zhangp365
zhangp365
In my case， updating the Pillow version to 10.3.0， It solved the problem.
NLLB-200 is a great model. It would be wonderful if GGML could support this model.
FreeU is very useful, wish Onediff supports it. thank you very much.
use wheels: https://github.com/cczhong11/chatglm.cpp/actions/runs/5904410708
It's wonderful advice; comfyUI custom_node is absolutely necessary.
Thank you very much for your reply. I have searched for a solution. Actually, I found that CUDA supports updating the image size of the CUDA graph, but there is...
You can use an sd anime model to inpaint the area.
also can try this: https://github.com/zhangp365/ComfyUI_photomakerV2_native
same question. does onediff support flux in comfyui?
> OK, Thanks for replying. I have another question, is the video length used for inference only applicable to shorter videos, about 10-20 frames? I have predicted the video using...