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
is the code of the model also open source?
#26 opened 44 minutes ago
by
LejobuildYT
Confirming the DAV encoder accepts real audio β and a local app built on Music 3
#25 opened about 3 hours ago
by
Senzubean
Audio.cpp now supports MiniMax-Music3. No Python. Demo and performance metrics inside.
1
#24 opened about 21 hours ago
by
audio-cpp
Has anyone gotten a consistently vocal-free track out of the open weights?
π 1
1
#23 opened 1 day ago
by
fe2-o3
Frankenstein in Five Pieces: How to Build a Music Model from Spare Parts, Duct Tape, and Desperate Prayers
β€οΈπ 3
36
#22 opened 2 days ago
by
AdrienneNoctis
generating creepy audio with no lyrics after initial 5 seconds on rtx 5090
1
#21 opened 3 days ago
by
kai960
Open research toolkit extending MiniMax Music3 with arbitrary-audio encoding, continuation, inpainting, prepend generation, prompt-free generation, and automated evaluation.
π 1
1
#19 opened 4 days ago
by
coolpoodle
Assigning lyrics to voices
π 1
4
#18 opened 6 days ago
by
msze
System prompt
#17 opened 6 days ago
by
rzgar
it needs to accept: Humming as Audio as INPUT
1
#16 opened 6 days ago
by
usermma
demo "η§ε»ζ₯ε ε" is both awesome and buggy
#15 opened 6 days ago
by
J22
Apple Silicon MLX version proof of concept
π 3
#14 opened 7 days ago
by
liminalsunset
How to get accent?
1
#13 opened 7 days ago
by
ryg81
GGUF?
π₯ 1
3
#12 opened 7 days ago
by
rodrigomt
Any plans to release a RVQ encoder or Flow-VAE encoder to enable audio-conditioned generation?
π€ 9
3
#11 opened 7 days ago
by
TheLatentSpacer
Is the model trainable?
π 5
63
#10 opened 7 days ago
by
PabloFG
Without audio refrences this is useless, even more so for actual musicians
π 1
5
#9 opened 7 days ago
by
FreeDiddy
Imagine if MiniMax Speech 2.8 HD (and maybe Turbo) releases on Hugging Face!
#8 opened 7 days ago
by
MihaiPopa-1
rδΈηε°η,η₯θ΄ΊεεΈ
#7 opened 7 days ago
by
aifeifei798
Is the song reference supported?
3
#6 opened 7 days ago
by
AlperKTS
RVQ encoder
ππ 11
2
#5 opened 7 days ago
by
arifqai
music quality look like suno V3.5
5
#4 opened 7 days ago
by
rafiislam