Commit Graph

2438 Commits

Author SHA1 Message Date
Kohya S
b090d15f7d feat: add multi backend attention and related update for HI2.1 models and scripts 2025-09-20 19:45:33 +09:00
Kohya S
f834b2e0d4 fix: --fp8_vl to work 2025-09-18 23:46:18 +09:00
Kohya S
f6b4bdc83f feat: block-wise fp8 quantization 2025-09-18 21:20:54 +09:00
Kohya S
2ce506e187 fix: fp8 casting not working 2025-09-18 21:20:08 +09:00
Kohya S
f5b004009e fix: correct tensor indexing in HunyuanVAE2D class for blending and encoding functions 2025-09-17 21:54:25 +09:00
Kohya S
cbe2a9da45 feat: add conversion script for LoRA models to ComfyUI format with reverse option 2025-09-16 21:48:47 +09:00
kohya-ss
f318ddaeea docs: update HunyuanImage-2.1 training guide with model download instructions and VRAM optimization settings (by Claude) 2025-09-16 21:18:01 +09:00
kohya-ss
39458ec0e3 fix: update default values for guidance_scale, image_size, infer_steps, and flow_shift in argument parser 2025-09-16 21:17:21 +09:00
Kohya S
2732be0b29 Merge branch 'feat-hunyuan-image-2.1-inference' of https://github.com/kohya-ss/sd-scripts into feat-hunyuan-image-2.1-inference 2025-09-14 20:49:24 +09:00
Kohya S
1a73b5e8a5 feat: add script to convert LoRA format to ComfyUI format 2025-09-14 20:49:20 +09:00
kohya-ss
e04b9f0497 docs: add LoRA training guide for HunyuanImage-2.1 model (by Gemini CLI) 2025-09-13 22:06:10 +09:00
Kohya S
29b0500e70 fix: restore files section in _typos.toml for exclusion configuration 2025-09-13 21:18:50 +09:00
Kohya S
4e2a80a6ca refactor: update imports to use safetensors_utils for memory-efficient operations 2025-09-13 21:07:11 +09:00
Kohya S
d831c88832 fix: sample generation doesn't work with block swap 2025-09-13 21:06:04 +09:00
Kohya S
bae7fa74eb Merge branch 'sd3' into feat-hunyuan-image-2.1-inference 2025-09-13 20:13:58 +09:00
Kohya S.
f5d44fd487 Merge pull request #2200 from kohya-ss/feat-faster-safetensors-load
feat: Speeding up loading .safetensors files
2025-09-13 20:09:03 +09:00
Kohya S
4568631b43 docs: update README to reflect improved loading speed of .safetensors files 2025-09-13 20:05:39 +09:00
Kohya S.
e1c666e97f Update library/safetensors_utils.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-09-13 20:03:55 +09:00
Kohya S
8783f8aed3 feat: faster safetensors load and split safetensor utils 2025-09-13 19:51:38 +09:00
Kohya S
9a61d61b22 feat: avoid unet type casting when fp8_scaled 2025-09-12 22:18:29 +09:00
Kohya S
7a651efd4d feat: add 'tak' to recognized words and update block swap method to support backward pass 2025-09-12 22:00:41 +09:00
Kohya S
aa0af24d01 Merge branch 'sd3' into feat-hunyuan-image-2.1-inference 2025-09-12 21:41:12 +09:00
Kohya S
209c02dbb6 feat: HunyuanImage LoRA training 2025-09-12 21:40:42 +09:00
Kohya S.
419a9c4af4 Merge pull request #2192 from kohya-ss/doc-update-for-latest-features
Doc update for latest features
2025-09-12 20:28:42 +09:00
Kohya S
cbc9e1a3b1 feat: add byt5 to the list of recognized words in typos configuration 2025-09-11 22:27:08 +09:00
Kohya S
a0f0afbb46 fix: revert constructor signature update 2025-09-11 22:27:00 +09:00
Kohya S
7f983c558d feat: block swap for inference and initial impl for HunyuanImage LoRA (not working) 2025-09-11 22:15:22 +09:00
Kohya S
5149be5a87 feat: initial commit for HunyuanImage-2.1 inference 2025-09-11 12:54:12 +09:00
kohya-ss
ee8e670765 Merge branch 'sd3' into doc-update-for-latest-features 2025-09-09 12:42:09 +09:00
Kohya S.
f8337726cf Merge pull request #2196 from rockerBOO/validation-dataset-subset
Fix validation dataset documentation to not use subsets
2025-09-09 12:38:23 +09:00
rockerBOO
fe4c18934c blocks_to_swap is supported for validation loss now 2025-09-08 14:28:55 -04:00
rockerBOO
78685b9c5f Move general settings to top to make more clear the validation bits 2025-09-08 14:18:50 -04:00
rockerBOO
ef4397963b Fix validation dataset documentation to not use subsets 2025-09-08 14:16:33 -04:00
kohya-ss
0bb0d91615 doc: update introduction and clarify command line option priorities in config README 2025-09-06 19:52:54 +09:00
Kohya S.
952f9ce7be Update docs/train_textual_inversion.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-09-04 19:46:04 +09:00
kohya-ss
884fc8c7f5 doc: remove SD3/FLUX.1 training guide 2025-09-04 18:40:21 +09:00
kohya-ss
ddfb38e501 doc: add documentation for Textual Inversion training scripts 2025-09-04 18:39:52 +09:00
kohya-ss
6c82327dc8 doc: remove Japanese section on Gradual Latent options from gen_img README 2025-09-01 21:32:50 +09:00
kohya-ss
9984868154 doc: update README to include support for SDXL models and additional command-line options for gen_img.py 2025-09-01 21:32:24 +09:00
kohya-ss
142d0be180 doc: add comprehensive fine-tuning guide for various model architectures 2025-09-01 12:36:51 +09:00
kohya-ss
c38b07d0da doc: add validation loss documentation for model training 2025-08-31 21:39:47 +09:00
kohya-ss
80710134d5 doc: add Sage Attention and sample batch size options to Lumina training guide 2025-08-31 21:19:28 +09:00
kohya-ss
fe81d40202 doc: refactor structure for improved readability and maintainability 2025-08-31 21:14:45 +09:00
kohya-ss
989448afdd doc: enhance SD3/SDXL LoRA training guide 2025-08-31 19:19:10 +09:00
Kohya S.
884e07d73e Merge pull request #2191 from kohya-ss/fix-chroma-training-withtout-te-cache
fix: chroma LoRA training without Text Encode caching
2025-08-30 09:31:11 +09:00
Kohya S
e836b7f66d fix: chroma LoRA training without Text Encode caching 2025-08-30 09:30:24 +09:00
Kohya S.
8cadec68bb Merge pull request #2178 from kohya-ss/update-libraries
Feat: Update libraries, remove warnings
2025-08-28 08:42:53 +09:00
Kohya S
5a5138d0ab doc: add PR reference for PyTorch and library versions update 2025-08-28 08:38:14 +09:00
Kohya S
c52c45cd7a doc: update for PyTorch and libraries versions 2025-08-28 08:36:09 +09:00
Kohya S
ac72cf88a7 feat: remove bitsandbytes version specification in requirements.txt 2025-08-28 08:35:40 +09:00