{
  "last_node_id": 5,
  "last_link_id": 4,
  "nodes": [
    {
      "id": 1,
      "type": "CheckpointLoaderSimple",
      "pos": [100, 100],
      "size": [315, 98],
      "flags": {},
      "order": 0,
      "mode": 0,
      "outputs": [
        {
          "name": "MODEL",
          "type": "MODEL",
          "links": [1]
        },
        {
          "name": "CLIP",
          "type": "CLIP",
          "links": [2]
        },
        {
          "name": "VAE",
          "type": "VAE",
          "links": []
        }
      ],
      "properties": {
        "Node name for S&R": "CheckpointLoaderSimple"
      },
      "widgets_values": [
        "ace_step_v1_3.5b.safetensors"
      ],
      "title": "Load ACE Step Checkpoint"
    },
    {
      "id": 2,
      "type": "CLIPTextEncode",
      "pos": [500, 100],
      "size": [400, 200],
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 2
        }
      ],
      "outputs": [
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
          "links": [3]
        }
      ],
      "properties": {
        "Node name for S&R": "CLIPTextEncode"
      },
      "widgets_values": [
        "energetic rock, 140 BPM, electric guitar drums bass, powerful, D minor\n\n[verse]\nBreaking through the walls tonight\nFacing all my fears head on\n[chorus]\nWe rise together, burning bright\nNothing can hold us down for long\n[bridge]\nThrough the fire, through the rain\n[outro]"
      ],
      "title": "Text Prompt (Tags + Lyrics)"
    },
    {
      "id": 3,
      "type": "EmptyLatentAudio",
      "pos": [500, 350],
      "size": [315, 106],
      "flags": {},
      "order": 2,
      "mode": 0,
      "outputs": [
        {
          "name": "LATENT",
          "type": "LATENT",
          "links": [4]
        }
      ],
      "properties": {
        "Node name for S&R": "EmptyLatentAudio"
      },
      "widgets_values": [
        60,
        512,
        1
      ],
      "title": "Empty Latent (60 seconds)"
    },
    {
      "id": 4,
      "type": "KSampler",
      "pos": [900, 100],
      "size": [315, 262],
      "flags": {},
      "order": 3,
      "mode": 0,
      "inputs": [
        {
          "name": "model",
          "type": "MODEL",
          "link": 1
        },
        {
          "name": "positive",
          "type": "CONDITIONING",
          "link": 3
        },
        {
          "name": "negative",
          "type": "CONDITIONING",
          "link": null
        },
        {
          "name": "latent_image",
          "type": "LATENT",
          "link": 4
        }
      ],
      "outputs": [
        {
          "name": "LATENT",
          "type": "LATENT",
          "links": [5]
        }
      ],
      "properties": {
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
        123,
        "randomize",
        27,
        7.0,
        "euler",
        "normal",
        1.0
      ],
      "title": "Sampler (27 steps, cfg=7.0)"
    },
    {
      "id": 5,
      "type": "VAEDecode",
      "pos": [1300, 100],
      "size": [210, 46],
      "flags": {},
      "order": 4,
      "mode": 0,
      "inputs": [
        {
          "name": "samples",
          "type": "LATENT",
          "link": 5
        },
        {
          "name": "vae",
          "type": "VAE",
          "link": null
        }
      ],
      "outputs": [
        {
          "name": "AUDIO",
          "type": "AUDIO",
          "links": [6]
        }
      ],
      "properties": {
        "Node name for S&R": "VAEDecode"
      },
      "title": "Decode Audio"
    },
    {
      "id": 6,
      "type": "SaveAudio",
      "pos": [1550, 100],
      "size": [315, 58],
      "flags": {},
      "order": 5,
      "mode": 0,
      "inputs": [
        {
          "name": "audio",
          "type": "AUDIO",
          "link": 6
        }
      ],
      "properties": {
        "Node name for S&R": "SaveAudio"
      },
      "widgets_values": [
        "acestep_simple_output"
      ],
      "title": "Save Audio"
    }
  ],
  "links": [
    [1, 1, 0, 4, 0, "MODEL"],
    [2, 1, 1, 2, 0, "CLIP"],
    [3, 2, 0, 4, 1, "CONDITIONING"],
    [4, 3, 0, 4, 3, "LATENT"],
    [5, 4, 0, 5, 0, "LATENT"],
    [6, 5, 0, 6, 0, "AUDIO"]
  ],
  "groups": [],
  "config": {},
  "extra": {
    "workflow_info": {
      "name": "ACE Step Simple Text-to-Music v1",
      "description": "Basic text-to-music generation using ACE Step with native ComfyUI nodes (60 seconds)",
      "version": "1.0.0",
      "author": "valknar@pivoine.art",
      "category": "text-to-music",
      "tags": ["acestep", "music-generation", "text-to-music", "simple", "60s"],
      "requirements": {
        "models": ["ace_step_v1_3.5b.safetensors (Comfy-Org/ACE-Step_ComfyUI_repackaged)"],
        "vram_min": "8GB",
        "vram_recommended": "16GB",
        "custom_nodes": []
      },
      "usage": {
        "checkpoint": "ace_step_v1_3.5b.safetensors",
        "prompt_format": "Tags + Lyrics with section markers",
        "tags": "style, tempo (BPM), instruments, mood, key/scale",
        "lyrics_format": "[verse], [chorus], [bridge], [outro], [inst] sections",
        "duration": "60 seconds (adjustable via EmptyLatentAudio)",
        "steps": "27 (default, quality-speed balance)",
        "cfg_scale": "7.0 (classifier-free guidance)",
        "seed": "123 or randomize for variation"
      },
      "performance": {
        "generation_time": "~2 seconds on RTX 4090 (30x real-time)",
        "vram_usage": "~8-12GB during generation",
        "quality": "High-quality coherent music with lyric alignment"
      },
      "notes": [
        "ACE Step is 15x faster than LLM baselines with superior structural coherence",
        "Supports 19 languages - use language tags like [en], [zh], [ja], [ko]",
        "For multi-language: Prefix lyrics with language code",
        "BPM range: 60-180, optimal 90-140",
        "Key signatures: Major/minor scales work best",
        "Use [inst] for instrumental sections without lyrics",
        "Increase steps to 35-50 for higher quality (slower)",
        "Lower CFG (4-6) for more creative, higher (8-10) for faithful to prompt"
      ],
      "examples": {
        "rock_example": {
          "tags": "energetic rock, 140 BPM, electric guitar drums bass, powerful, D minor",
          "lyrics": "[verse]\\nBreaking through the walls tonight\\n[chorus]\\nWe rise together, burning bright"
        },
        "pop_example": {
          "tags": "upbeat pop, 120 BPM, synth piano drums, cheerful happy, C major",
          "lyrics": "[verse]\\nSunshine on a summer day\\n[chorus]\\nDancing all our cares away"
        },
        "ballad_example": {
          "tags": "emotional ballad, 70 BPM, piano strings, melancholic sad, A minor",
          "lyrics": "[verse]\\nMemories of yesterday\\n[chorus]\\nWishing you were here to stay"
        }
      }
    }
  },
  "version": 0.4
}