search

tencent-ailab / V-Express

V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.
2.03k stars 250 forks source link

hugging face #4

Closed jokedud closed 1 month ago

jokedud commented 1 month ago

i tried setting it up in hugging face but didnt work, has anyone set it up there yet? or is it not out yet??

tiankuan93 commented 1 month ago

We provide the model on the huggingface website and you need to follow the installation steps for offline inference. We don't provide the hugging face demo yet.

faraday commented 1 month ago

from @cantonalex : https://huggingface.co/spaces/alexcanton/V-Express/ from me: https://huggingface.co/spaces/faraday/V-Express (loads the required models only at the start, code slightly refactored. fixed requirements.txt a little, noticing a problem with Onnx GPU package setup missing. added in accelerate package as well)

both require GPU runtime

jokedud commented 1 month ago

https://huggingface.co/spaces/faraday/V-Express is closed

faraday commented 1 month ago

@jokedud You should duplicate the space and set a GPU to run it with. It costs a lot in my opinion and not suitable to apply ZeroGPU, that's why it's closed.