Commit Graph

13 Commits

Author SHA1 Message Date
JSTayco
7b5639cff5 Huge WIP
This is a massive WIP and should not be trusted or used right now. However, major milestones have been crossed. Both message boxes and file dialogs are now properly subprocessed and work on macOS. I think by extension, it may work on runpod environments as well, but that remains to be tested.
2023-03-30 01:40:00 -07:00
bmaltais
f83638b8a6 Add device support 2023-03-22 12:55:30 -04:00
bmaltais
ccae80186a Update to latest sd-script code 2023-03-20 08:47:00 -04:00
bmaltais
2deddd5f3c Update to sd-script latest update 2023-03-09 11:06:59 -05:00
bmaltais
2e47a45e3f Change how subprocess is run 2023-03-05 11:43:59 -05:00
bmaltais
3beeef4414 Add linux support 2023-03-04 18:56:22 -05:00
devdn
129cd5f97d Revert "fix paths with spaces"
This reverts commit 7af9e48d30.
2023-03-04 17:13:02 -05:00
devdn
7af9e48d30 fix paths with spaces 2023-03-04 00:39:34 -05:00
devdn
bc45bd7e70 fix bugs that make some processes not work on linux 2023-03-04 00:11:23 -05:00
bmaltais
5498539fda Fix typos 2023-03-01 19:20:05 -05:00
bmaltais
cbfc311687 Integrate new bucket parameters in GUI 2023-02-05 20:07:00 -05:00
bmaltais
045750b46a v20.6.0
- 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.
2023-02-04 08:36:35 -05:00
bmaltais
34f7cd8e57 Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00