search

dvlab-research / Video-P2P

Video-P2P: Video Editing with Cross-attention Control
https://video-p2p.github.io/
355 stars 24 forks source link

I have completed the training, and the reasoning reports an error #8

Open willis opened 1 year ago

willis commented 1 year ago

Can't load tokenizer for './outputs/rabbit-jump'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './outputs/rabbit-jump' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer.

puppynull commented 10 months ago

It may be caused by 'TypeError: The keyword fps is no longer supported. Use duration(in ms) instead, e.g. fps=50 == duration=20 (1000 * 1/50).' when saving the model. Just follow the instruction and change that wrong keyword works for me.

Weiwenliang123 commented 10 months ago

Can't load tokenizer for './outputs/rabbit-jump'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './outputs/rabbit-jump' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer. Hello, how did you change the path of the pre trained model and where did you make the changes?