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.

Sign up for GitHub

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

Jump to bottom

for SDXL can we train TI using this? #1

Open

RYG81 opened this issue May 21, 2024 · 1 comment

RYG81 commented May 21, 2024

for SDXL can we train TI using this?

Owner

mbrostami commented May 21, 2024

I could train an embedding with textual_inversion_sdxl.py script provided by diffusers, but could never able to USE it with SDXL checkpoints as it was complaining about mismatch shape of the embedding space. 768 vs 1280.
If you want to give it a try, you can uncomment SDXL node here:
https://github.com/mbrostami/ComfyUI-TITrain/blob/main/training.py#L398
https://github.com/mbrostami/ComfyUI-TITrain/blob/main/training.py#L393

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment