Hugging Face's logo

pinecoresystems
/
MiniMax-Music3

Text-to-Audio
Diffusers
Safetensors
music-generation
text-to-music
Model card Files
xet
 Community
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("pinecoresystems/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]

MiniMax Music 3 (TinyPine mirror)

MiniMax-Music3 by MiniMax, unmodified, in its diffusers layout, mirrored so TinyPine Studio's installer does not depend on third-party download links. TinyPine did not train or change the model. Upstream: MiniMaxAI/MiniMax-Music3.

Licence: the MiniMax-Music3 Community License in LICENSE (copyright (c) 2026 MiniMax), including its Acceptable Use Policy (Exhibit A). Commercial products that use the model must show "MiniMax-Music3" in their interface; above USD 20 million yearly revenue a separate authorisation from MiniMax is required.

Also included: the AudioSeal watermark generator and detector (Meta, MIT, audioseal/LICENSE), which TinyPine embeds in every song it makes, from facebook/audioseal.

Only the diffusers sub-folders are mirrored; the SGLang layout (qwen_7B/, flowmatching_vae.pth, dav.pth) is not.

SHA-256 of the large files:

  • condition_encoder/diffusion_pytorch_model.safetensors 83179c5eaa9a68a370affe0c1b96c2179f659ea4175666b31071490a202c2a4d
  • language_model/model-00001-of-00004.safetensors 1e95924a158b45b67cfad04fa0f0a352e5a263e69338734d7c1d558be776cc98
  • language_model/model-00002-of-00004.safetensors fde2d335eef7eafa268d35e53d4b040ee51d2f3fa727f9855b4c97d88a2892da
  • language_model/model-00003-of-00004.safetensors 6549a831637ab678a573047e7fa8fdf966998c4f45330e6eb7573d67f7b9b4c6
  • language_model/model-00004-of-00004.safetensors a1c9865f357b64d3ae9f428fb98a844831e5a0aee9ed17b19bd7f7be32b964a9
  • rvq_depth_decoder/diffusion_pytorch_model.safetensors 80e86ab006bb5c8d4f223205045035a1c77b2bb9c3be9a86d7e740bbafe5ddf0
  • tokenizer/tokenizer.json b1537fa9e59a537276ecbc2e12d0438edff635a1f4a4948e679774b5feb3e610
  • transformer/diffusion_pytorch_model-00001-of-00002.safetensors 1943baebe93b5d5a57e9e1f603d9cef51a73a55e7a42f52913932dc06dcf10f0
  • transformer/diffusion_pytorch_model-00002-of-00002.safetensors b2f9e29d241e107e5a281f8b369d6db48eee983917df966c56d7b8dd0bd482c2
  • vocoder/diffusion_pytorch_model.safetensors daf0bf0560ea978ce7b5ec3e82f420a44429efef18bdfbe3c714d55ceffbe934
  • audioseal/generator_base.pth 7a845b5fbe9364a63a3909d8ab3fe064d13a76ae4c2e983573e08c69b7b51748
  • audioseal/detector_base.pth 8a78e8a83584113523e161fc599fcab10fd0e94c04d2eb9d2fa1e9ec91ab69d9
Downloads last month
42
Safetensors
Model size
2B params
Tensor type
F32
·
Inference Providers NEW
Text-to-Audio
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support