Your Name
6686e7fd18
[feat] enable taylor cache
2025-06-04 10:39:21 +00:00
zc8gerard
feba2a62c8
Merge pull request #6 from songruizz/release_0.0.3
...
fix incorrect FA3 usage when both have FA and FA3 package with non-Hopper GPU
2025-05-30 00:28:33 +08:00
songruizz
2281955f45
fix incorrect FA3 usage when both have FA and FA3 package with non-Hopper GPU
2025-05-29 23:48:06 +08:00
zc8gerard
4057dc55b3
Merge pull request #5 from songruizz/release_0.0.3
...
Using fa3 through option '--enable-fa3'
2025-05-29 16:27:09 +08:00
songruizz
15e4e0bdb8
Using fa3 through option '--enable-fa3'
2025-05-29 15:36:16 +08:00
zc8gerard
7ae8070fd9
Merge pull request #4 from songruizz/fix/FA3-duplicated-code
...
fix performance regression due to duplicated code
2025-05-27 16:21:46 +08:00
songrui.771
2fc28056fa
fix performance regression due to Flash Attention duplicated code
2025-05-27 16:14:07 +08:00
zc8gerard
3c7c6f8b29
Merge pull request #2 from bytedance-iaas/mul_device_teacache
...
[FEAT] support Mul device teacache
2025-05-26 21:59:27 +08:00
kousakawang
ed01a1e721
Merge branch 'release_0.0.3' into mul_device_teacache
2025-05-26 21:58:25 +08:00
zc8gerard
cce8316296
Merge pull request #3 from songruizz/feat/xdit-fa3
...
add support for Flash Attention 3 on multi-gpu inference
2025-05-26 21:11:34 +08:00
kousakawang
8bbcee625e
add teacache switch
2025-05-26 15:25:46 +08:00
kousakawang
3e209f8b45
[FEAT] enable multi-device teacache
2025-05-26 14:46:48 +08:00
songrui.771
4c35b3fd58
add support for FA3 on multi-gpu inference
2025-05-26 14:46:33 +08:00
zc8gerard
420963b7b5
Merge pull request #1 from bytedance-iaas/teacache_support
...
[Feat] Add teacache implement for Wan2.1
2025-05-23 21:30:34 +08:00
kousakawang
a11333634c
add teacache implement for Wan2.1
2025-05-23 19:15:52 +08:00
Shiwei Zhang
e5a741309d
Update README.md ( #406 )
2025-05-17 10:57:06 +08:00
Ang Wang
76e9427657
Format the code ( #402 )
...
* isort the code
* format the code
* Add yapf config file
* Remove torch cuda memory profiler
2025-05-16 12:35:38 +08:00
Zhen Han
c709fcf0e7
fix vace size ( #397 )
2025-05-14 22:01:45 +08:00
Ang Wang
18d53feb7a
[feature] Add VACE ( #389 )
...
* Add VACE
* Support training with multiple gpus
* Update default args for vace task
* vace block update
* Add vace exmaple jpg
* Fix dist vace fwd hook error
* Update vace exmample
* Update vace args
* Update pipeline name for vace
* vace gradio and Readme
* Update vace snake png
---------
Co-authored-by: hanzhn <han.feng.jason@gmail.com>
2025-05-14 20:44:25 +08:00
Shiwei Zhang
204f899b64
Update README.md
2025-04-22 15:10:03 +08:00
WanX-Video-1
397629b5f5
update readme
2025-04-22 11:11:57 +08:00
WanX-Video-1
d6aadd44cf
update community works
2025-04-22 10:50:21 +08:00
WanX-Video-1
325cfd41e6
update community works
2025-04-18 16:02:32 +08:00
yupeng1111
df44622e72
[feature] Wan2.1-FLF2V-14B ( #338 )
...
