Compare commits

...

3 Commits

Author SHA1 Message Date
Jeremy Jin-Young Kim
93a77f0130
Merge 76bceb2fe5 into 8f7f6514f1 2025-06-18 14:21:15 +08:00
Shiwei Zhang
8f7f6514f1
Update README.md 2025-06-13 14:15:30 +08:00
root
76bceb2fe5 fix: enalbe prompt extend for flf2v 2025-05-02 05:10:43 +00:00
2 changed files with 3 additions and 1 deletions

View File

@ -36,6 +36,8 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid
## Community Works
If your work has improved **Wan2.1** and you would like more people to see it, please inform us.
- [HyperMotion](https://vivocameraresearch.github.io/hypermotion/), a human image animation framework based on **Wan2.1**, addresses the challenge of generating complex human body motions in pose-guided animation. Refer to [their website](https://vivocameraresearch.github.io/magictryon/) for more examples.
- [MagicTryOn](https://vivocameraresearch.github.io/magictryon/), a video virtual try-on framework built upon **Wan2.1-14B-I2V**, addresses the limitations of existing models in expressing garment details and maintaining dynamic stability during human motion. Refer to [their website](https://vivocameraresearch.github.io/magictryon/) for more examples.
- [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).
- [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!

View File

@ -312,7 +312,7 @@ def generate(args):
elif args.prompt_extend_method == "local_qwen":
prompt_expander = QwenPromptExpander(
model_name=args.prompt_extend_model,
is_vl="i2v" in args.task,
is_vl="i2v" in args.task or "flf2v" in args.task,
device=rank)
else:
raise NotImplementedError(