Skip to content

Beginner's question #34

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
zhengrongw1013 opened this issue May 21, 2024 · 4 comments
Open

Beginner's question #34

zhengrongw1013 opened this issue May 21, 2024 · 4 comments

Comments

@zhengrongw1013
Copy link

Hello author,
Thank you for this great work. I am a beginner in diffusion model. Can I use my own trained model in your project?Currently, I only use diffusion_ffhq_10m and 256x256_diffusion_uncond.

@yuanzhi-zhu
Copy link
Owner

yes you can.
The diffusion model in our method is used to provide image prior, you can use your denoisers in other image domains, e.g, medical image restoration.

@zhengrongw1013
Copy link
Author

Thank you for your answer. If I want to train a model with my own face data set to use in your project, where can I train my data set? Can you point out a path for me?

@yuanzhi-zhu
Copy link
Owner

it is suggested to train a diffusion model using https://github.com/openai/guided-diffusion on your own data set, as our codebase is based on guided diffusion and utilizes the checkpoints from guided diffusion

@zhengrongw1013
Copy link
Author

Thanks for your quick answer. I'll try.

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