_file = "<none>"
|
||||
@ -200,12 +199,24 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
|
||||
if ititial_step > steps:
|
||||
return embedding, filename
|
||||
|
||||
schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
|
||||
(learn_rate, end_step) = next(schedules)
|
||||
print(f'Training at rate of {learn_rate} until step {end_step}')
|
||||
|
||||
optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
|
||||
|
||||
pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
|
||||
for i, (x, text) in pbar:
|
||||
for i, (x, text, _) in pbar:
|
||||
embedding.step = i + ititial_step
|
||||
|
||||
if embedding.step > steps:
|
||||
break
|
||||
if embedding.step > end_step:
|
||||
try:
|
||||
(learn_rate, end_step) = next(schedules)
|
||||
except:
|
||||
break
|
||||
tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
|
||||
for pg in optimizer.param_groups:
|
||||
pg['lr'] = learn_rate
|
||||
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
@ -223,7 +234,10 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
pbar.set_description(f"loss: {losses.mean():.7f}")
|
||||
epoch_num = embedding.step // len(ds)
|
||||
epoch_step = embedding.step - (epoch_num * len(ds)) + 1
|
||||
|
||||
pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{len(ds)}]loss: {losses.mean():.7f}")
|
||||
|
||||
if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
|
||||
last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.pt')
|
||||
@ -232,10 +246,14 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
|
||||
if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0:
|
||||
last_saved_image = os.path.join(images_dir, f'{embedding_name}-{embedding.step}.png')
|
||||
|
||||
preview_text = text if preview_image_prompt == "" else preview_image_prompt
|
||||
|
||||
p = processing.StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
prompt=text,
|
||||
prompt=preview_text,
|
||||
steps=20,
|
||||
height=training_height,
|
||||
width=training_width,
|
||||
do_not_save_grid=True,
|
||||
do_not_save_samples=True,
|
||||
)
|
||||
@ -246,7 +264,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
|
||||
shared.state.current_image = image
|
||||
image.save(last_saved_image)
|
||||
|
||||
last_saved_image += f", prompt: {text}"
|
||||
last_saved_image += f", prompt: {preview_text}"
|
||||
|
||||
shared.state.job_no = embedding.step
|
||||
|
||||
@ -268,4 +286,3 @@ Last saved image: {html.escape(last_saved_image)}<br/>
|
||||
embedding.save(filename)
|
||||
|
||||
return embedding, filename
|
||||
|
||||
|
||||
@ -23,6 +23,8 @@ def preprocess(*args):
|
||||
|
||||
def train_embedding(*args):
|
||||
|
||||
assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible'
|
||||
|
||||
try:
|
||||
sd_hijack.undo_optimizations()
|
||||
|
||||
|
||||
124
modules/ui.py
124
modules/ui.py
@ -39,6 +39,7 @@ import modules.generation_parameters_copypaste
|
||||
from modules import prompt_parser
|
||||
from modules.images import save_image
|
||||
import modules.textual_inversion.ui
|
||||
import modules.hypernetworks.ui
|
||||
|
||||
# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
|
||||
mimetypes.init()
|
||||
@ -50,6 +51,11 @@ if not cmd_opts.share and not cmd_opts.listen:
|
||||
gradio.utils.version_check = lambda: None
|
||||
gradio.utils.get_local_ip_address = lambda: '127.0.0.1'
|
||||
|
||||
if cmd_opts.ngrok != None:
|
||||
import modules.ngrok as ngrok
|
||||
print('ngrok authtoken detected, trying to connect...')
