Skip to content
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

Janus problem #27

Open
zhou431496 opened this issue Mar 16, 2024 · 2 comments
Open

Janus problem #27

zhou431496 opened this issue Mar 16, 2024 · 2 comments

Comments

@zhou431496
Copy link

Janus problem is serious
image

@lingtengqiu
Copy link
Collaborator

What is your prompt?
And, what is your config setting? NeRF, Or DMTet;
General Speaking, if MV-ND produce multi-face results, the results prone to suffer from Janue problem. I suggest sampling MV-nd images before 3D generation.
Thank you for the information on the failure case

@zhou431496
Copy link
Author

就是输入的勒布朗. 詹姆斯,其他是默认的。我想知道文本到图像的扩散模型如何微调到文本到normal 和depth的扩散模型。能告诉我们相关代码,谢谢。并且normal和纹理并没有对齐,是否存在fake 3D detail问题。期待你的回复

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