Missing image_encoder and image_processor

#2
by qhz991029 - opened

Hi,

Thank you for the wonderful work!

During the initial try, I met the issue as follows:

"""
ValueError: Pipeline <class 'diffusers.pipelines.wan.pipeline_wan_i2v.WanImageToVideoPipeline'> expected ['image_encoder', 'image_processor', 'scheduler', 'text_encoder', 'tokenizer', 'transformer', 'vae'], but only {'text_encoder', 'scheduler', 'tokenizer', 'vae', 'transformer'} were passed.
"""

I thought this might be due to the missing files of the image processor and the image encoder in the HuggingFace checkpoint. I wonder if there's a way to fix this to try the model.

Thank you for your help!

Wan-AI org

we will merge the PR https://github.com/huggingface/diffusers/pull/12004 soon
for now you need to install from the PR
pip install git+https://github.com/huggingface/diffusers.git@wan2.2

we will merge the PR https://github.com/huggingface/diffusers/pull/12004 soon
for now you need to install from the PR
pip install git+https://github.com/huggingface/diffusers.git@wan2.2

Hi, I found that the branch of wan2.2 is missing and cannot working anymore, as well as the huggingface is not working(still found that the processor is missing), how can I solve the problem? Thank you!

Sign up or log in to comment