# feizc/FluxMusic

Text-to-Music Generation with Rectified Flow Transformers

Repository: https://github.com/feizc/FluxMusic
Canonical: https://ross.abutalabs.com/products/fluxmusic
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-12-10T06:35:10+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 54
- inputs: {"age_days": 757, "days_push": 631, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1711, forks 128 (observed 2026-08-28T04:05:25.749636+00:00)

## What it is
FluxMusic is the official PyTorch implementation of a rectified flow Transformer model for text-to-music generation, from the paper 'Flux that plays music'. It provides model definitions, pre-trained checkpoints, and training/inference scripts.

## Use cases
- generate music clips from text prompts
- train a text-to-music diffusion transformer model
- sample audio from pre-trained FluxMusic checkpoints
- experiment with rectified flow models for audio generation
- research text-conditioned music synthesis

## When to choose
- you need a research-grade text-to-music generation model with open weights
- you want to train or fine-tune a rectified flow transformer on audio
- you are reproducing or extending the FluxMusic paper

## When to avoid
- you need a polished end-user music generation app with a GUI
- you lack GPU resources, as training and inference require significant compute
- you need production-supported, licensed software (license is non-standard)

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, audio-processing, llm-training
- domain: artificial-intelligence, machine-learning, deep-learning
- platform: python
- tags: text-to-music, rectified-flow, diffusion-transformer, pytorch, music-generation, research-code, audio, gpu, linux

## Member repositories
- feizc/FluxMusic (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:25.749636+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:34:58.736681+00:00, confidence not recorded.
  - readme: https://github.com/feizc/FluxMusic (fetched 2026-08-28T04:05:25.749636+00:00, sha 5be55abdb5b9)
- Data as of 2026-08-30T08:39:29.467469+00:00.