Skip to content

Failed to recognize encoder layers in taesd/taesdxl. #608

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
Closed
rmatif opened this issue Feb 28, 2025 · 2 comments · Fixed by #609
Closed

Failed to recognize encoder layers in taesd/taesdxl. #608

rmatif opened this issue Feb 28, 2025 · 2 comments · Fixed by #609

Comments

@rmatif
Copy link

rmatif commented Feb 28, 2025

During my testing, I noticed that the current release fails to retrieve the encoder layers in taesd or taesdxl. I didn’t encounter these errors before the taesd refactoring commits, though inference still works

taesd log

taesd_log.txt

taesdxl log

taesdxl_log.txt
@stduhpf
Copy link
Contributor

stduhpf commented Feb 28, 2025 •
edited
Loading

Oh no... I can reproduce it, but not reliably. Running the same command multiple times in a row, I sometime get those logs, and somtimes everything seems fine. If I try in img2img mode, sometimes it works, and sometimes it crashes when trying to encode the image...

@stduhpf
Copy link
Contributor

stduhpf commented Feb 28, 2025

Ah, I found the cause of it. It's just a dumb race condition bacause of a typo.

@stduhpf stduhpf mentioned this issue Feb 28, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Tae: fix race condition causing inconsistent value for decoder_only stduhpf/stable-diffusion.cpp
2 participants
@stduhpf @rmatif