Text-to-Audio
Diffusers
Safetensors
PyTorch
minimax_music3
music-generation
text-to-music
sglang-omni
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
GGUF?
#12
by rodrigomt - opened
When is the GGUF version coming?
Use this until the official GGUF:
https://huggingface.co/ChrisColeTech/minimax-music-GGUF
But yes we need GGUF's especially for the text_encoder.
There is no "official" GGUF because there are several ways to do it. I created a minimal GGML port here, simpler than acestep.cpp but same code style template :
https://github.com/ServeurpersoCom/minimaxmusic.cpp
https://huggingface.co/Serveurperso/MiniMax-Music3-GGUF
If I manage to integrate it into llama.cpp's MTMD, it would result in more complex/unified/official GGUF files. It remains to be seen if it's possible.