Closed lstein closed 7 months ago
I fixed this issue a few days ago. It was a race condition resulting from some async code not being awaited, no ambiguity as to the cause. I can't seem to reproduce it locally, is it possible you were a few commits behind?
I think this was just related to stale UI build.
Is there an existing issue for this problem?
Operating system
Linux
GPU vendor
Nvidia (CUDA)
GPU model
RTX 4070
GPU VRAM
12GB
Version number
main (essentially 4.0rc2)
Browser
Google chrome for ios
Python dependencies
{ "accelerate": "0.28.0", "compel": "2.0.2", "cuda": "12.1", "diffusers": "0.27.0", "numpy": "1.26.4", "opencv": "4.9.0.80", "onnx": "1.15.0", "pillow": "10.0.0", "python": "3.10.12", "torch": "2.1.2+cu121", "torchvision": "0.16.2", "transformers": "4.38.2", "xformers": null }
What happened
When I add a T2I adapter to the linear generation, add a control image, and then attempt to generate an image, the following error message pops up in the UI:
There are no errors in the server log. I have tried rebuilding the front end, clearing the browser cache, etc.
What you expected to happen
I expected image generation to start.
How to reproduce the problem
+ T2I Adapter
canny-sd15
T2I processorAdditional context
No response
Discord username
l.stein