DiffRhythm

Full-length song generation model using diffusion with lyrics and style conditioning.

Open SourceSelf HostedOffline CapableGPU Required (12GB+ VRAM)
0.0 (0)

About

DiffRhythm is a diffusion-based model for generating full-length songs (up to 4m45s). Conditions on lyrics and musical style descriptions. Produces vocals and instrumentals together. By ASLP@NPU. Requires GPU with 12+ GB VRAM. Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Apache-2.0
Minimum VRAM
12 GB
Added
Apr 3, 2026

Similar Tools

Featured

Audio generation framework by Meta including MusicGen for text-to-music.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Latent diffusion model for text-to-audio, music, and speech generation.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Real-time music generation using Stable Diffusion on spectrograms.

Open SourceSelf HostedOfflineGPU 6GB+
Intermediate
0.0 (0)