Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
THUDM
/
CogVideoX1.5-5B-I2V
like
40
Follow
Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University
1,248
Image-to-Video
Diffusers
Safetensors
English
CogVideoXImageToVideoPipeline
video-generation
thudm
arxiv:
2408.06072
License:
other
Model card
Files
Files and versions
Community
7
Use this model
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (5)
Any optimization ways to accelerate the speed of inference
1
#7 opened about 4 hours ago by
mayukitan
AttributeError: 'CogVideoXTransformer3DModel' object has no attribute 'ofs_embedding'. Did you mean: 'time_embedding'?
14
#3 opened 5 days ago by
froilo