From 223c68ebd3838120dc15771f1f88a67e7272dcd3 Mon Sep 17 00:00:00 2001 From: StopDeletingMyComment123 Date: Sat, 22 Aug 2026 13:33:04 +0300 Subject: [PATCH] Links for community version of a working RVQ-Encoder Community version of a working RVQ-Encoder: https://huggingface.co/SimpleTuner/open-rvq-encoder-minimax-music3 https://huggingface.co/scragnog/open-rvq-encoder-minimax-music3-169m-hotstep-v1 --- README.md | 158 +++--------------------------------------------------- 1 file changed, 6 insertions(+), 152 deletions(-) diff --git a/README.md b/README.md index 06241e7..ca82f6c 100644 --- a/README.md +++ b/README.md @@ -1,157 +1,11 @@ -
- MiniMax -
-

- MiniMax Agent - API - MiniMax Music 3 Live Demo - MiniMax Website -
- ModelScope MiniMax AI - WeChat - Discord - Hugging Face - GitHub - LICENSE -

+Someone keeps deleting this comment, not sure why?... -# MiniMax Music 3 +I will just repost if there is no explanation given... -**MiniMax Music 3** is a high-performance music generation model for creating complete songs up to **five minutes** long. Conditioned on lyrics and a detailed music description, it generates structurally coherent songs with expressive vocals, evolving arrangements, and stable long-form audio quality. +Community version of a working RVQ-Encoder: -MiniMax Music 3 combines an **8B Global LLM** for long-range musical structure, a **0.6B Local LLM** for frame-level acoustic detail, and a continuous hidden-state synthesis system based on **Flow Matching** and **Flow-VAE**. The model produces 32 kHz, 16-bit stereo WAV audio. +https://huggingface.co/SimpleTuner/open-rvq-encoder-minimax-music3 -## Prompt Enhancement +https://huggingface.co/scragnog/open-rvq-encoder-minimax-music3-169m-hotstep-v1 + -A concise natural-language description can be used directly. For richer prompts and more precise control, use the provided [`music-caption-rewriter`](skills/music-caption-rewriter/SKILL.md) skill to expand it into a Structured Caption containing `Global Metadata`, `Vocal Details`, and `Arrangement`. The skill preserves musical instructions attached to lyric section tags in the arrangement description while keeping the lyric text in the lyrics input. See the [skills page](skills/README.md) for installation instructions and a full feature overview. - -```bash -npx skills add MiniMax-AI/MiniMax-Music3 --skill music-caption-rewriter -``` - -## Demo - -Explore music generation examples on the [MiniMax Music 3 Demo](https://minimax-ai.github.io/music3-demo/). - -

