Hello everyone, new to ComfyUI and i would love if someone could help me!
Ill start with my pc configuration
Processor: AMD Ryzen 5 2600 six-core processor
Board: ASUS Prime B450M-A II
RAM: 16GB DDR4
Graphics: NVIDIA GeForce GTX 1080 Ti 11264 Memory
Windows 10 Pro
I downloaded from the ComfyUI website for Windows and installed, tried to generate image to video, and downloaded the needed missing models but the following message appeared “CLIPVisionEncode
CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.”
I had the same issue and find a way to make it work.
1)First, I did a clean installation of comfy ui by deleting the apps and all the folder (don’t know if it’s useful, but I find out the windows uninstaller don’t deleted everything)
This does not seem to work anymore. What should I do? It was working fine until today, when I tried installing a custom node that updated the python torch thing…
Your custom node has killed the torch installation. You need to do a clean install of ComfyUI. And reinstall all. Minus this custom node.
It is one of the nastiest behaviours of ComfyUI that custom nodes are allowed to mess with python versions and torch versions. It simply breaks everything then.
As a note, the portable version might be your friend here. It contains everything needed in its own folder.