---
title: MiniMax Music 3 Latent Refiner
emoji: 🎵
colorFrom: purple
colorTo: gray
sdk: gradio
sdk_version: 6.26.0
app_file: app.py
short_description: Restore damaged music in MiniMax Music 3 DAV latent space
python_version: "3.12"
startup_duration_timeout: 30m
---

# MiniMax Music 3 — Latent Refiner v0.10

Restore damaged music while retaining the performance, timing, vocals, and arrangement.
This Space runs the [MiniMax Music 3 latent refiner](https://huggingface.co/terminusresearch/minimax-music3-latent-refiner-v0.10) — a 137M-parameter bridge
transformer operating directly in MiniMax Music 3's continuous DAV latent space, conditioned on
MERT frame-aligned features (layer 7), pooled CLAP music embeddings, and an SR3-style degraded
latent stream with in-context reference tokens.

## How it works

The refiner integrates a deterministic 32-step Euler **bridge** sampler from the damaged latent
endpoint (t=1) back to the clean one (t=0), then decodes the refined latents through the DAV
decoder. Inputs are resampled to 44.1 kHz stereo; clips longer than 30 s are processed in
overlapping 30-second windows with a 2-second latent cross-fade (the training configuration).

## Usage

1. **Restore** — upload damaged/degraded music (bandwidth-limited, noisy, quantized, clipped
   recordings) and press *Restore*. 32 bridge steps, 30 s windows by default.
2. **Damage your own audio** — apply the training-style degradation chain (bandwidth reduction,
   additive noise, bit-depth reduction, soft clipping) to a clean clip, then restore it in the
   *Restore* tab and compare against the original.

The bundled examples are public-domain instrumental music (FreePD/CC0, via
[mrfakename/cc0-music-captioned](https://huggingface.co/datasets/mrfakename/cc0-music-captioned))
with the degradation chain applied; the undamaged originals are included for side-by-side
listening.

## Notes

- FP32 is the verified release precision for the refiner.
- Inputs are trimmed to 120 s to keep ZeroGPU durations bounded.
- The `minimax_music3_latent_refiner` inference package is vendored in `src/` (Apache-2.0, from
  the model repository).