|
||||
ngrok.connect(cmd_opts.ngrok, cmd_opts.port if cmd_opts.port != None else 7860)
|
||||
|
||||
|
||||
def gr_show(visible=True):
|
||||
return {"visible": visible, "__type__": "update"}
|
||||
@ -125,6 +131,8 @@ def save_files(js_data, images, do_make_zip, index):
|
||||
images = [images[index]]
|
||||
start_index = index
|
||||
|
||||
os.makedirs(opts.outdir_save, exist_ok=True)
|
||||
|
||||
with open(os.path.join(opts.outdir_save, "log.csv"), "a", encoding="utf8", newline='') as file:
|
||||
at_start = file.tell() == 0
|
||||
writer = csv.writer(file)
|
||||
@ -175,8 +183,15 @@ def wrap_gradio_call(func, extra_outputs=None):
|
||||
try:
|
||||
res = list(func(*args, **kwargs))
|
||||
except Exception as e:
|
||||
# When printing out our debug argument list, do not print out more than a MB of text
|
||||
max_debug_str_len = 131072 # (1024*1024)/8
|
||||
|
||||
print("Error completing request", file=sys.stderr)
|
||||
print("Arguments:", args, kwargs, file=sys.stderr)
|
||||
argStr = f"Arguments: {str(args)} {str(kwargs)}"
|
||||
print(argStr[:max_debug_str_len], file=sys.stderr)
|
||||
if len(argStr) > max_debug_str_len:
|
||||
print(f"(Argument list truncated at {max_debug_str_len}/{len(argStr)} characters)", file=sys.stderr)
|
||||
|
||||
print(traceback.format_exc(), file=sys.stderr)
|
||||
|
||||
shared.state.job = ""
|
||||
@ -428,7 +443,10 @@ def create_toprow(is_img2img):
|
||||
|
||||
with gr.Row():
|
||||
with gr.Column(scale=8):
|
||||
negative_prompt = gr.Textbox(label="Negative prompt", elem_id="negative_prompt", show_label=False, placeholder="Negative prompt", lines=2)
|
||||
with gr.Row():
|
||||
negative_prompt = gr.Textbox(label="Negative prompt", elem_id="negative_prompt", show_label=False, placeholder="Negative prompt", lines=2)
|
||||
with gr.Column(scale=1, elem_id="roll_col"):
|
||||
sh = gr.Button(elem_id="sh", visible=True)
|
||||
|
||||
with gr.Column(scale=1, elem_id="style_neg_col"):
|
||||
prompt_style2 = gr.Dropdown(label="Style 2", elem_id=f"{id_part}_style2_index", choices=[k for k, v in shared.prompt_styles.styles.items()], value=next(iter(shared.prompt_styles.styles.keys())), visible=len(shared.prompt_styles.styles) > 1)
|
||||
@ -524,7 +542,7 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7)
|
||||
|
||||
with gr.Row():
|
||||
batch_count = gr.Slider(minimum=1, maximum=cmd_opts.max_batch_count, step=1, label='Batch count', value=1)
|
||||
batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)
|
||||
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)
|
||||
|
||||
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0)
|
||||
@ -555,9 +573,9 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
with gr.Row():
|
||||
download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
|
||||
|
||||
with gr.Group():
|
||||
html_info = gr.HTML()
|
||||
generation_info = gr.Textbox(visible=False)
|
||||
with gr.Group():
|
||||
html_info = gr.HTML()
|
||||
generation_info = gr.Textbox(visible=False)
|
||||
|
||||
connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
|
||||
connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
|
||||
@ -710,7 +728,7 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
tiling = gr.Checkbox(label='Tiling', value=False)
|
||||
|
||||
with gr.Row():
|
||||
batch_count = gr.Slider(minimum=1, maximum=cmd_opts.max_batch_count, step=1, label='Batch count', value=1)
|
||||
batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)
|
||||
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)
|
||||
|
||||
with gr.Group():
|
||||
@ -743,9 +761,9 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
with gr.Row():
|
||||
download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
|
||||
|
||||
with gr.Group():
|
||||
html_info = gr.HTML()
|
||||
generation_info = gr.Textbox(visible=False)
|
||||
with gr.Group():
|
||||
html_info = gr.HTML()
|
||||
generation_info = gr.Textbox(visible=False)
|
||||
|
||||
connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
|
||||
connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
|
||||
@ -973,7 +991,7 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
|
||||
extras_send_to_inpaint.click(
|
||||
fn=lambda x: image_from_url_text(x),
|
||||
_js="extract_image_from_gallery_img2img",
|
||||
_js="extract_image_from_gallery_inpaint",
|
||||
inputs=[result_images],
|
||||
outputs=[init_img_with_mask],
|
||||
)
|
||||
@ -1034,18 +1052,37 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
gr.HTML(value="")
|
||||
|
||||
with gr.Column():
|
||||
create_embedding = gr.Button(value="Create", variant='primary')
|
||||
create_embedding = gr.Button(value="Create embedding", variant='primary')
|
||||
|
||||
with gr.Group():
|
||||
gr.HTML(value="<p style='margin-bottom: 0.7em'>Create a new hypernetwork</p>")
|
||||
|
||||
new_hypernetwork_name = gr.Textbox(label="Name")
|
||||
new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "320", "640", "1280"])
|
||||
|
||||
with gr.Row():
|
||||
with gr.Column(scale=3):
|
||||
gr.HTML(value="")
|
||||
|
||||
with gr.Column():
|
||||
create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary')
|
||||
|
||||
with gr.Group():
|
||||
gr.HTML(value="<p style='margin-bottom: 0.7em'>Preprocess images</p>")
|
||||
|
||||
process_src = gr.Textbox(label='Source directory')
|
||||
process_dst = gr.Textbox(label='Destination directory')
|
||||
process_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
|
||||
process_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
|
||||
|
||||
with gr.Row():
|
||||
process_flip = gr.Checkbox(label='Create flipped copies')
|
||||
process_split = gr.Checkbox(label='Split oversized images into two')
|
||||
process_caption = gr.Checkbox(label='Use BLIP caption as filename')
|
||||
if cmd_opts.deepdanbooru:
|
||||
process_caption_deepbooru = gr.Checkbox(label='Use deepbooru caption as filename')
|
||||
else:
|
||||
process_caption_deepbooru = gr.Checkbox(label='Use deepbooru caption as filename', visible=False)
|
||||
|
||||
with gr.Row():
|
||||
with gr.Column(scale=3):
|
||||
@ -1055,24 +1092,25 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
run_preprocess = gr.Button(value="Preprocess", variant='primary')
|
||||
|
||||
with gr.Group():
|
||||
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding; must specify a directory with a set of 512x512 images</p>")
|
||||
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding; must specify a directory with a set of 1:1 ratio images</p>")
|
||||
train_embedding_name = gr.Dropdown(label='Embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
|
||||
learn_rate = gr.Number(label='Learning rate', value=5.0e-03)
|
||||
train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', choices=[x for x in shared.hypernetworks.keys()])
|
||||
learn_rate = gr.Textbox(label='Learning rate', placeholder="Learning rate", value="0.005")
|
||||
dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
|
||||
log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")
|
||||
template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"))
|
||||
training_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
|
||||
training_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
|
||||
steps = gr.Number(label='Max steps', value=100000, precision=0)
|
||||
