Instructions to use SimpleTuner/open-rvq-encoder-minimax-music3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SimpleTuner/open-rvq-encoder-minimax-music3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SimpleTuner/open-rvq-encoder-minimax-music3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "id": "f9df4058-b0bd-409c-a2e7-c41c8d68d56f", | |
| "revision": 0, | |
| "last_node_id": 46, | |
| "last_link_id": 12, | |
| "nodes": [ | |
| { | |
| "id": 6, | |
| "type": "UNETLoader", | |
| "pos": [ | |
| 40, | |
| 80 | |
| ], | |
| "size": [ | |
| 480, | |
| 90 | |
| ], | |
| "flags": {}, | |
| "order": 0, | |
| "mode": 0, | |
| "showAdvanced": false, | |
| "inputs": [ | |
| { | |
| "localized_name": "unet_name", | |
| "name": "unet_name", | |
| "type": "COMBO", | |
| "widget": { | |
| "name": "unet_name" | |
| } | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "MODEL", | |
| "name": "MODEL", | |
| "type": "MODEL", | |
| "links": [ | |
| 9 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "UNETLoader", | |
| "models": [ | |
| { | |
| "name": "minimax_music3_dit_fp16.safetensors", | |
| "url": "https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/diffusion_models/minimax_music3_dit_fp16.safetensors", | |
| "directory": "diffusion_models" | |
| } | |
| ] | |
| }, | |
| "widgets_values": [ | |
| "minimax_music3_dit_fp16.safetensors", | |
| "default" | |
| ] | |
| }, | |
| { | |
| "id": 3, | |
| "type": "CLIPLoader", | |
| "pos": [ | |
| 40, | |
| 250 | |
| ], | |
| "size": [ | |
| 480, | |
| 120 | |
| ], | |
| "flags": {}, | |
| "order": 1, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "localized_name": "clip_name", | |
| "name": "clip_name", | |
| "type": "COMBO", | |
| "widget": { | |
| "name": "clip_name" | |
| } | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "CLIP", | |
| "name": "CLIP", | |
| "type": "CLIP", | |
| "links": [ | |
| 1 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "CLIPLoader", | |
| "models": [ | |
| { | |
| "name": "minimax_music3_text_encoder_pruned_int8_convrot.safetensors", | |
| "url": "https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/text_encoders/minimax_music3_text_encoder_pruned_int8_convrot.safetensors", | |
| "directory": "text_encoders" | |
| } | |
| ] | |
| }, | |
| "widgets_values": [ | |
| "minimax_music3_text_encoder_pruned_int8_convrot.safetensors", | |
| "minimax", | |
| "default" | |
| ] | |
| }, | |
| { | |
| "id": 7, | |
| "type": "VAELoader", | |
| "pos": [ | |
| 40, | |
| 740 | |
| ], | |
| "size": [ | |
| 480, | |
| 70 | |
| ], | |
| "flags": {}, | |
| "order": 2, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "localized_name": "vae_name", | |
| "name": "vae_name", | |
| "type": "COMBO", | |
| "widget": { | |
| "name": "vae_name" | |
| } | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "VAE", | |
| "name": "VAE", | |
| "type": "VAE", | |
| "links": [ | |
| 11 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "VAELoader", | |
| "models": [ | |
| { | |
| "name": "minimax_music3_dav.safetensors", | |
