Skip to content

关于 inpainting + pose无法正常生成 & 如何区分不同任务 的一些疑问 #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
viakai opened this issue Apr 12, 2025 · 1 comment

Comments

@viakai
Copy link

viakai commented Apr 12, 2025

您好,非常感谢开源这样一个高质量的模型与代码。我在使用 Preview 模型进行多种条件视频生成任务时遇到了一些问题,想请教一下:

请问目前开源的 Preview 模型是否尚不支持同时结合 Inpainting 和 Pose 的视频生成?我在实际测试中发现,只要在 Pose 条件下使用非全 1 的 mask,模型似乎就无法正常生成。

另外,我在阅读代码时注意到,VACE 并未使用 task embedding 等机制来显式区分不同任务。这是否意味着 VACE 是通过输入的 Video Condition Unit 的内容来隐式识别和区分任务类型的?

期待您的解答,再次感谢您们的工作!

@hanzhn
Copy link
Collaborator

hanzhn commented Apr 12, 2025

  1. Sure VACE supports Inpainting + pose. You can refer to the case about Inpainting + control task.

  2. Exactly, yes. VACE implicitly interprets the user intentions fully based on src_video, src_mask, src_ref_images and prompt.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants