These models generate and modify music from text prompts and raw audio. They combine large language models and diffusion models trained on text-music pairs to understand musical concepts.
Featured models

Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts
Updated 2 months ago
58.2K runs

Music-1.5: Full-length songs (up to 4 mins) with natural vocals & rich instrumentation
Updated 2 months, 3 weeks ago
47.2K runs

Quickly generate up to 1 minute of music with lyrics and vocals in the style of a reference track
Updated 2 months, 3 weeks ago
500.8K runs

stability-ai/stable-audio-2.5Generate high-quality music and sound from text prompts
Updated 2 months, 3 weeks ago
17.1K runs

Compose a song from a prompt or a composition plan
Updated 3 months ago
1.6K runs

meta/musicgenGenerate music from a prompt or melody
Updated 1 year, 10 months ago
3.3M runs

sakemin/musicgen-stereo-chordGenerate music in stereo, restricted to chord sequences and tempo
Updated 2 years, 2 months ago
3.4K runs

andreasjansson/musicgen-looperGenerate fixed-bpm loops from text prompts
Updated 2 years, 7 months ago
60.5K runs
Recommended Models
Recommended Models

lucataco/ace-stepA Step Towards Music Generation Foundation Model text2music
Updated 8 months, 2 weeks ago
95.8K runs

zsxkib/flux-music🎼FluxMusic Text-to-Music Generation with Rectified Flow Transformer🎶
Updated 1 year, 4 months ago
8.8K runs

sakemin/musicgen-remixerRemix the music into another styles with MusicGen Chord
Updated 2 years ago
18.6K runs

lucataco/magnetMAGNeT: Masked Audio Generation using a Single Non-Autoregressive Transformer
Updated 2 years ago
2.9K runs

sakemin/musicgen-stereo-chordGenerate music in stereo, restricted to chord sequences and tempo
Updated 2 years, 2 months ago
3.4K runs

sakemin/musicgen-chordGenerate music restricted to chord sequences and tempo
Updated 2 years, 2 months ago
3.1K runs

riffusion/riffusionStable diffusion for real-time music generation
Updated 3 years, 1 month ago
1.1M runs