| "url": "https://huggingface.co/Comfy-Org/MiniMax-Music-3/resolve/main/vae/minimax_music3_dav.safetensors", | |
| "directory": "vae" | |
| } | |
| ] | |
| }, | |
| "widgets_values": [ | |
| "minimax_music3_dav.safetensors" | |
| ] | |
| }, | |
| { | |
| "id": 10, | |
| "type": "ConditioningZeroOut", | |
| "pos": [ | |
| 1390, | |
| 440 | |
| ], | |
| "size": [ | |
| 230, | |
| 40 | |
| ], | |
| "flags": {}, | |
| "order": 3, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "localized_name": "conditioning", | |
| "name": "conditioning", | |
| "type": "CONDITIONING", | |
| "link": 5 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "CONDITIONING", | |
| "name": "CONDITIONING", | |
| "type": "CONDITIONING", | |
| "links": [ | |
| 7 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "ConditioningZeroOut" | |
| }, | |
| "widgets_values": [] | |
| }, | |
| { | |
| "id": 15, | |
| "type": "EmptyMiniMaxMusic3LatentAudio", | |
| "pos": [ | |
| 1390, | |
| 220 | |
| ], | |
| "size": [ | |
| 350, | |
| 90 | |
| ], | |
| "flags": {}, | |
| "order": 4, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "localized_name": "seconds", | |
| "name": "seconds", | |
| "type": "FLOAT", | |
| "widget": { | |
| "name": "seconds" | |
| }, | |
| "link": 6 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "LATENT", | |
| "name": "LATENT", | |
| "type": "LATENT", | |
| "links": [ | |
| 8 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "EmptyMiniMaxMusic3LatentAudio" | |
| }, | |
| "widgets_values": [ | |
| 120, | |
| 1 | |
| ] | |
| }, | |
| { | |
| "id": 9, | |
| "type": "KSampler", | |
| "pos": [ | |
| 1740, | |
| 220 | |
| ], | |
| "size": [ | |
| 370, | |
| 270 | |
| ], | |
| "flags": {}, | |
| "order": 5, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "localized_name": "model", | |
| "name": "model", | |
| "type": "MODEL", | |
| "link": 9 | |
| }, | |
| { | |
| "localized_name": "positive", | |
| "name": "positive", | |
| "type": "CONDITIONING", | |
| "link": 4 | |
| }, | |
| { | |
| "localized_name": "negative", | |
| "name": "negative", | |
| "type": "CONDITIONING", | |
| "link": 7 | |
| }, | |
| { | |
| "localized_name": "latent_image", | |
| "name": "latent_image", | |
| "type": "LATENT", | |
| "link": 8 | |
| }, | |
| { | |
| "localized_name": "seed", | |
| "name": "seed", | |
| "type": "INT", | |
| "widget": { | |
| "name": "seed" | |
| } | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "LATENT", | |
| "name": "LATENT", | |
| "type": "LATENT", | |
| "links": [ | |
| 10 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "KSampler" | |
| }, | |
| "widgets_values": [ | |
| 42, | |
| "fixed", | |
| 30, | |
| 1.0, | |
| "euler", | |
| "simple", | |
| 1 | |
| ] | |
| }, | |
| { | |
| "id": 12, | |
| "type": "VAEDecodeAudio", | |
| "pos": [ | |
| 2160, | |
| 220 | |
| ], | |
| "size": [ | |
| 230, | |
| 60 | |
| ], | |
| "flags": {}, | |
| "order": 6, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "localized_name": "samples", | |
| "name": "samples", | |
| "type": "LATENT", | |
| "link": 10 | |
| }, | |
| { | |
| "localized_name": "vae", | |
| "name": "vae", | |
| "type": "VAE", | |
