ComfyUI
ComfyUI copied to clipboard
Published
2 weeks ago
•
comfyanonymous
comfyanonymous
Decreased inference speed after latest changes
Expected Behavior
The inference speed and VRAM usage should have remained the same.
Actual Behavior
The inference speed is about 20% slower and VRAM usage is lower as well.
Steps to Reproduce
Used a default SDXL workflow with lora
Debug Logs
No error logs
Other
No response
