theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:32:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
831 Commits 36 Branches 11 Tags
a36f2f6032d8b3d97ac2aa723c372eba0e5a43b3
Commit Graph

831 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Artiprocher
a36f2f6032 support wan2.2-animate-14b 2025-09-30 12:45:56 +08:00
Zhongjie Duan
0d6de58af9 Merge pull request #949 from modelscope/qwen-image-edit-multi 
update qwen-image-edit training script
 2025-09-25 11:07:38 +08:00
Artiprocher
acbf932974 update qwen-image-edit training script 2025-09-25 11:07:01 +08:00
Zhongjie Duan
0b4b337e9a Merge pull request #933 from lzws/main 
update wan2.2-VACE-Fun-A14B
 2025-09-24 09:56:37 +08:00
Zhongjie Duan
99908d9a1c Merge pull request #940 from mi804/eligen_poster 
support eligen-poster
 2025-09-23 17:49:37 +08:00
mi804
73ced7a46d support eligen-poster 2025-09-23 17:41:48 +08:00
Zhongjie Duan
32b8b9b51e Merge pull request #910 from ldiex/main 
Fix gradient checkpointing in WAN VACE blocks
 2025-09-23 12:23:12 +08:00
Zhongjie Duan
f6534a5b63 Merge pull request #909 from huarzone/fix_bug 
fix load gif
 2025-09-23 12:22:00 +08:00
Zhongjie Duan
034c9b6c60 Qwen-Image-Edit-2509 (#937) 
* qwen-image-edit-2509
 2025-09-22 20:37:11 +08:00
lzws
76335e0fe5 uodate wan2.2-VACE-Fun 2025-09-22 02:14:20 +08:00
lzws
c0b589d934 add wan2.2-VACE-Fun infereance and trining 2025-09-22 01:57:05 +08:00
Zhongjie Duan
833ba1e1fa update vram management strategy (#929) 2025-09-18 16:53:13 +08:00
Artiprocher
7a5974d964 update vram management strategy 2025-09-18 16:51:53 +08:00
Zhongjie Duan
b0abdaffb4 Qwen image split training Bug Fix (#926) 
* bugfix
 2025-09-17 20:53:46 +08:00
Zhongjie Duan
e9f29bc402 Merge pull request #921 from modelscope/qwen-image-distill-dmd2-lora 
support qwen-image-distill-dmd2-lora
 2025-09-16 19:43:59 +08:00
Artiprocher
1a7f482fbd support qwen-image-distill-dmd2-lora 2025-09-16 19:43:07 +08:00
Tianlin Pan
3a0d51d100 Fix gradient checkpointing in WAN VACE blocks 2025-09-14 16:21:46 +08:00
Kared
bffdb901ed fix load gif 2025-09-13 21:01:44 +08:00
Zhongjie Duan
d93e8738cd Merge pull request #902 from xycdx/feature/improve-fastblend 
add torch implementation for interpolation
 2025-09-11 11:45:55 +08:00
xycdx
7e5ce5d5c9 Update diffsynth/extensions/FastBlend/patch_match.py 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-09-10 20:48:54 +08:00
xycdx
7aef554d83 add torch implementation for interpolation 
- Implement bilinear interpolation kernel using Numba
- Benchmark shows 2x speedup compared to CPU version
- Closes #817
 2025-09-10 20:39:35 +08:00
Zhongjie Duan
090074e395 Merge pull request #899 from modelscope/version_update_1.1.8 
Update setup.py
v1.1.8 		2025-09-09 18:43:03 +08:00
Zhongjie Duan
2dcdeefca8 Update setup.py 2025-09-09 18:42:39 +08:00
Zhongjie Duan
452a6ca5cf Merge pull request #898 from modelscope/direct_distill 
support direct distill
 2025-09-09 16:16:32 +08:00
Artiprocher
d6cf20ef33 support direct distill 2025-09-09 16:12:31 +08:00
Zhongjie Duan
efdd6a59b6 Merge pull request #892 from modelscope/dev2-dzj 
refine training framework
 2025-09-04 15:53:52 +08:00
Artiprocher
42ec7b08eb bugfix 2025-09-04 15:45:39 +08:00
Artiprocher
d049fb6d1d bugfix 2025-09-04 15:44:37 +08:00
Artiprocher
144365b07d merge data process to training script 2025-09-04 15:18:56 +08:00
Artiprocher
cb8de6be1b move training code to base trainer 2025-09-03 12:03:49 +08:00
Zhongjie Duan
8c13362dcf Merge pull request #884 from modelscope/dev2-dzj 
Unified Dataset & Splited Training
 2025-09-03 09:50:23 +08:00
Zhongjie Duan
c13fd7e0ee Merge pull request #877 from mi804/wans2v_framepack 
support s2v framepack
 2025-09-02 16:54:37 +08:00
Artiprocher
958ebf1352 remove testing script 2025-09-02 16:44:36 +08:00
Artiprocher
b6da77e468 qwen-image splited training 2025-09-02 16:44:14 +08:00
Artiprocher
260e32217f unified dataset 2025-09-02 13:14:08 +08:00
mi804
5cee326f92 support s2v framepack 2025-09-01 16:48:46 +08:00
Zhongjie Duan
1d240994e7 Merge pull request #874 from mi804/wans2v_example 
Wans2v example
 2025-08-29 15:13:28 +08:00
mi804
a0bae07825 add wans2v example 2025-08-29 15:11:30 +08:00
ShunqiangBian
ff71720297 Create Wan2.2-S2V-14B.py 
This commit introduces the core inference functionality for the Wan2.2-S2V-14B model.
 2025-08-29 14:54:41 +08:00
Zhongjie Duan
dea85643e6 Merge pull request #872 from modelscope/dev2-dzj 
remove some requirements & update Qwen-Image Quickstart
 2025-08-29 14:22:35 +08:00
Artiprocher
6a46f32afe update Qwen-Image Quickstart 2025-08-29 14:09:49 +08:00
Artiprocher
4641d0f360 remove some requirements 2025-08-29 14:04:58 +08:00
Zhongjie Duan
826bab5962 Merge pull request #859 from krahets/main 
Fix batch decoding for Wan-Video-VAE
 2025-08-29 12:45:49 +08:00
Zhongjie Duan
5b6d112c15 Merge pull request #843 from wuutiing/main 
add read gifs as video support
 2025-08-29 12:36:24 +08:00
Zhongjie Duan
febdaf6067 Merge pull request #856 from lzws/main 
add wan2.2-fun training scripts
 2025-08-29 12:34:55 +08:00
Zhongjie Duan
0a78bb9d38 Merge pull request #864 from modelscope/wans2v 
Support Wan-S2V
 2025-08-28 10:21:12 +08:00
mi804
9cea10cc69 minor fix 2025-08-28 10:13:52 +08:00
mi804
caa17da5b9 wans2v readme 2025-08-27 20:05:44 +08:00
mi804
fdeb363fa2 wans2v usp 2025-08-27 19:50:33 +08:00
mi804
4147473c81 wans2v refactor 2025-08-27 16:18:22 +08:00