Co-authored-by: 澎鹏 <shiyupeng.syp@taobao.com>
2025-04-17 21:56:46 +08:00
WanX-Video-1
679ccc6c68
update community works
2025-04-02 18:00:23 +08:00
WanX-Video-1
82c6bf86e2
update readme
2025-03-29 18:09:59 +08:00
WanX-Video-1
d1f5144c26
add report
2025-03-28 14:46:31 +08:00
WanX-Video-1
b254e7b7a4
add report
2025-03-28 14:45:59 +08:00
jiangzeyinzi
d6434cf8ef
To support system prompt as a input parameter ( #280 )
2025-03-28 11:51:31 +08:00
Wenting Shen
bc3249d61c
add free stroage api for FSDP ( #277 )
...
Signed-off-by: wenting.swt <wenting.swt@alibaba-inc.com>
2025-03-26 15:49:37 +08:00
Ang Wang
11a6a00822
Add all py files in the subfolders under the "wan" directory through pattern matching ( #271 )
2025-03-24 17:23:42 +08:00
WanX-Video-1
a78d3be654
update link
2025-03-24 15:38:06 +08:00
WanX-Video-1
412b3e1643
add technical report
2025-03-21 17:51:31 +08:00
Ang Wang
9fb8845009
Add more explanation about the context parallel ( #260 )
2025-03-20 17:04:49 +08:00
gnebie
0f816057da
Add a pyproject and a separate INSTALL.md ( #137 )
...
* Add a pyproject and a detailled separate installation file with a poetry installation to not overcharge the readme
* update mail
2025-03-20 10:16:23 +08:00
Steven-SWZhang
b58b7c5737
update readme
2025-03-07 16:08:20 +08:00
Yingda Chen
d0a086800a
Update prompt_extend.py
2025-03-06 13:11:22 +08:00
Steven-SWZhang
d18cc1b397
update diffusers
2025-03-04 20:17:26 +08:00
Steven-SWZhang
1ccdcaee27
Merge branch 'main' of https://github.com/Wan-Video/Wan2.1
2025-03-04 17:43:12 +08:00
Steven-SWZhang
b11c960542
support diffusers
2025-03-04 17:42:50 +08:00
Chengxi Guo
5cb59ec52b
fix resolution if reload webpage ( #86 )
...
Signed-off-by: mymusise <mymusise1@gmail.com>
2025-03-04 16:41:03 +08:00
Chris Z
9d54043a67
Update README.md ( #167 )
...
change discord link to avoid expire
2025-03-04 16:39:37 +08:00
Alan May
82c18d91a1
fix: correct Chinese ISO language code typo ( #10 )
...
Fix incorrect Chinese language ISO code abbreviation
from CH to ZH
2025-03-03 17:04:13 +08:00
zyckk4
2ef4e2184e
Fix an error saving videos on Windows ( #128 )
2025-03-03 13:48:19 +08:00
Didier Durand
a326079926
Update README.md: fixing spelling errors / typos ( #88 )
...
Hi,
As title says: fixing some issues in the README text. See commit diff for all details.
Best,
Didier
2025-02-28 09:42:41 +08:00
章谨
6797c48002
update comfyui
2025-02-27 12:56:36 +08:00
Yingda Chen
190e928681
add modelscope download cli
2025-02-26 22:31:12 +08:00
WanX-Video
d7b01803de
update gradio ( #58 )
2025-02-26 20:33:18 +08:00
cocktailpeanut
89b065f4fe
os.path.sep instead of / ( #12 )
2025-02-26 18:57:30 +08:00
Adrian Corduneanu
0e3c42a830
Update text2video.py to reduce GPU memory by emptying cache ( #44 )
...
* Update text2video.py to reduce GPU memory by emptying cache
If offload_model is set, empty_cache() must be called after the model is moved to CPU to actually free the GPU. I verified on a RTX 4090 that without calling empty_cache the model remains in memory and the subsequent vae decoding never finishes.
* Update text2video.py only one empty_cache needed before vae decode
2025-02-26 18:56:57 +08:00
