salu133445/musegan
An AI for Music Generation
Generates multi-track polyphonic music in symbolic form (pianoroll) using 3D convolutional GANs, supporting both unconditional generation and user-guided accompaniment from existing tracks. Trained on the Lakh Pianoroll Dataset to produce five-instrument pop phrases (bass, drums, guitar, piano, strings). Outputs in multiple formats including MIDI via Pypianoroll integration, with support for latent space interpolation.
2,013 stars. No commits in the last 6 months.
Stars
2,013
Forks
394
Language
Python
License
MIT
Category
Last pushed
Jun 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/salu133445/musegan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
asigalov61/tegridy-tools
Symbolic Music NLP Artificial Intelligence Toolkit
jaschadub/harmonydagger
Make Music Unlearnable for Generative AI.
declare-lab/TangoFlux
[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
kyegomez/MORPHEUS-1
Implementation of "MORPHEUS-1" from Prophetic AI and "The world’s first multi-modal generative...
FORARTfe/HyMPS
HyMPS will be a platform-indipendent software suite for advanced audio/video contents production.