search

teticio / audio-diffusion

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.
GNU General Public License v3.0
707 stars 69 forks source link

Request ... No GUI ??? #47

Closed kalle07 closed 6 months ago

teticio commented 8 months ago

There is this... https://huggingface.co/spaces/teticio/audio-diffusion

kalle07 commented 8 months ago

i see THX,

is it also all offline possible without colab ?

teticio commented 7 months ago

Sure, but you will need a GPU or lots of patience. You can run the app.py file locally.

kalle07 commented 7 months ago

i have an RTX .... in your describtion i dont see wat exactly i should install and which models i should copy in which folder... and i only want create audio from text-prompts app.py its starts localhost on a spezific port ?

teticio commented 7 months ago

It doesn't work with text prompts. Gradio runs on port 7860 by default. It will download the models for you. There is a requirements.txt file so "pip install -r requiirements.txt"

kalle07 commented 7 months ago

i see .. may i try ;)