search

huggingface / diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
https://huggingface.co/docs/diffusers
Apache License 2.0
25.19k stars 5.21k forks source link

CogVideoX Image2Video model not found #9454

Closed rolux closed 17 hours ago

rolux commented 1 day ago

Describe the bug

The updated documentation at https://huggingface.co/docs/diffusers/en/api/pipelines/cogvideox says:

pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V", torch_dtype=torch.bfloat16)

Trying to load this pipeline results in:

HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/api/models/THUDM/CogVideoX-5b-I2V

Most likely, this repository is still private.

Reproduction

Reproduction: see above, simply run code example in documentation

Logs

No response

System Info

diffusers 0.30.3

Who can help?

No response

a-r-r-o-w commented 1 day ago

The model has not been released yet. It will be in the next few days. The reason for the early-release with Diffusers is to enable usage of the pipeline to users in countries where Github is banned

a-r-r-o-w commented 17 hours ago

Model has been released here: https://huggingface.co/THUDM/CogVideoX-5b-I2V :partying_face: