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.
2.2k stars 277 forks source link

Not a coder #11

Closed sanganisahil closed 4 months ago

sanganisahil commented 4 months ago

Hi I'm not a coder, can you tell me if any space is there that i can use?

FurkanGozukara commented 4 months ago

i made auto installer and gradio app https://www.patreon.com/posts/105251204

interface

https://github.com/tencent-ailab/V-Express/assets/19240467/e76a9b48-4635-4cad-87fc-155003ddbec2

cantonalex commented 4 months ago

Can we delete this patreon crap. It goes against everything open source. The Vexpress team have open sourced the code. Don't then take it and try and monetise it by putting it on HF. Here is an open source version of HF https://huggingface.co/spaces/alexcanton/V-Express/ requires GPU for runtime

faraday commented 4 months ago

@cantonalex I also tried to prepare a Gradio app here: https://huggingface.co/spaces/faraday/V-Express (requires GPU for runtime)

Refactored the code a bit, to make it slightly more understandable and directly callable as functions.

Modified inference.py to have an InferenceEngine class that keeps required models loaded when Gradio app.py starts. Refactor kps sequence extraction script as extract_kps_sequence_from_video function from sequence_utils.

The idea was to serve subsequent inference requests without model loads every time.

cantonalex commented 4 months ago

@faraday do you know how you can export the video without the crop onto the source video? https://github.com/tencent-ailab/V-Express/issues/9