MiniMax Music 3 - ComfyUI Song Generator Workflow (Local AI Music with Vocals)

Author notes from minimaxMusic3ComfyuiSong_v10.json · selected release

## MiniMax Music 3 A music generation model by MiniMax that creates complete songs up to 5 minutes long with stable structure and high audio quality. Two inputs drive it: **Caption** (structured music description: style, mood, vocals, arrangement) and **Lyrics** (with `[intro]` `[verse]` `[chorus]` `[bridge]` `[outro]` tags controlling song structure). ### Parameters | Parameter | Description | |---|---| | Caption | Music description. Write it in three sections — Global Metadata → Vocal Details → Arrangement. The more specific, the closer the result. | | Lyrics | Song lyrics + section tags. Tags are the only executable structural instructions; the lyric text itself only conveys mood. | | max_duration | Target song length in seconds (default 120 = 2 minutes; the model supports up to ~300 s / 5 minutes). Longer songs take more time and VRAM. | | seed | Random seed for the generation. Keep it fixed to reproduce the same song; change it to get a different take. | | Model files | diffusion model / text encoder / VAE.| | Tiled decode | Decode the audio VAE in overlapping tiles to drastically cut VRAM usage — helpful for long songs on low-VRAM GPUs. Slightly slower, with a small risk of seams at tile boundaries; turn it off on high-VRAM GPUs for the best quality. | ### Prompt Writing Guide You can find an official [Music Caption Rewriter Skill here](https://github.com/MiniMax-AI/MiniMax-Music3)

Author notes from minimaxMusic3ComfyuiSong_v10.json · selected release

## Model Links **diffusion_models** - [minimax_music3_dit_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/diffusion_models/minimax_music3_dit_int8_convrot.safetensors) # For low VRAM - [minimax_music3_dit_fp16.safetensors](https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/diffusion_models/minimax_music3_dit_fp16.safetensors) **text_encoders** - [minimax_music3_text_encoder_pruned_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/text_encoders/minimax_music3_text_encoder_pruned_int8_convrot.safetensors) **vae** - [minimax_music3_dav.safetensors](https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/vae/minimax_music3_dav.safetensors) ## Model Storage Location ``` 📂 ComfyUI/ ├── 📂 models/ │ ├── 📂 diffusion_models/ │ │ ├── minimax_music3_dit_int8_convrot.safetensors # For low VRAM │ │ └── minimax_music3_dit_fp16.safetensors │ ├── 📂 text_encoders/ │ │ └── minimax_music3_text_encoder_pruned_int8_convrot.safetensors │ └── 📂 vae/ │ └── minimax_music3_dav.safetensors ``` ## Report Issue Note: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet. - Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues) - UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues) - Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)