- MiniMax Music 3 architecture diagram -

- -## Complete Songs with Long-Range Coherence - -MiniMax Music 3 natively supports full-song generation up to five minutes. The model maintains musical themes, rhythm, vocal identity, and arrangement progression across long sequences, enabling complete structures such as intro, verse, pre-chorus, chorus, bridge, instrumental break, and outro. - -## Fine-Grained Music Control - -The model accepts two complementary inputs: - -- **Lyrics** define the words to be sung and may include explicit section tags such as `[Intro]`, `[Verse]`, `[Pre-Chorus]`, `[Chorus]`, `[Post-Chorus]`, `[Bridge]`, `[Instrumental]`, `[Solo]`, and `[Outro]`. -- **Music description** defines the musical style, emotional progression, vocal performance, instrumentation, arrangement, and production profile. - -For precise control, we recommend using a Structured Caption with three sections: - -- **Global Metadata**: genre, subgenre, BPM, key, scale, emotional progression, listening scenario, and production profile. -- **Vocal Details**: vocal gender, timbre, performance style, harmony, backing vocals, and vocal effects. -- **Arrangement**: primary and secondary instruments, section-level instrument evolution, groove, bass, percussion, textures, and spatial effects. - -This representation allows the model to follow not only a global style, but also the musical development of the song over time. - -## Hybrid-LM - -MiniMax Music 3 uses a hierarchical autoregressive architecture that separates global musical modeling from local acoustic modeling. - -- The **Global LLM (8B)** predicts the first RVQ codebook frame by frame and models the song's long-range semantic and structural progression. -- The **Local LLM (0.6B)** predicts the remaining acoustic codebooks within each frame and restores fine-grained acoustic information. - -The Global LLM is initialized from Qwen3-8B. During training, its embedding and output layers are first adapted to semantic music tokens. The Global and Local LLMs are then jointly trained to model all RVQ codebooks. - -## Continuous Hidden-State Synthesis - -Instead of decoding only from discrete RVQ tokens, the synthesis module fuses the final hidden states of the Global and Local LLMs. These continuous representations preserve richer acoustic information for vocal articulation, instrumental texture, and temporal continuity. - -The synthesis path is: - -```text -Global and Local LLM hidden states - ↓ - Hidden-state fusion - ↓ - Flow Matching (2.4B) - ↓ - Flow-VAE latent - ↓ - Flow-VAE Decoder (123M) - ↓ - 32 kHz stereo audio -``` - -The Flow-VAE architecture is adapted from MiniMax Speech and retrained for the dynamic range and spectral characteristics of music. - -## Music Tokenizer - -The training tokenizer uses eight layers of Residual Vector Quantization (RVQ): - -- The first semantic codebook contains **16,384** entries and captures the core musical semantics and structure. -- The remaining seven acoustic codebooks contain **1,024** entries each and represent residual acoustic details. - -Training first optimizes the semantic codebook, then jointly trains all eight codebooks. At inference time, waveform synthesis uses the fused LLM hidden states and does not require the discrete tokenizer decoder. - -## How to Use - -### Download the Model - -```bash -hf download MiniMaxAI/MiniMax-Music3 --local-dir /path/to/minimax_ttm -``` - -### Serve with SGLang-Omni - -MiniMax Music 3 is currently supported by [SGLang-Omni](https://github.com/sgl-project/sglang-omni). From the SGLang-Omni repository root, run: - -```bash -sgl-omni serve --model-path MiniMaxAI/MiniMax-Music3 --port 8000 -``` - -Inference uses two CUDA GPUs: - -- **GPU 0** runs Qwen3 and eight-codebook RVQ autoregressive generation. -- **GPU 1** runs Flow Matching and DAV waveform decoding. - -### Generate Music - -The service uses the shared speech API. Put the lyrics in `input` and the music description in `instructions`. - -```bash -curl http://127.0.0.1:8000/v1/audio/speech \ - -H 'Content-Type: application/json' \ - -d '{ - "model": "minimax_ttm", - "input": "[Verse]\nMorning light filtering through the pine\n[Chorus]\nSoftly the world begins to breathe", - "instructions": "A warm acoustic pop song with intimate female vocals, fingerpicked guitar, soft piano, and a gradual emotional build into a wide final chorus.", - "response_format": "wav", - "seed": 7, - "max_new_tokens": 9000, - "stream": false - }' \ - --output minimax_music3.wav -``` - -An example generated with this checkpoint is available at [`assets/minimax_ttm.wav`](assets/minimax_ttm.wav). - -### Music Caption Rewriter Skill - -This repository includes `music-caption-rewriter`, an agent skill that turns a brief music description and optional tagged lyrics into a detailed Music 3.0 Structured Caption. It uses a bundled text library to select compatible style references, combine requested influences, and build a coherent section-by-section arrangement without external APIs or runtime dependencies. - -Then invoke `$music-caption-rewriter` in a supported coding agent with a music description and, optionally, lyrics containing section tags such as `[Verse]` or `[Chorus]`. The skill returns `Global Metadata`, `Vocal Details`, and `Arrangement` while preserving explicit musical constraints and keeping lyric text out of the rewritten caption. - -## Limitations - -- Inference requires two CUDA GPUs. -- Only non-streaming generation is currently supported. -- The tokenized text prompt is limited to 5,000 tokens. -- Audio generation is limited to 9,000 acoustic frames. -- Section tags and music descriptions provide generative control rather than strict symbolic guarantees. The generated tempo, key, instrumentation, lyrics, and song structure may not always match every requested detail exactly. - -## Contact Us - -Contact us at [model@minimax.io](mailto:model@minimax.io).