Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-06-17 12:57:40 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Compare commits

base: Zengtudor:bc8732ee9250d010c818a983091fe93211f01cc2
Branches Tags
Zengtudor:main
Zengtudor:dev/format
Zengtudor:dev/vace_seed
Zengtudor:dev/vace_dev
Zengtudor:dev/vace_size
Zengtudor:dev/vace
...
compare: Zengtudor:b0facc54b467b8aa5594e29b36f0412e42b849c1
Branches Tags
Zengtudor:main
Zengtudor:dev/format
Zengtudor:dev/vace_seed
Zengtudor:dev/vace_dev
Zengtudor:dev/vace_size
Zengtudor:dev/vace

3 Commits
bc8732ee92 ... b0facc54b4

Author SHA1 Message Date
Feiteng
b0facc54b4
Merge 57843a2111 into 827906c30f 2025-06-05 10:03:29 +08:00
Shiwei Zhang
827906c30f
Update README.md 2025-06-05 10:02:00 +08:00
Feiteng
57843a2111 Fix msk frame_num 2025-05-09 07:41:18 +00:00
2 changed files with 2 additions and 1 deletions
Show Stats Expand all files Collapse all files

1
README.md
View File

@ -36,6 +36,7 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid
## Community Works ## Community Works
If your work has improved **Wan2.1** and you would like more people to see it, please inform us. If your work has improved **Wan2.1** and you would like more people to see it, please inform us.
- [ATI](https://github.com/bytedance/ATI), built on **Wan2.1-I2V-14B**, is a trajectory-based motion-control framework that unifies object, local, and camera movements in video generation. Refer to [their website](https://anytraj.github.io/) for more examples.
- [Phantom](https://github.com/Phantom-video/Phantom) has developed a unified video generation framework for single and multi-subject references based on both **Wan2.1-T2V-1.3B** and **Wan2.1-T2V-14B**. Please refer to [their examples](https://github.com/Phantom-video/Phantom). - [Phantom](https://github.com/Phantom-video/Phantom) has developed a unified video generation framework for single and multi-subject references based on both **Wan2.1-T2V-1.3B** and **Wan2.1-T2V-14B**. Please refer to [their examples](https://github.com/Phantom-video/Phantom).
- [UniAnimate-DiT](https://github.com/ali-vilab/UniAnimate-DiT), based on **Wan2.1-14B-I2V**, has trained a Human image animation model and has open-sourced the inference and training code. Feel free to enjoy it! - [UniAnimate-DiT](https://github.com/ali-vilab/UniAnimate-DiT), based on **Wan2.1-14B-I2V**, has trained a Human image animation model and has open-sourced the inference and training code. Feel free to enjoy it!
- [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.

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, frame_num, 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:]