SD models use more vram than XL models?
Open
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
I'm not sure if this is a bug or if I don't understand something. But when I generate an image with an XL model, it uses less VRAM than if I use the same settings and switch to an SD model.
To make sure everything is clean, I restarted the server every time.
The results are shown in the screenshots.
Has anyone else observed this behavior?
SD:
XL
Contributor guide
Assessment
This issue has not been assessed yet.