import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SimpleTuner/MiniMax-Music-3-Encoder", 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 Audio VAE
This repository contains the MiniMax Music 3 DAV audio autoencoder converted to a Diffusers-style component for SimpleTuner.
The converted component is stored in audio_vae/ and can be loaded with MiniMaxMusic3DAV.from_pretrained(repo_id, subfolder="audio_vae") from SimpleTuner.
This is the continuous waveform autoencoder used for VAECache and waveform decode. It is not the RVQ tokenizer, Qwen3 language model, RVQ depth decoder, or flow transformer from the full MiniMax Music 3 pipeline.
Source weights: MiniMaxAI/MiniMax-Music3 dav.pth.
- Downloads last month
- -
Model tree for SimpleTuner/MiniMax-Music-3-Encoder
Base model
MiniMaxAI/MiniMax-Music3