-
Notifications
You must be signed in to change notification settings - Fork 4.3k
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
'NoneType' object has no attribute 'tokenize' #2119
Comments
You cannot load that model with regular checkpoint loading node. It's CLIP output is not compatible with regular CLIP text encoders. |
Hi, Levicki. |
You cannot load that specific checkpoint file with that loader — they aren't compatible and there's no simpler way to explain it. In other words, what you were trying to do doesn't make sense at all (because you don't understand what you are doing) and hence doesn't work. |
Simply. The selected your model isn't valid. |
Hi, Itdrdata. |
In that case read this. |
Thanks for the link. I downloaded and tried txt_to_image_to_video.webp, but faced the same issue. Here are the screenshots : |
If you have only 6GB of VRAM, then you should not use the SVD-XT model. Go to this link - https://huggingface.co/stabilityai/stable-video-diffusion-img2vid/tree/main and download the SVD.safetensors model. Then put this into your ComfyUI/Models/Checkpoints folder. Then in ComfyUI workflow select SVD.safetensors in Image Only Checkpoint Loader(img2vid model). |
Great!!! It works! I can't thank you enough. |
This helped me so much! Thank you all who contributed! |
执行CLIPTextEncode时出现错误: “NoneType”对象没有属性“tokenize” |
I have no idea what's wrong with it. Just installed ComfyUI and put the model in the P:\AI_Tools\ComfyUI_windows_portable\ComfyUI\models\checkpoints\ folder.
What am I missing?
The text was updated successfully, but these errors were encountered: