Instructions to use MiniMaxAI/MiniMax-Music3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MiniMaxAI/MiniMax-Music3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-Music3", 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
Request to include upstream license files (Apache 2.0 & MIT) in the repository
Dear MiniMax Team,
Thank you for open-sourcing MiniMax-Music3. We greatly appreciate your contribution to the community.
While reviewing the LICENSE file, we noticed the note mentioning that parts of the model and codebase were built upon or modified from open-source projects, specifically:
Qwen3-8B (Apache License 2.0)
Stable Audio Tools / DiT-2B (MIT License)
DAC / VAE (MIT License)
To ensure full open-source compliance and to help users and developers safely adopt and redistribute the repository, could you please include the full text copies of these upstream licenses (e.g., LICENSE-APACHE and LICENSE-MIT or within a LICENSES/ directory) alongside your community license?
Including these original attribution files would clarify the licensing terms for everyone in the community.
Thank you for your time, support, and great work!
Best regards,