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
my test case for comfyui workflow is bad #52
Comments
Hi! It's a great ComfyUI Wrapper for Champ. But for the Semantic_map, we actually use a different ColorMap and different part segmentation. This "gap" may introduce severe artifacts for diffusion models. And I guess for this example, the normal map and pose predicted are severe, would you like to show them here? |
@Leoooo333 ok, the followings are the motion sequences: |
Hi there, thanks for your detailed description. It's a great ComfyUI Wrapper for Champ. But for the Semantic_map, we actually use a different ColorMap and different part segmentation. This "gap" may introduce severe artifacts for diffusion models. We are going to release our SMPL & Rendering code, which can solve this gap. |
How did you achieve these condition maps? I think there may be a large domain gap between these maps with ours (which are achieved by SMPL). |
@suqingkun 要不直接用中文沟通?我是根据你们的视频教程,跑出来的效果,所以不太清楚问题在哪里?https://www.youtube.com/watch?v=cbElsTBv2-A |
@zhouhualei hello 你好,这个comfyui有在README上面提到是unofficial的,所以是存在一点问题的,主要是semantic map那一块的color map以及part segmentation不同。你的例子中的motion人物小,动作太快,我看到产出的几个condition中在时间上不连续,伪影比较严重,这些是受到normal,depth预测网络能力的约束,而不是Champ的问题。建议您使用我们新发布的SMPL & Rendering里的教程去准备数据。 |
@Leoooo333 预处理的代码和教程已经发布了吗?看你们roadmap里好像delay了 |
之前发布之后对国内配置环境不太友好,就revert了。现在的这个版本正在PR中,你也可以直接fork这个branch:https://github.com/Leoooo333/champ/tree/feature/data_processors |
好的,我试试,感谢! |
here is my test image and video:
2s.mp4
and here is the result video:
Champ.mp4
So, what's the problem? is there any requirements for test data? Thanks
The text was updated successfully, but these errors were encountered: