045750b46a
- Increase max LoRA rank (dim) size to 1024. - Update finetune preprocessing scripts. - ``.bmp`` and ``.jpeg`` are supported. Thanks to breakcore2 and p1atdev! - The default weights of ``tag_images_by_wd14_tagger.py`` is now ``SmilingWolf/wd-v1-4-convnext-tagger-v2``. You can specify another model id from ``SmilingWolf`` by ``--repo_id`` option. Thanks to SmilingWolf for the great work. - To change the weight, remove ``wd14_tagger_model`` folder, and run the script again. - ``--max_data_loader_n_workers`` option is added to each script. This option uses the DataLoader for data loading to speed up loading, 20%~30% faster. - Please specify 2 or 4, depends on the number of CPU cores. - ``--recursive`` option is added to ``merge_dd_tags_to_metadata.py`` and ``merge_captions_to_metadata.py``, only works with ``--full_path``. - ``make_captions_by_git.py`` is added. It uses [GIT microsoft/git-large-textcaps](https://huggingface.co/microsoft/git-large-textcaps) for captioning. - ``requirements.txt`` is updated. If you use this script, [please update the libraries](https://github.com/kohya-ss/sd-scripts#upgrade). - Usage is almost the same as ``make_captions.py``, but batch size should be smaller. - ``--remove_words`` option removes as much text as possible (such as ``the word "XXXX" on it``). - ``--skip_existing`` option is added to ``prepare_buckets_latents.py``. Images with existing npz files are ignored by this option. - ``clean_captions_and_tags.py`` is updated to remove duplicated or conflicting tags, e.g. ``shirt`` is removed when ``white shirt`` exists. if ``black hair`` is with ``red hair``, both are removed. - Tag frequency is added to the metadata in ``train_network.py``. Thanks to space-nuko! - __All tags and number of occurrences of the tag are recorded.__ If you do not want it, disable metadata storing with ``--no_metadata`` option.
72 lines
2.0 KiB
Python
72 lines
2.0 KiB
Python
# v1: initial release
|
|
# v2: add open and save folder icons
|
|
# v3: Add new Utilities tab for Dreambooth folder preparation
|
|
# v3.1: Adding captionning of images to utilities
|
|
|
|
import gradio as gr
|
|
import os
|
|
import argparse
|
|
from library.basic_caption_gui import gradio_basic_caption_gui_tab
|
|
from library.convert_model_gui import gradio_convert_model_tab
|
|
from library.blip_caption_gui import gradio_blip_caption_gui_tab
|
|
from library.git_caption_gui import gradio_git_caption_gui_tab
|
|
from library.wd14_caption_gui import gradio_wd14_caption_gui_tab
|
|
|
|
|
|
def utilities_tab(
|
|
train_data_dir_input=gr.Textbox(),
|
|
reg_data_dir_input=gr.Textbox(),
|
|
output_dir_input=gr.Textbox(),
|
|
logging_dir_input=gr.Textbox(),
|
|
enable_copy_info_button=bool(False),
|
|
enable_dreambooth_tab=True,
|
|
):
|
|
with gr.Tab('Captioning'):
|
|
gradio_basic_caption_gui_tab()
|
|
gradio_blip_caption_gui_tab()
|
|
gradio_git_caption_gui_tab()
|
|
gradio_wd14_caption_gui_tab()
|
|
gradio_convert_model_tab()
|
|
|
|
return (
|
|
train_data_dir_input,
|
|
reg_data_dir_input,
|
|
output_dir_input,
|
|
logging_dir_input,
|
|
)
|
|
|
|
|
|
def UI(username, password):
|
|
css = ''
|
|
|
|
if os.path.exists('./style.css'):
|
|
with open(os.path.join('./style.css'), 'r', encoding='utf8') as file:
|
|
print('Load CSS...')
|
|
css += file.read() + '\n'
|
|
|
|
interface = gr.Blocks(css=css)
|
|
|
|
with interface:
|
|
utilities_tab()
|
|
|
|
# Show the interface
|
|
if not username == '':
|
|
interface.launch(auth=(username, password))
|
|
else:
|
|
interface.launch()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# torch.cuda.set_per_process_memory_fraction(0.48)
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument(
|
|
'--username', type=str, default='', help='Username for authentication'
|
|
)
|
|
parser.add_argument(
|
|
'--password', type=str, default='', help='Password for authentication'
|
|
)
|
|
|
|
args = parser.parse_args()
|
|
|
|
UI(username=args.username, password=args.password)
|