| "link": 11 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "AUDIO", | |
| "name": "AUDIO", | |
| "type": "AUDIO", | |
| "links": [ | |
| 12 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0", | |
| "Node name for S&R": "VAEDecodeAudio" | |
| }, | |
| "widgets_values": [] | |
| }, | |
| { | |
| "id": 13, | |
| "type": "MiniMaxMusic3ReferenceAudioEncode", | |
| "pos": [ | |
| 810, | |
| 220 | |
| ], | |
| "size": [ | |
| 520, | |
| 560 | |
| ], | |
| "flags": {}, | |
| "order": 8, | |
| "mode": 0, | |
| "showAdvanced": true, | |
| "inputs": [ | |
| { | |
| "localized_name": "clip", | |
| "name": "clip", | |
| "type": "CLIP", | |
| "link": 1 | |
| }, | |
| { | |
| "localized_name": "reference_encoder", | |
| "name": "reference_encoder", | |
| "type": "MINIMAX_MUSIC3_RVQ_REFERENCE_ENCODER", | |
| "link": 2 | |
| }, | |
| { | |
| "localized_name": "audio", | |
| "name": "audio", | |
| "type": "AUDIO", | |
| "link": 3 | |
| }, | |
| { | |
| "localized_name": "caption", | |
| "name": "caption", | |
| "type": "STRING", | |
| "widget": { | |
| "name": "caption" | |
| } | |
| }, | |
| { | |
| "localized_name": "lyrics", | |
| "name": "lyrics", | |
| "type": "STRING", | |
| "widget": { | |
| "name": "lyrics" | |
| } | |
| }, | |
| { | |
| "localized_name": "seed", | |
| "name": "seed", | |
| "type": "INT", | |
| "widget": { | |
| "name": "seed" | |
| } | |
| }, | |
| { | |
| "localized_name": "reference_interval", | |
| "name": "reference_interval", | |
| "type": "INT", | |
| "widget": { | |
| "name": "reference_interval" | |
| } | |
| }, | |
| { | |
| "localized_name": "cfg_scale", | |
| "name": "cfg_scale", | |
| "type": "FLOAT", | |
| "widget": { | |
| "name": "cfg_scale" | |
| } | |
| }, | |
| { | |
| "localized_name": "top_k", | |
| "name": "top_k", | |
| "type": "INT", | |
| "widget": { | |
| "name": "top_k" | |
| } | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "localized_name": "conditioning", | |
| "name": "conditioning", | |
| "type": "CONDITIONING", | |
| "links": [ | |
| 4, | |
| 5 | |
| ] | |
| }, | |
| { | |
| "localized_name": "seconds", | |
| "name": "seconds", | |
| "type": "FLOAT", | |
| "links": [ | |
| 6 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfyui_open_rvq", | |
| "Node name for S&R": "MiniMaxMusic3ReferenceAudioEncode" | |
| }, | |
| "widgets_values": [ | |
| "1980s heavy metal cover, distorted electric guitars, driving bass, double-kick drums, dramatic arena production", | |
| "[instrumental]", | |
| 299871780, | |
| 5, | |
| 1.5, | |
| 50 | |
| ] | |
| }, | |
| { | |
| "id": 44, | |
| "type": "MiniMaxMusic3RVQReferenceEncoderLoader", | |
| "pos": [ | |
| 40, | |
| 420 | |
| ], | |
| "size": [ | |
| 650, | |
| 100 | |
| ], | |
| "flags": {}, | |
| "order": 9, | |
| "mode": 0, | |
| "inputs": [], | |
| "outputs": [ | |
| { | |
| "localized_name": "reference_encoder", | |
| "name": "reference_encoder", | |
| "type": "MINIMAX_MUSIC3_RVQ_REFERENCE_ENCODER", | |
| "links": [ | |
| 2 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfyui_open_rvq", | |
| "Node name for S&R": "MiniMaxMusic3RVQReferenceEncoderLoader", | |
| "models": [ | |
| { | |
| "name": "minimax_music3_rvq_encoder_v4_169m_autoregressive_depth_recommended.safetensors", | |
| "url": "https://huggingface.co/SimpleTuner/open-rvq-encoder-minimax-music3/resolve/main/encoders/minimax_music3_rvq_encoder_v4_169m_autoregressive_depth_recommended.safetensors", | |
| "directory": "minimax_music3_rvq_encoders" | |
| }, | |
| { | |
| "name": "dav.pth", | |
| "url": "https://huggingface.co/MiniMaxAI/MiniMax-Music3/resolve/main/dav.pth", | |
| "directory": "vae" | |
| } | |
| ] | |
| }, | |
| "widgets_values": [ | |
| "minimax_music3_rvq_encoder_v4_169m_autoregressive_depth_recommended.safetensors", | |
| "dav.pth" | |
| ] | |
| }, | |
| { | |
| "id": 45, | |
| "type": "LoadAudio", | |
| "pos": [ | |
| 40, | |
| 570 | |
| ], | |
| "size": [ | |
| 650, | |
| 100 | |
| ], | |
| "flags": {}, | |
| "order": 10, | |
| "mode": 0, | |
| "inputs": [], | |
| "outputs": [ | |
| { | |
| "localized_name": "AUDIO", | |
| "name": "AUDIO", | |
| "type": "AUDIO", | |
| "links": [ | |
| 3 | |
| ] | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "Node name for S&R": "LoadAudio" | |
| }, | |
| "widgets_values": [ | |
| "reference_audio.flac" | |
| ] | |
| }, | |
| { | |
| "id": 46, | |
| "type": "SaveAudioAdvanced", | |
| "pos": [ | |
| 2480, | |
| 220 | |
| ], | |
| "size": [ | |
| 750, | |
| 160 | |
| ], | |
| "flags": {}, | |
| "order": 11, | |
| "mode": 0, | |
| "inputs": [ | |
| { | |
| "name": "audio", | |
| "type": "AUDIO", | |
| "link": 12 | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "name": "audio", | |
| "type": "AUDIO", | |
| "links": null | |
| } | |
| ], | |
| "properties": { | |
| "cnr_id": "comfy-core", | |
| "ver": "0.31.0" | |
| }, | |
| "widgets_values": [ | |
| "audio/minimax_music3_rvq_reference", | |
| "flac" | |
| ] | |
| } | |
| ], | |
| "links": [ | |
| [ | |
| 1, | |
| 3, | |
| 0, | |
| 13, | |
| 0, | |
| "CLIP" | |
| ], | |
| [ | |
| 2, | |
| 44, | |
| 0, | |
| 13, | |
| 1, | |
| "MINIMAX_MUSIC3_RVQ_REFERENCE_ENCODER" | |
| ], | |
| [ | |
| 3, | |
| 45, | |
| 0, | |
| 13, | |
| 2, | |
| "AUDIO" | |
| ], | |
| [ | |
| 4, | |
| 13, | |
| 0, | |
| 9, | |
| 1, | |
| "CONDITIONING" | |
| ], | |
| [ | |
| 5, | |
| 13, | |
| 0, | |
| 10, | |
| 0, | |
| "CONDITIONING" | |
| ], | |
| [ | |
| 6, | |
| 13, | |
| 1, | |
| 15, | |
| 0, | |
| "FLOAT" | |
| ], | |
| [ | |
| 7, | |
| 10, | |
| 0, | |
| 9, | |
| 2, | |
| "CONDITIONING" | |
| ], | |
| [ | |
| 8, | |
| 15, | |
| 0, | |
| 9, | |
| 3, | |
| "LATENT" | |
| ], | |
| [ | |
| 9, | |
| 6, | |
| 0, | |
| 9, | |
| 0, | |
| "MODEL" | |
| ], | |
| [ | |
| 10, | |
| 9, | |
| 0, | |
| 12, | |
| 0, | |
| "LATENT" | |
| ], | |
| [ | |
| 11, | |
| 7, | |
| 0, | |
| 12, | |
| 1, | |
| "VAE" | |
| ], | |
| [ | |
| 12, | |
| 12, | |
| 0, | |
| 46, | |
| 0, | |
| "AUDIO" | |
| ] | |
| ], | |
| "groups": [], | |
| "definitions": { | |
| "subgraphs": [] | |
| }, | |
| "config": {}, | |
| "extra": { | |
| "ds": { | |
| "scale": 0.72, | |
| "offset": [ | |
| 150, | |
| 100 | |
| ] | |
| }, | |
| "frontendVersion": "1.49.6" | |
| }, | |
| "version": 0.4 | |
| } | |