Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-12-19 05:32:07 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Compare commits

base: Zengtudor:09327da6fa2274f31a72d00681f3856a57aa9e5c
Branches Tags
Zengtudor:main
Zengtudor:dev/format
...
compare: Zengtudor:9c498d513660743b227580e47bb8b72e7ca8e4e6
Branches Tags
Zengtudor:main
Zengtudor:dev/format

3 Commits
09327da6fa ... 9c498d5136

Author SHA1 Message Date
Dingkang Liang
9c498d5136
Merge 3677b69fb4 into 841fe5237b 2025-12-03 15:34:11 +08:00
Shiguang Ai
841fe5237b
When frame_num is changed from 81 the tensor does not match (#533) 2025-12-02 14:53:33 +08:00
dingkang
3677b69fb4 [Community Contribution] EasyCache 
Co-Authored-By: Xin Zhou <104890257+lmd0311@users.noreply.github.com>
 2025-07-14 11:44:05 +08:00
2 changed files with 2 additions and 1 deletions
Show Stats Expand all files Collapse all files

1
README.md
View File

@ -46,6 +46,7 @@ If your work has improved **Wan2.1** and you would like more people to see it, p
- [CFG-Zero](https://github.com/WeichenFan/CFG-Zero-star) enhances **Wan2.1** (covering both T2V and I2V models) from the perspective of CFG. - [CFG-Zero](https://github.com/WeichenFan/CFG-Zero-star) enhances **Wan2.1** (covering both T2V and I2V models) from the perspective of CFG.
- [TeaCache](https://github.com/ali-vilab/TeaCache) now supports **Wan2.1** acceleration, capable of increasing speed by approximately 2x. Feel free to give it a try! - [TeaCache](https://github.com/ali-vilab/TeaCache) now supports **Wan2.1** acceleration, capable of increasing speed by approximately 2x. Feel free to give it a try!
- [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) provides more support for **Wan2.1**, including video-to-video, FP8 quantization, VRAM optimization, LoRA training, and more. Please refer to [their examples](https://github.com/modelscope/DiffSynth-Studio/tree/main/examples/wanvideo). - [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) provides more support for **Wan2.1**, including video-to-video, FP8 quantization, VRAM optimization, LoRA training, and more. Please refer to [their examples](https://github.com/modelscope/DiffSynth-Studio/tree/main/examples/wanvideo).
- EasyCache (Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching): [EasyCache](https://github.com/H-EmbodVis/EasyCache) by [Dingkang Liang](https://github.com/dk-liang) and [Xin Zhou](https://github.com/LMD0311)
## 📑 Todo List ## 📑 Todo List

2
wan/image2video.py
View File

@ -207,7 +207,7 @@ class WanI2V:
generator=seed_g, generator=seed_g,
device=self.device) device=self.device)
msk = torch.ones(1, 81, lat_h, lat_w, device=self.device) msk = torch.ones(1, F, lat_h, lat_w, device=self.device)
msk[:, 1:] = 0 msk[:, 1:] = 0
msk = torch.concat([ msk = torch.concat([
torch.repeat_interleave(msk[:, 0:1], repeats=4, dim=1), msk[:, 1:] torch.repeat_interleave(msk[:, 0:1], repeats=4, dim=1), msk[:, 1:]