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

SCEdit Controllable SC-Tuner semantic segmentation checkpoint, training code and configuration #8

Closed
XIRZC opened this issue Mar 11, 2024 · 2 comments

Comments

@XIRZC
Copy link

XIRZC commented Mar 11, 2024

Thank you for your outstanding work and contributions!

I've reviewed the released paper, which includes impressive results on semantic segmentation map-based conditional generation. However, upon visiting the Scepter modelscope link (https://modelscope.cn/models/iic/scepter_scedit/files), I couldn't find any models specifically focused on semantic segmentation map-based conditional generation.

I'm curious to know why this particular model hasn't been released yet. Additionally, I'm wondering if there are plans to release the code and configuration for training semantic segmentation map-based conditional generation models. Your insights on this matter would be greatly appreciated.

@jiangzeyinzi
Copy link
Collaborator

SCEdit is currently integrated into the SCEPTER framework, and to maintain the simplicity of the framework, we have not introduced a heavy code for segmentation models. Segmentation-based control can be easily trained, and one can refer to other conditional methods for the data organization and training.

@XIRZC
Copy link
Author

XIRZC commented Mar 21, 2024

Thanks.

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