---
title: "Minimax Music3 Dav in ComfyUI"
description: "Minimax Music3 Dav is a VAE (Variational Autoencoder) that encodes and decodes latent representations."
canonical: https://comfy.org/p/supported-models/minimax-music3-dav
lang: en
index: https://comfy.org/llms.txt
---

# Minimax Music3 Dav in ComfyUI

Minimax Music3 Dav is a VAE (Variational Autoencoder) that encodes and decodes latent representations. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Minimax Music3 Dav with ControlNets, LoRAs, upscalers, and custom nodes to build any pipeline you need. There is 1 community workflow template using Minimax Music3 Dav on Comfy Workflows, ready to load and customize.

## Facts

- Type: VAE
- Pricing: free to run locally on your own hardware; on Comfy Cloud it meters as GPU time at the published Cloud GPU rate: https://docs.comfy.org/tutorials/partner-nodes/pricing#cloud-gpu
- Community workflow templates: 1
- Weights: https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/vae/minimax_music3_dav.safetensors

## How to run Minimax Music3 Dav

1. Locally in ComfyUI — open source, free on your own hardware: https://comfy.org/download
2. On Comfy Cloud — hosted GPUs, every parameter still exposed: https://cloud.comfy.org
3. Start from a community workflow template and adjust it node by node: https://www.comfy.org/workflows
4. From your own application with the Comfy SDKs (Python and TypeScript, beta): https://docs.comfy.org/development/api-development/sdks.md
5. From a terminal or a coding agent with Comfy CLI, which runs workflows on Comfy Cloud or a local ComfyUI: https://docs.comfy.org/agent-tools/cli.md
6. From Claude Code, Cursor, or Codex over Comfy MCP at https://cloud.comfy.org/mcp: https://docs.comfy.org/agent-tools/mcp.md

This page as HTML: https://comfy.org/p/supported-models/minimax-music3-dav
Full model catalog: https://comfy.org/p/supported-models/llms.txt
