Audio to 3D (Question)

[arielkantorovich]

Hi, Thank you all for a great git! I want to try some new thing instead use the text prompt diffusion model to generate 3d I want to try the audio diffusion model but I am confused by all the configuration details. My question is where In your code I can change the diffusion model and put the audio image model instead? I will be happy to get where is the "area" in the code that I need.

[dsidorenkoSU]

If I got your idea correctly then you just need to use some speach-to-text model in front of this model. It'll produce text prompt and you'll feed it to the pipeline.