runpod/comfyui/workflows/text-to-music/diffrhythm-simple-t2m-v1.json

{
  "last_node_id": 3,
  "last_link_id": 2,
  "nodes": [
    {
      "id": 1,
      "type": "DiffRhythmRun",
      "pos": [100, 100],
      "size": [400, 400],
      "flags": {},
      "order": 0,
      "mode": 0,
      "outputs": [
        {
          "name": "AUDIO",
          "type": "AUDIO",
          "links": [1, 2]
        }
      ],
      "properties": {
        "Node name for S&R": "DiffRhythmRun"
      },
      "widgets_values": [
        false,
        "cfm_model_v1_2.pt",
        "Upbeat electronic dance music with energetic beats and synthesizer melodies",
        "",
        "[-1, 20], [60, -1]",
        "euler",
        30,
        4,
        "speed",
        true,
        42
      ],
      "title": "DiffRhythm Text-to-Music (95s)"
    },
    {
      "id": 2,
      "type": "PreviewAudio",
      "pos": [600, 100],
      "size": [300, 100],
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [
        {
          "name": "audio",
          "type": "AUDIO",
          "link": 1
        }
      ],
      "properties": {
        "Node name for S&R": "PreviewAudio"
      },
      "title": "Preview Audio"
    },
    {
      "id": 3,
      "type": "SaveAudio",
      "pos": [600, 250],
      "size": [300, 100],
      "flags": {},
      "order": 2,
      "mode": 0,
      "inputs": [
        {
          "name": "audio",
          "type": "AUDIO",
          "link": 2
        }
      ],
      "properties": {
        "Node name for S&R": "SaveAudio"
      },
      "widgets_values": [
        "diffrhythm_output"
      ],
      "title": "Save Audio"
    }
  ],
  "links": [
    [1, 1, 0, 2, 0, "AUDIO"],
    [2, 1, 0, 3, 0, "AUDIO"]
  ],
  "groups": [],
  "config": {},
  "extra": {
    "workflow_info": {
      "name": "DiffRhythm Simple Text-to-Music v1",
      "description": "Basic text-to-music generation using DiffRhythm 1.2 (95 seconds)",
      "version": "1.0.0",
      "author": "valknar@pivoine.art",
      "category": "text-to-music",
      "tags": ["diffrhythm", "music-generation", "text-to-music", "95s"],
      "requirements": {
        "custom_nodes": ["ComfyUI_DiffRhythm"],
        "models": ["ASLP-lab/DiffRhythm-1_2", "ASLP-lab/DiffRhythm-vae", "OpenMuQ/MuQ-MuLan-large", "OpenMuQ/MuQ-large-msd-iter", "FacebookAI/xlm-roberta-base"],
        "vram_min": "12GB",
        "vram_recommended": "16GB",
        "system_deps": ["espeak-ng"]
      },
      "usage": {
        "model": "cfm_model_v1_2.pt (DiffRhythm 1.2 - 95s generation)",
        "style_prompt": "Text description of the desired music style, mood, and instruments",
        "unload_model": "Boolean to unload model after generation (default: true)",
        "odeint_method": "ODE solver: euler, midpoint, rk4, implicit_adams (default: euler)",
        "steps": "Number of diffusion steps: 1-100 (default: 30)",
        "cfg": "Classifier-free guidance scale: 1-10 (default: 4)",
        "quality_or_speed": "Generation mode: quality or speed (default: speed)",
        "seed": "Random seed for reproducibility (default: 42)",
        "edit": "Enable segment editing mode (default: false)",
        "edit_segments": "Segments to edit when edit=true (default: [-1, 20], [60, -1])"
      },
      "notes": [
        "This workflow uses DiffRhythm 1.2 for 95-second music generation",
        "All parameters except model and style_prompt are optional",
        "Supports English and Chinese text prompts",
        "Generation time: ~30-60 seconds on RTX 4090",
        "Can optionally connect MultiLineLyricsDR node for lyrics input"
      ]
    }
  },
  "version": 0.4
}