-
Notifications
You must be signed in to change notification settings - Fork 460
-
Star 2.9k
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
The image is very dark #79
The image is very dark #79
Comments
WindFall-wyx
commented
Mar 23, 2023
I have encountered the same problem. Have you solved it? Thank you. |
pfeducode
commented
Mar 28, 2023
I use guide - ddfm to train, and within the same training time, the guide - ddfm results seem to be better. However, I need to do other experiments, so I don't have time to train for more rounds. |
pfeducode
commented
Apr 5, 2023
If you have solved the problem, I hope you can let me know |
WindFall-wyx
commented
Apr 6, 2023
•
edited
edited
This problem has not been resolved satisfactorily, although I have also tried diffusion in https://github.com/lucidrains/denoising-diffusion-pytorch, which seems to yield slightly better results. |
I used the command you gave. The generated image is very dark. I trained for 10k rounds. Is this normal. Or you can give the record of loss value in your training process and when the model reaches the convergence result.
The text was updated successfully, but these errors were encountered: