-
Notifications
You must be signed in to change notification settings - Fork 11
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Using the default workflow, default parameters, an error occurs at runtime. #20
Comments
same |
1 similar comment
same |
I don't know where the problem lies |
this problem has been solved Problem Solving Document |
删除 ..cache\sdwebuilauncher\hfmirror\里面的文件,.cache\huggingface\hub目录里的models--laion--CLIP-ViT-bigG-14-laion2B-39B-b160k也删除掉,其他的最好别动。再运行流程,重新下载models--laion--CLIP-ViT-bigG-14-laion2B-39B-b160k |
有效 |
按照这个步骤 结果还是报错 |
没删除干净吧,先退出COMFYUI,不退出也是不行的,再删除models--laion--CLIP-ViT-bigG-14-laion2B-39B-b160k的缓存,.cache\sdwebuilauncher\hfmirror里的blob目录里就是缓存文件,不删除不重新下载,所以都要删除,huggingface里不能随便删,里面有可能有其他插件的模型 |
很可惜,我这里也没能工作。我确定已经删除了所有你指出的文件,还重新下载了所有的模型文件,但还是报错。
|
me same |
Using the default workflow, default parameters, an error occurs at runtime.:
Error occurred when executing UltraPixelProcess:
Error(s) in loading state_dict for CLIPTextModelWithProjection:
size mismatch for text_projection.weight: copying a param with shape torch.Size([1280, 1280]) from checkpoint, the shape in current model is torch.Size([512, 1280]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.
The text was updated successfully, but these errors were encountered: