git
ask
hub
Privacy
Terms
Sign in with GitHub
zacharynovack/live-music-diffusion-models
↗
Stars ·
47
Language ·
Python
License ·
MIT
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: zacharynovack
Ask anything about this repo to start.
I want to fine-tune the live-music-diffusion-models codebase on my own audio dataset. Walk me through the two-step training process: first fine-tuning the base model, then applying ARC-forcing.
Show me how to run inference with live-music-diffusion-models to stream continuously generated music, reusing cached computations for faster block output.
I want to reproduce the results from the live-music-diffusion-models paper. What checkpoints do I need, and how do I run the Jupyter notebook example from loading a checkpoint to producing audio?
Explain the difference between the bidirectional and causal attention model configs in live-music-diffusion-models and when to use each for a true streaming setup.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).