Merge pull request #189 from bmaltais/LR-Free
bmaltais
2023-02-17 19:18:39 -0500
674ed88d13* 2023/02/16 (v20.7.3) - Noise offset is recorded to the metadata. Thanks to space-nuko! - Show the moving average loss to prevent loss jumping in train_network.py and train_db.py. Thanks to shirayu!
bmaltais
2023-02-17 19:18:11 -0500
f9863e3950add dadapation to other trainers
bmaltais
2023-02-16 19:33:46 -0500
655f885cf4Add dadapation to other trainers
bmaltais
2023-02-16 19:33:33 -0500
641a168e55Integrate new kohya sd-script
bmaltais
2023-02-14 18:52:08 -0500
Merge pull request #147 from bmaltais/dev
bmaltais
2023-02-11 12:00:17 -0500
a49fb9cb8c2023/02/11 (v20.7.2): - `lora_interrogator.py is added in networks folder. See python networks\lora_interrogator.py -h for usage. - For LoRAs where the activation word is unknown, this script compares the output of Text Encoder after applying LoRA to that of unapplied to find out which token is affected by LoRA. Hopefully you can figure out the activation word. LoRA trained with captions does not seem to be able to interrogate. - Batch size can be large (like 64 or 128). - train_textual_inversion.py` now supports multiple init words. - Following feature is reverted to be the same as before. Sorry for confusion: > Now the number of data in each batch is limited to the number of actual images (not duplicated). Because a certain bucket may contain smaller number of actual images, so the batch may contain same (duplicated) images. - Add new tool to sort, group and average crop image in a dataset
bmaltais
2023-02-11 11:59:38 -0500
e5f8ba559fAdd server_port and inbrowser support - to all gui scripts
bmaltais
2023-02-10 08:22:03 -0500
Merge pull request #138 from bmaltais/dev
bmaltais
2023-02-09 19:18:08 -0500
7bc93821a02023/02/09 (v20.7.1) - Caption dropout is supported in `train_db.py, fine_tune.py and train_network.py. Thanks to forestsource! - --caption_dropout_rate option specifies the dropout rate for captions (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the image is trained with the empty caption. Default is 0 (no dropout). - --caption_dropout_every_n_epochs option specifies how many epochs to drop captions. If 3 is specified, in epoch 3, 6, 9 ..., images are trained with all captions empty. Default is None (no dropout). - --caption_tag_dropout_rate option specified the dropout rate for tags (comma separated tokens) (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the tag is removed from the caption. If --keep_tokens option is set, these tokens (tags) are not dropped. Default is 0 (no droupout). - The bulk image downsampling script is added. Documentation is [here](https://github.com/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md#%E7%94%BB%E5%83%8F%E3%83%AA%E3%82%B5%E3%82%A4%E3%82%BA%E3%82%B9%E3%82%AF%E3%83%AA%E3%83%97%E3%83%88) (in Jpanaese). Thanks to bmaltais! - Typo check is added. Thanks to shirayu! - Add option to autolaunch the GUI in a browser and set the server_port. USe either gui.ps1 --inbrowser --server_port 3456or gui.cmd -inbrowser -server_port 3456`
bmaltais
2023-02-09 19:17:24 -0500
90c0d554572023/02/09 (v20.7.1) - Caption dropout is supported in `train_db.py, fine_tune.py and train_network.py. Thanks to forestsource! - --caption_dropout_rate option specifies the dropout rate for captions (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the image is trained with the empty caption. Default is 0 (no dropout). - --caption_dropout_every_n_epochs option specifies how many epochs to drop captions. If 3 is specified, in epoch 3, 6, 9 ..., images are trained with all captions empty. Default is None (no dropout). - --caption_tag_dropout_rate option specified the dropout rate for tags (comma separated tokens) (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the tag is removed from the caption. If --keep_tokens option is set, these tokens (tags) are not dropped. Default is 0 (no droupout). - The bulk image downsampling script is added. Documentation is [here](https://github.com/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md#%E7%94%BB%E5%83%8F%E3%83%AA%E3%82%B5%E3%82%A4%E3%82%BA%E3%82%B9%E3%82%AF%E3%83%AA%E3%83%97%E3%83%88) (in Jpanaese). Thanks to bmaltais! - Typo check is added. Thanks to shirayu! - Add option to autolaunch the GUI in a browser and set the server_port. USe either gui.ps1 --inbrowser --server_port 3456or gui.cmd -inbrowser -server_port 3456`
bmaltais
2023-02-09 19:17:17 -0500
Merge pull request #118 from bmaltais/dev
bmaltais
2023-02-06 11:04:55 -0500
8d559ded18* 2023/02/06 (v20.7.0) - `--bucket_reso_steps and --bucket_no_upscale options are added to training scripts (fine tuning, DreamBooth, LoRA and Textual Inversion) and prepare_buckets_latents.py. - --bucket_reso_steps takes the steps for buckets in aspect ratio bucketing. Default is 64, same as before. - Any value greater than or equal to 1 can be specified; 64 is highly recommended and a value divisible by 8 is recommended. - If less than 64 is specified, padding will occur within U-Net. The result is unknown. - If you specify a value that is not divisible by 8, it will be truncated to divisible by 8 inside VAE, because the size of the latent is 1/8 of the image size. - If --bucket_no_upscale option is specified, images smaller than the bucket size will be processed without upscaling. - Internally, a bucket smaller than the image size is created (for example, if the image is 300x300 and bucket_reso_steps=64, the bucket is 256x256). The image will be trimmed. - Implementation of [#130](https://github.com/kohya-ss/sd-scripts/issues/130). - Images with an area larger than the maximum size specified by --resolution are downsampled to the max bucket size. - Now the number of data in each batch is limited to the number of actual images (not duplicated). Because a certain bucket may contain smaller number of actual images, so the batch may contain same (duplicated) images. - --random_crop` now also works with buckets enabled. - Instead of always cropping the center of the image, the image is shifted left, right, up, and down to be used as the training data. This is expected to train to the edges of the image. - Implementation of discussion [#34](https://github.com/kohya-ss/sd-scripts/discussions/34).
bmaltais
2023-02-06 11:04:07 -0500
cbfc311687Integrate new bucket parameters in GUI
bmaltais
2023-02-05 20:07:00 -0500
2486af9903Update to latest dev code of kohya_s. WIP
bmaltais
2023-02-05 14:16:53 -0500
Merge pull request #105 from bmaltais/dev
bmaltais
2023-02-04 08:37:25 -0500
045750b46av20.6.0 - 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.
bmaltais
2023-02-04 08:36:35 -0500
20e62af1a6Update to latest kohya_ss sd-script code
bmaltais
2023-02-03 14:40:03 -0500
Merge pull request #74 from bmaltais/dev
bmaltais
2023-01-26 16:23:46 -0500
03bd2e9b01Add TI training support
bmaltais
2023-01-26 16:22:58 -0500
49bada0d25Update default save model file format to safetensors
bmaltais
2023-01-22 18:21:09 -0500
511361c80b- Add new tool to verify LoRA weights produced by the trainer. Can be found under "Dreambooth LoRA/Tools/Verify LoRA
bmaltais
2023-01-22 11:40:14 -0500
bmaltais