Dynamic Lora Weights Using Flux and 2 Loras Cause Out Of Memory With 24GB VRAM
Open
User Support
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 158
Description
### Your question
I am trying the new lora scheduling using 2 loras and I'm not sure if I'm using it right but ComfyUI is giving me Out Of Memory with an RTX4090.
[workflow7.json](https://github.com/user-attachments/files/18572389/workflow7.json)
edit: I corrected the CFG to 1 and start at step to 1 after I posted.
Contributor guide
Assessment
This issue has not been assessed yet.