theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:48:12 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,104 Commits 36 Branches 11 Tags
dev
Commit Graph

525 Commits

Author SHA1 Message Date
feng0w0
6be244233a [model][NPU]:Wan model rope use torch.complex64 in NPU 2026-01-12 11:34:41 +08:00
Feng
f4d06ce3fc Merge branch 'modelscope:main' into wan_rope 2026-01-12 11:21:09 +08:00
Zhongjie Duan
381067515c Merge pull request #1176 from Feng0w0/z-image-rope 
[model][NPU]: Z-image model support NPU
 2026-01-12 10:11:22 +08:00
Zhongjie Duan
00f2d1aa5d Merge pull request #1169 from Feng0w0/sample_add 
Docs:Supplement NPU training script samples and documentation instruction
 2026-01-12 10:08:38 +08:00
feng0w0
3b662da31e [model][NPU]:Wan model rope use torch.complex64 in NPU 2026-01-09 18:11:40 +08:00
feng0w0
19ce3048c1 [model][NPU]:Wan model rope use torch.complex64 in NPU 2026-01-09 18:06:41 +08:00
Zhongjie Duan
0efab85674 Support Z-Image-Omni-Base and its related models 
Support Z-Image-Omni-Base and its related models.
 2026-01-08 13:43:59 +08:00
Artiprocher
f45a0ffd02 support z-image-omni-base vram management 2026-01-08 13:41:00 +08:00
Artiprocher
8ba528a8f6 bugfix 2026-01-08 13:21:33 +08:00
Artiprocher
dd479e5bff support z-image-omni-base-i2L 2026-01-07 20:36:53 +08:00
Artiprocher
bac39b1cd2 support z-image controlnet 2026-01-07 15:56:53 +08:00
feng0w0
c1c9a4853b [model][NPU]:Z-image model support NPU 2026-01-07 11:42:19 +08:00
feng0w0
3ee5f53a36 [model][NPU]:Z-image model support NPU 2026-01-07 11:31:22 +08:00
Artiprocher
32449a6aa0 support z-image-omni-base training 2026-01-05 20:04:00 +08:00
Zhongjie Duan
a6884f6b3a Merge pull request #1171 from YZBPXX/main 
Fix issue where LoRa loads on a device different from Dit
 2026-01-05 16:39:02 +08:00
Artiprocher
7604ca1e52 flux compatibility patch 2026-01-05 16:04:20 +08:00
Artiprocher
5745c9f200 support z-image-omni-base 2026-01-05 14:45:01 +08:00
yaozhengbing
60ac96525b Fix issue where LoRa loads on a device different from Dit 2025-12-31 21:31:01 +08:00
feng0w0
507e7e5d36 Docs:Supplement NPU training script samples and documentation instruction 2025-12-30 19:58:47 +08:00
Artiprocher
20e1aaf908 bugfix 2025-12-20 14:00:22 +08:00
Artiprocher
c6722b3f56 support qwen-image-layered 2025-12-19 19:06:37 +08:00
Artiprocher
4629d4cf9e support qwen-image-edit-2511 2025-12-18 19:16:52 +08:00
Artiprocher
1547c3f786 bugfix 2025-12-16 16:09:29 +08:00
Zhongjie Duan
bfaaf12bf4 Merge pull request #1129 from modelscope/ascend 
Support Ascend NPU
 2025-12-15 19:13:40 +08:00
Artiprocher
2883bc1b76 support ascend npu 2025-12-15 15:48:42 +08:00
Junming Chen
127cc9007a Fixed: S2V Long video severe quality downgrade 2025-12-14 20:30:34 +00:00
Artiprocher
64c5139502 revert FluxLoRAConverter due to dependency issues 2025-12-12 17:19:13 +08:00
Artiprocher
864080d8f2 fix typo 2025-12-09 22:29:50 +08:00
Artiprocher
30f93161fb support i2L 2025-12-09 22:07:35 +08:00
root
72af7122b3 DiffSynth-Studio 2.0 major update 2025-12-04 16:33:07 +08:00
Artiprocher
1313f4dd63 support downloading resource 2025-11-18 10:29:07 +08:00
Zhongjie Duan
8332ecebb7 Merge pull request #1034 from modelscope/video_as_prompt 
Video as prompt
 2025-11-04 17:32:50 +08:00
Yudong Jin
b8d7d55568 Fix dtype issue in time embedding calculation 2025-11-01 03:11:03 +08:00
Artiprocher
b73e713028 support LongCat-Video 2025-10-30 13:38:14 +08:00
yjy415
e0eabaa426 Krea realtime video (#1011) 
* krea-realtime-video

* Add Krea real-time video inference and training support

* Delete .gitignore

* update README

* update README

---------

Co-authored-by: Artiprocher <wangye87v5@hotmail.com>
Co-authored-by: Jintao Huang <huangjintao.hjt@alibaba-inc.com>
Co-authored-by: Zhongjie Duan <35051019+Artiprocher@users.noreply.github.com>
 2025-10-27 19:09:28 +08:00
lzws
30292d9411 update wan2.2-S2V training 2025-10-21 19:59:44 +08:00
lzws
8ea45b0daa update wans2v training 2025-10-21 10:34:48 +08:00
Artiprocher
77fac2a03f bugfix 2025-10-10 15:41:39 +08:00
Artiprocher
c63d474b60 fix bug in issue 953 2025-09-30 12:59:44 +08:00
Zhongjie Duan
c5d426c254 Merge branch 'main' into wan-animate 2025-09-30 12:56:28 +08:00
Artiprocher
a36f2f6032 support wan2.2-animate-14b 2025-09-30 12:45:56 +08:00
lzws
ed256ef8be fix wan vace bug (#960) 
* fix wan vace bug
 2025-09-26 13:49:27 +08:00
Zhongjie Duan
e9bc42f233 Update wan_video_new.py 2025-09-25 15:34:09 +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
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
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