num_repeats = gr.Number(label='Number of repeats for a single input image per epoch', value=100, precision=0)
|
||||
create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
|
||||
save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)
|
||||
preview_image_prompt = gr.Textbox(label='Preview prompt', value="")
|
||||
|
||||
with gr.Row():
|
||||
with gr.Column(scale=2):
|
||||
gr.HTML(value="")
|
||||
|
||||
with gr.Column():
|
||||
with gr.Row():
|
||||
interrupt_training = gr.Button(value="Interrupt")
|
||||
train_embedding = gr.Button(value="Train", variant='primary')
|
||||
interrupt_training = gr.Button(value="Interrupt")
|
||||
train_hypernetwork = gr.Button(value="Train Hypernetwork", variant='primary')
|
||||
train_embedding = gr.Button(value="Train Embedding", variant='primary')
|
||||
|
||||
with gr.Column():
|
||||
progressbar = gr.HTML(elem_id="ti_progressbar")
|
||||
@ -1098,15 +1136,31 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
]
|
||||
)
|
||||
|
||||
create_hypernetwork.click(
|
||||
fn=modules.hypernetworks.ui.create_hypernetwork,
|
||||
inputs=[
|
||||
new_hypernetwork_name,
|
||||
new_hypernetwork_sizes,
|
||||
],
|
||||
outputs=[
|
||||
train_hypernetwork_name,
|
||||
ti_output,
|
||||
ti_outcome,
|
||||
]
|
||||
)
|
||||
|
||||
run_preprocess.click(
|
||||
fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
|
||||
_js="start_training_textual_inversion",
|
||||
inputs=[
|
||||
process_src,
|
||||
process_dst,
|
||||
process_width,
|
||||
process_height,
|
||||
process_flip,
|
||||
process_split,
|
||||
process_caption,
|
||||
process_caption_deepbooru
|
||||
],
|
||||
outputs=[
|
||||
ti_output,
|
||||
@ -1122,10 +1176,34 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
learn_rate,
|
||||
dataset_directory,
|
||||
log_directory,
|
||||
training_width,
|
||||
training_height,
|
||||
steps,
|
||||
num_repeats,
|
||||
create_image_every,
|
||||
save_embedding_every,
|
||||
template_file,
|
||||
preview_image_prompt,
|
||||
],
|
||||
outputs=[
|
||||
ti_output,
|
||||
ti_outcome,
|
||||
]
|
||||
)
|
||||
|
||||
train_hypernetwork.click(
|
||||
fn=wrap_gradio_gpu_call(modules.hypernetworks.ui.train_hypernetwork, extra_outputs=[gr.update()]),
|
||||
_js="start_training_textual_inversion",
|
||||
inputs=[
|
||||
train_hypernetwork_name,
|
||||
learn_rate,
|
||||
dataset_directory,
|
||||
log_directory,
|
||||
steps,
|
||||
create_image_every,
|
||||
save_embedding_every,
|
||||
template_file,
|
||||
preview_image_prompt,
|
||||
],
|
||||
outputs=[
|
||||
ti_output,
|
||||
@ -1139,6 +1217,7 @@ def create_ui(wrap_gradio_gpu_call):
|
||||
outputs=[],
|
||||
)
|
||||
|
||||
|
||||
def create_setting_component(key):
|
||||
def fun():
|
||||
return opts.data[key] if key in opts.data else opts.data_labels[key].default
|
||||
@ -1292,6 +1371,7 @@ Requested path was: {f}
|
||||
shared.state.interrupt()
|
||||
settings_interface.gradio_ref.do_restart = True
|
||||
|
||||
|
||||
restart_gradio.click(
|
||||
fn=request_restart,
|
||||
inputs=[],
|
||||
@ -1333,7 +1413,7 @@ Requested path was: {f}
|
||||
|
||||
with gr.Tabs() as tabs:
|
||||
for interface, label, ifid in interfaces:
|
||||
with gr.TabItem(label, id=ifid):
|
||||
with gr.TabItem(label, id=ifid, elem_id='tab_' + ifid):
|
||||
interface.render()
|
||||
|
||||
if os.path.exists(os.path.join(script_path, "notification.mp3")):
|
||||
|
||||
@ -4,7 +4,7 @@ fairscale==0.4.4
|
||||
fonts
|
||||
font-roboto
|
||||
gfpgan
|
||||
gradio==3.4b3
|
||||
gradio==3.4.1
|
||||
invisible-watermark
|
||||
numpy
|
||||
omegaconf
|
||||
@ -23,4 +23,3 @@ resize-right
|
||||
torchdiffeq
|
||||
kornia
|
||||
lark
|
||||
functorch
|
||||
|
||||
@ -2,7 +2,7 @@ transformers==4.19.2
|
||||
diffusers==0.3.0
|
||||
basicsr==1.4.2
|
||||
gfpgan==1.3.8
|
||||
gradio==3.4b3
|
||||
gradio==3.4.1
|
||||
numpy==1.23.3
|
||||
Pillow==9.2.0
|
||||
realesrgan==0.3.0
|
||||
@ -22,4 +22,3 @@ resize-right==0.0.2
|
||||
torchdiffeq==0.2.3
|
||||
kornia==0.6.7
|
||||
lark==1.1.2
|
||||
functorch==0.2.1
|
||||
|
||||
23
script.js
23
script.js
@ -6,6 +6,10 @@ function get_uiCurrentTab() {
|
||||
return gradioApp().querySelector('.tabs button:not(.border-transparent)')
|
||||
}
|
||||
|
||||
function get_uiCurrentTabContent() {
|
||||
return gradioApp().querySelector('.tabitem[id^=tab_]:not([style*="display: none"])')
|
||||
}
|
||||
|
||||
uiUpdateCallbacks = []
|
||||
uiTabChangeCallbacks = []
|
||||
let uiCurrentTab = null
|
||||
@ -40,6 +44,25 @@ document.addEventListener("DOMContentLoaded", function() {
|
||||
mutationObserver.observe( gradioApp(), { childList:true, subtree:true })
|
||||
});
|
||||
|
||||
/**
|
||||
* Add a ctrl+enter as a shortcut to start a generation
|
||||
*/
|
||||
document.addEventListener('keydown', function(e) {
|
||||
var handled = false;
|
||||
if (e.key !== undefined) {
|
||||
if((e.key == "Enter" && (e.metaKey || e.ctrlKey))) handled = true;
|
||||
} else if (e.keyCode !== undefined) {
|
||||
if((e.keyCode == 13 && (e.metaKey || e.ctrlKey))) handled = true;
|
||||
}
|
||||
if (handled) {
|
||||
button = get_uiCurrentTabContent().querySelector('button[id$=_generate]');
|
||||
if (button) {
|
||||
button.click();
|
||||
}
|
||||
e.preventDefault();
|
||||
}
|
||||
})
|
||||
|
||||
/**
|
||||
* checks that a UI element is not in another hidden element or tab content
|
||||
*/
|
||||
|
||||
@ -129,8 +129,6 @@ class Script(scripts.Script):
|
||||
return [original_prompt, original_negative_prompt, cfg, st, randomness, sigma_adjustment]
|
||||
|
||||
def run(self, p, original_prompt, original_negative_prompt, cfg, st, randomness, sigma_adjustment):
|
||||
p.batch_size = 1
|
||||
p.batch_count = 1
|
||||
|
||||
|
||||
def sample_extra(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
|
||||
@ -154,7 +152,7 @@ class Script(scripts.Script):
|
||||
rec_noise = find_noise_for_image(p, cond, uncond, cfg, st)
|
||||
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:], [p.seed + x + 1 for x in range(p.init_latent.shape[0])])
|
||||
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)
|
||||
|
||||
|
||||
@ -38,6 +38,7 @@ class Script(scripts.Script):
|
||||
|
||||
grids = []
|
||||
all_images = []
|
||||
original_init_image = p.init_images
|
||||
state.job_count = loops * batch_count
|
||||
|
||||
initial_color_corrections = [processing.setup_color_correction(p.init_images[0])]
|
||||
@ -45,6 +46,9 @@ class Script(scripts.Script):
|
||||
for n in range(batch_count):
|
||||
history = []
|
||||
|
||||
# Reset to original init image at the start of each batch
|
||||
p.init_images = original_init_image
|
||||
|
||||
for i in range(loops):
|
||||
p.n_iter = 1
|
||||
p.batch_size = 1
|
||||
|
||||
@ -10,7 +10,8 @@ import numpy as np
|
||||
import modules.scripts as scripts
|
||||
import gradio as gr
|
||||
|
||||
from modules import images, hypernetwork
|
||||
from modules import images
|
||||
from modules.hypernetworks import hypernetwork
|
||||
from modules.processing import process_images, Processed, get_correct_sampler
|
||||
from modules.shared import opts, cmd_opts, state
|
||||
import modules.shared as shared
|
||||
@ -27,6 +28,9 @@ def apply_field(field):
|
||||
|
||||
|
||||
def apply_prompt(p, x, xs):
|
||||
if xs[0] not in p.prompt and xs[0] not in p.negative_prompt:
|
||||
raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt.")
