Instructions to use AEmotionStudio/sonicmaster-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AEmotionStudio/sonicmaster-models with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AEmotionStudio/sonicmaster-models", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
SonicMaster — bundled mirror
Self-contained inference bundle for the MAESTRO desktop app.
Contents
sonicmaster/model.safetensors— diffusion checkpoint (source: amaai-lab/SonicMaster)sonicmaster/tangoflux_config.yaml— model architecture configt5/—google/flan-t5-largetext encoder + tokenizer (Apache-2.0)vae/— Oobleck VAE fromstabilityai/stable-audio-open-1.0
License
- SonicMaster: Apache-2.0
- T5 (flan-t5-large): Apache-2.0
- Stable Audio Open 1.0 VAE: Stability AI Community License (research-friendly)
Paper: Melechovsky, Mehrish, Herremans. "SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering." ICML 2026 (arXiv:2508.03448).