THUDM

/

CogVideoX-5b-I2V

like 212

Follow

Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University 1,182

Getting this error. Any idea how to fix?
CogVideoXPatchEmbed( (proj): Conv2d(32, 3072, kernel_size=(2, 2), stride=(2, 2)) (text_proj): Linear(in_features=4096, out_features=3072, bias=True) ) does not have a parameter or a buffer named pos_embedding.

FIXED: Issue was diffusers not updated. Did this by going into ComfyUI-CogVideoXWrapper folder and do a pip install -r requirements.txt