|
||||
|
||||
p.prompt = p.prompt.replace(xs[0], x)
|
||||
p.negative_prompt = p.negative_prompt.replace(xs[0], x)
|
||||
|
||||
@ -193,7 +197,7 @@ class Script(scripts.Script):
|
||||
x_values = gr.Textbox(label="X values", visible=False, lines=1)
|
||||
|
||||
with gr.Row():
|
||||
y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[4].label, visible=False, type="index", elem_id="y_type")
|
||||
y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[0].label, visible=False, type="index", elem_id="y_type")
|
||||
y_values = gr.Textbox(label="Y values", visible=False, lines=1)
|
||||
|
||||
draw_legend = gr.Checkbox(label='Draw legend', value=True)
|
||||
@ -205,7 +209,10 @@ class Script(scripts.Script):
|
||||
if not no_fixed_seeds:
|
||||
modules.processing.fix_seed(p)
|
||||
|
||||
p.batch_size = 1
|
||||
if not opts.return_grid:
|
||||
p.batch_size = 1
|
||||
|
||||
|
||||
CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers
|
||||
|
||||
def process_axis(opt, vals):
|
||||
|
||||
43
style.css
43
style.css
@ -1,3 +1,28 @@
|
||||
.container {
|
||||
max-width: 100%;
|
||||
}
|
||||
|
||||
#txt2img_token_counter {
|
||||
height: 0px;
|
||||
}
|
||||
|
||||
#img2img_token_counter {
|
||||
height: 0px;
|
||||
}
|
||||
|
||||
#sh{
|
||||
min-width: 2em;
|
||||
min-height: 2em;
|
||||
max-width: 2em;
|
||||
max-height: 2em;
|
||||
flex-grow: 0;
|
||||
padding-left: 0.25em;
|
||||
padding-right: 0.25em;
|
||||
margin: 0.1em 0;
|
||||
opacity: 0%;
|
||||
cursor: default;
|
||||
}
|
||||
|
||||
.output-html p {margin: 0 0.5em;}
|
||||
|
||||
.row > *,
|
||||
@ -215,6 +240,7 @@ fieldset span.text-gray-500, .gr-block.gr-box span.text-gray-500, label.block s
|
||||
#settings fieldset span.text-gray-500, #settings .gr-block.gr-box span.text-gray-500, #settings label.block span{
|
||||
position: relative;
|
||||
border: none;
|
||||
margin-right: 8em;
|
||||
}
|
||||
|
||||
.gr-panel div.flex-col div.justify-between label span{
|
||||
@ -463,3 +489,20 @@ input[type="range"]{
|
||||
max-width: 32em;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
canvas[key="mask"] {
|
||||
z-index: 12 !important;
|
||||
filter: invert();
|
||||
mix-blend-mode: multiply;
|
||||
pointer-events: none;
|
||||
}
|
||||
|
||||
|
||||
/* gradio 3.4.1 stuff for editable scrollbar values */
|
||||
.gr-box > div > div > input.gr-text-input{
|
||||
position: absolute;
|
||||
right: 0.5em;
|
||||
top: -0.6em;
|
||||
z-index: 200;
|
||||
width: 8em;
|
||||
}
|
||||
|
||||
27
textual_inversion_templates/hypernetwork.txt
Normal file
27
textual_inversion_templates/hypernetwork.txt
Normal file
@ -0,0 +1,27 @@
|
||||
a photo of a [filewords]
|
||||
a rendering of a [filewords]
|
||||
a cropped photo of the [filewords]
|
||||
the photo of a [filewords]
|
||||
a photo of a clean [filewords]
|
||||
a photo of a dirty [filewords]
|
||||
a dark photo of the [filewords]
|
||||
a photo of my [filewords]
|
||||
a photo of the cool [filewords]
|
||||
a close-up photo of a [filewords]
|
||||
a bright photo of the [filewords]
|
||||
a cropped photo of a [filewords]
|
||||
a photo of the [filewords]
|
||||
a good photo of the [filewords]
|
||||
a photo of one [filewords]
|
||||
a close-up photo of the [filewords]
|
||||
a rendition of the [filewords]
|
||||
a photo of the clean [filewords]
|
||||
a rendition of a [filewords]
|
||||
a photo of a nice [filewords]
|
||||
