Files
runpod/comfyui/workflows/text-to-music/musicgen-small-t2m-production-v1.json
Sebastian Krüger f1788f88ca fix: replace PreviewAudio with AudioPlay in MusicGen workflows
Sound Lab's Musicgen_ node outputs AUDIO format that is only compatible with Sound Lab nodes like AudioPlay, not the built-in ComfyUI audio nodes (SaveAudio/PreviewAudio).
2025-11-23 11:20:15 +01:00

152 lines
3.9 KiB
JSON

{
"last_node_id": 2,
"last_link_id": 1,
"nodes": [
{
"id": 1,
"type": "Musicgen_",
"pos": [50, 100],
"size": [400, 300],
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [1],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "Musicgen_"
},
"widgets_values": [
"Upbeat electronic dance music with energetic beats and synthesizer melodies",
30.0,
3.0,
42,
"auto"
],
"title": "MusicGen Small Generator"
},
{
"id": 2,
"type": "AudioPlay",
"pos": [500, 100],
"size": [315, 100],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 1
}
],
"properties": {
"Node name for S&R": "AudioPlay"
},
"title": "API Audio Output"
}
],
"links": [
[1, 1, 0, 2, 0, "AUDIO"]
],
"groups": [],
"config": {},
"extra": {
"workflow_info": {
"name": "MusicGen Small Text-to-Music Production",
"version": "1.2.0",
"description": "Fast music generation using MusicGen Small. Lower quality but fastest generation and minimal VRAM.",
"category": "text-to-music",
"tags": ["musicgen", "small", "t2m", "audio", "production", "fast"],
"requirements": {
"models": ["facebook/musicgen-small"],
"custom_nodes": ["comfyui-sound-lab"],
"vram_min": "4GB",
"vram_recommended": "6GB"
},
"parameters": {
"prompt": {
"node_id": 1,
"widget_index": 0,
"type": "string",
"required": true,
"default": "Upbeat electronic dance music",
"description": "Text description of desired music style, genre, mood, instruments"
},
"duration": {
"node_id": 1,
"widget_index": 1,
"type": "float",
"required": false,
"default": 30.0,
"min": 1.0,
"max": 60.0,
"description": "Duration in seconds (up to 30s recommended for best quality)"
},
"guidance_scale": {
"node_id": 1,
"widget_index": 2,
"type": "float",
"required": false,
"default": 3.0,
"min": 0.0,
"max": 20.0,
"description": "How closely to follow the prompt (3.0 recommended)"
},
"seed": {
"node_id": 1,
"widget_index": 3,
"type": "integer",
"required": false,
"default": 42,
"min": 0,
"max": 2147483647,
"description": "Random seed for reproducibility"
},
"device": {
"node_id": 1,
"widget_index": 4,
"type": "string",
"required": false,
"default": "auto",
"options": ["auto", "cpu"],
"description": "Computation device (auto recommended)"
}
},
"outputs": {
"audio": {
"node_id": 2,
"type": "audio",
"format": "FLAC",
"sample_rate": "32000 Hz",
"channels": "stereo"
}
},
"performance": {
"avg_generation_time": "20-35 seconds for 30s audio",
"vram_usage": "~4-6GB",
"gpu_utilization": "85-95%"
},
"use_cases": [
"Rapid prototyping",
"Low-resource environments",
"Quick background music drafts",
"Testing different prompts quickly"
],
"notes": [
"MusicGen Small is fastest but lowest quality",
"Good for rapid iteration and testing",
"Best results with clear, specific prompts",
"Can specify genre, mood, instruments, tempo",
"Output is 32kHz stereo FLAC format"
]
}
},
"version": 0.4
}