-
Notifications
You must be signed in to change notification settings - Fork 137
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
Clear Instructions for Finetuning Faces #13
Comments
Hi, class_prompt: the category of the training images, e.g., For training, using these configurations should be good.
|
@nupurkmr9 If you check regularization images in real_reg/samples_person, you will find that those images are very bad. Most of them are not real faces. |
Hi, Also, our method works with generated images as regularization as well which can be enabled by removing the |
Hi, I appreciate your work. I used same command as you mentioned here. Some of the results comparison between 1.5 vs 2.1 versions. 2.1 prompts: On long prompts: Total identity loss on Emma Watson Images. But dreambooth working fine on these long prompts. Can you please guide me how I can improve the model on long prompts. |
@nupurkmr9 Thanks for amazing wonderful work, I used the these configurations, but the result is bad. accelerate launch src/diffuser_training.py |
Hi, I'm sorry for the delayed response in this thread. I trained a model on 16 face photos with the following configurations on 2 GPUs. Training on faces with the
And these are the results with sampling done as |
Hey thanks for amazing work,
I was trying to implement finetuning faces like dreambooth works really well in finetuning model on specific face subject. But when I tried finetuning faces there is very less guidelines for it. But I tried training through diffusers and the results were very odd and the identity loss was very high. Training through scripts is difficult to understand since there is no specific guideline for what is instance prompt and what is class prompt.
It would be great if you can provide us better guidelines on finetuning faces easily with custom diffusion.
Also the papers say the model is ~6x faster than dreambooth, however this does not seems to be the case, since training custom diffusion through diffusers is taking almost the same time and gpu memory, please guide us on this as well.
Really looking forward to your reply
The text was updated successfully, but these errors were encountered: