audio_palette / README.md
manasch's picture
Update readme
bb2771f verified
|
raw
history blame
No virus
792 Bytes
metadata
title: Audio Palette
emoji: 🎧
colorFrom: purple
colorTo: indigo
sdk: gradio
sdk_version: 4.7.1
app_file: app.py
pinned: false
license: mit
models:
  - onlycaps/pace_model_weights
  - Salesforce/blip-image-captioning-large
  - facebook/musicgen-small
tags:
  - image2music-generation
  - image-captioning

Audio Palette

Usage

  • Since this space is running on CPU, it is not possible to generate music in a reasonable time.
  • To address this, we have provided a python notebook that handles the music generation part which can be run locally (if you have GPU) or elsewhere.
  • This uses fastAPI to accept api requests and ngrok to expose the server. The same ngrok link needs to be pasted in the input box. (Make sure to include the trailing /).