a good photo of a [filewords]
|
||||
a photo of the nice [filewords]
|
||||
a photo of the small [filewords]
|
||||
a photo of the weird [filewords]
|
||||
a photo of the large [filewords]
|
||||
a photo of a cool [filewords]
|
||||
a photo of a small [filewords]
|
||||
1
textual_inversion_templates/none.txt
Normal file
1
textual_inversion_templates/none.txt
Normal file
@ -0,0 +1 @@
|
||||
picture
|
||||
33
webui.py
33
webui.py
@ -29,13 +29,9 @@ from modules import devices
|
||||
from modules import modelloader
|
||||
from modules.paths import script_path
|
||||
from modules.shared import cmd_opts
|
||||
import modules.hypernetworks.hypernetwork
|
||||
|
||||
|
||||
modelloader.cleanup_models()
|
||||
modules.sd_models.setup_model()
|
||||
codeformer.setup_model(cmd_opts.codeformer_models_path)
|
||||
gfpgan.setup_model(cmd_opts.gfpgan_models_path)
|
||||
shared.face_restorers.append(modules.face_restoration.FaceRestoration())
|
||||
modelloader.load_upscalers()
|
||||
queue_lock = threading.Lock()
|
||||
|
||||
|
||||
@ -77,16 +73,24 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
|
||||
return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs)
|
||||
|
||||
|
||||
modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
|
||||
def initialize():
|
||||
modelloader.cleanup_models()
|
||||
modules.sd_models.setup_model()
|
||||
codeformer.setup_model(cmd_opts.codeformer_models_path)
|
||||
gfpgan.setup_model(cmd_opts.gfpgan_models_path)
|
||||
shared.face_restorers.append(modules.face_restoration.FaceRestoration())
|
||||
modelloader.load_upscalers()
|
||||
|
||||
shared.sd_model = modules.sd_models.load_model()
|
||||
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model)))
|
||||
modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
|
||||
|
||||
loaded_hypernetwork = modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)
|
||||
shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
|
||||
shared.sd_model = modules.sd_models.load_model()
|
||||
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model)))
|
||||
shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
|
||||
|
||||
|
||||
def webui():
|
||||
initialize()
|
||||
|
||||
# make the program just exit at ctrl+c without waiting for anything
|
||||
def sigint_handler(sig, frame):
|
||||
print(f'Interrupted with signal {sig} in {frame}')
|
||||
@ -98,7 +102,7 @@ def webui():
|
||||
|
||||
demo = modules.ui.create_ui(wrap_gradio_gpu_call=wrap_gradio_gpu_call)
|
||||
|
||||
app,local_url,share_url = demo.launch(
|
||||
app, local_url, share_url = demo.launch(
|
||||
share=cmd_opts.share,
|
||||
server_name="0.0.0.0" if cmd_opts.listen else None,
|
||||
server_port=cmd_opts.port,
|
||||
@ -108,7 +112,7 @@ def webui():
|
||||
prevent_thread_lock=True
|
||||
)
|
||||
|
||||
app.add_middleware(GZipMiddleware,minimum_size=1000)
|
||||
app.add_middleware(GZipMiddleware, minimum_size=1000)
|
||||
|
||||
while 1:
|
||||
time.sleep(0.5)
|
||||
@ -124,9 +128,10 @@ def webui():
|
||||
modules.scripts.reload_scripts(os.path.join(script_path, "scripts"))
|
||||
print('Reloading modules: modules.ui')
|
||||
importlib.reload(modules.ui)
|
||||
print('Refreshing Model List')
|
||||
modules.sd_models.list_models()
|
||||
print('Restarting Gradio')
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
webui()
|
||||
|
||||
Loading…
Reference in New Issue
Block a user