MyNiuuu / MOFA-Video

Official Pytorch implementation for MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.
https://myniuuu.github.io/MOFA_Video
Other
358 stars 22 forks source link

about MOFA-ADapter download link? #2

Closed zhanghongyong123456 closed 3 weeks ago

zhanghongyong123456 commented 3 weeks ago

I can't find the corresponding link, looking for Pointers Download the checkpoint of MOFA-Adapter from huggingface to ./ckpts I

zhanghongyong123456 commented 3 weeks ago

when run demo.py have this error?
image

win10 cuda 12.1 cupy(pip install cupy-cuda12x) torch 2.2.0cu12.1

MyNiuuu commented 3 weeks ago

I can't find the corresponding link, looking for Pointers Download the checkpoint of MOFA-Adapter from huggingface to ./ckpts I

You can find the checkpoint here: https://huggingface.co/MyNiuuu/MOFA-Video-Traj/blob/main/ckpts/controlnet. To use it, download the entire folder and place it in the ./ckpts directory (make sure not to forget the config.json file).

MyNiuuu commented 3 weeks ago

when run demo.py have this error? image

win10 cuda 12.1 cupy(pip install cupy-cuda12x) torch 2.2.0cu12.1

What is the cuda version of your machine? Have you tried pip install cupy-cuda117 instead of pip install cupy-cuda12x?

zhanghongyong123456 commented 3 weeks ago

I can't find the corresponding link, looking for Pointers Download the checkpoint of MOFA-Adapter from huggingface to ./ckpts I

You can find the checkpoint here: https://huggingface.co/MyNiuuu/MOFA-Video-Traj/blob/main/ckpts/controlnet. To use it, download the entire folder and place it in the ./ckpts directory (make sure not to forget the config.json file).

I misunderstood. I thought there was a new training model

zhanghongyong123456 commented 3 weeks ago

my cuda 12.1 cupy(pip install cupy-cuda12x) torch 2.2.0cu12.1 have this error when i change the cuda version to 11.7, cupy-cuda-11.7 torch2.0.1 ,It's OK