ComfyUI-Prompt-Calibrator/workflow/workflow_ltx_audio.json

{
  "id": "ltx-audio-relay",
  "last_node_id": 4,
  "last_link_id": 4,
  "nodes": [
    {
      "id": 1,
      "type": "LoadImage",
      "pos": [
        40,
        40
      ],
      "size": [
        320,
        380
      ],
      "flags": {},
      "order": 0,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
            1
          ]
        },
        {
          "name": "MASK",
          "type": "MASK",
          "links": null
        }
      ],
      "properties": {
        "Node name for S&R": "LoadImage"
      },
      "widgets_values": [
        "reference.png",
        "image"
      ]
    },
    {
      "id": 3,
      "type": "CalibratorText",
      "pos": [
        40,
        460
      ],
      "size": [
        360,
        300
      ],
      "flags": {},
      "order": 1,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "text",
          "type": "STRING",
          "links": [
            3
          ]
        }
      ],
      "properties": {
        "Node name for S&R": "CalibratorText"
      },
      "widgets_values": [
        "You are an expert prompt engineer for the LTX-2.3 video model, generating a\nmulti-segment \"Prompt Relay\" timeline TIMED TO AUDIO. Output ONLY valid JSON — no\nmarkdown, no code fences, no text before or after.\n\nYou are given:\n- IMAGE 1 = the REFERENCE subject/scene. Use it ONLY for persistent visual appearance\n  (subject's look, setting, lighting, color palette, style) in global_prompt.\n- IMAGE 2 = the AUDIO ENERGY WAVEFORM (energy envelope with segment boundaries and beat\n  markers). Read the overall energy shape and where it peaks.\n- An \"AUDIO GUIDE\" text block: per-segment start, duration_s, frames (already snapped to\n  8n+1), energy level, stage hint, per-segment NOTE, and GLOBAL NOTES.\n\nMatch this schema exactly:\n\n{\n  \"fps\": 24,\n  \"global_prompt\": \"string\",\n  \"negative_prompt\": \"string\",\n  \"beats\": [\n    {\n      \"segment\": 1,\n      \"duration_s\": 5,\n      \"frames\": 121,\n      \"camera\": \"string\",\n      \"delta\": \"string\",\n      \"sound\": \"string\",\n      \"dialogue\": \"string\",\n      \"prompt\": \"string\"\n    }\n  ]\n}\n\nRules:\n- fps: take from the AUDIO GUIDE.\n- global_prompt: one present-tense paragraph with ALL persistent elements taken from\n  IMAGE 1 — subject's physical appearance (age, hair, clothing as visual cues), setting,\n  lighting, color palette, style — plus the sustained ambient/audio layer. No camera\n  moves. Never repeated in beats.\n- negative_prompt: \"shaky, glitchy, low quality, worst quality, deformed, distorted,\n  disfigured, motion smear, motion artifacts, fused fingers, bad anatomy, ugly, static\".\n- beats: EXACTLY ONE beat per AUDIO GUIDE segment, in order. Copy that segment's\n  \"segment\", \"duration_s\", and \"frames\" verbatim (do not recompute).\n- Beat 1: \"delta\" = the static visible starting state only; \"camera\" = \"static hold\".\n- Every later beat: \"delta\" = ONLY what CHANGES from the previous beat. Never repeat the\n  global_prompt or earlier beats.\n- MOTION FROM AUDIO: drive each beat's motion from its energy — higher energy => faster\n  motion and bigger camera moves; lower energy => slower, settle. Follow the energy\n  envelope across the timeline (establish -> build -> peak -> settle), putting the release\n  on the final segment.\n- NOTES OVERRIDE: if a segment has a NOTE, that instruction OVERRIDES the energy default\n  for that beat (e.g. NOTE \"slow\" on a HIGH-energy segment => slow, deliberate motion).\n  Apply GLOBAL NOTES throughout.\n- \"camera\" starts with a camera verb (push in, pan, arc, handheld drift, hold).\n- \"sound\" = short sound cue; \"dialogue\" = spoken line in quotes or \"\".\n- \"prompt\" = the final assembled beat text in order: camera, then delta action, then any\n  dialogue/sound — present tense, concrete on-screen verbs, no emotion labels. Ready to paste.\n"
      ]
    },
    {
      "id": 2,
      "type": "AudioWaveSegments",
      "pos": [
        40,
        800
      ],
      "size": [
        420,
        320
      ],
      "flags": {},
      "order": 2,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "waveform_image",
          "type": "IMAGE",
          "links": [
            2
          ]
        },
        {
          "name": "audio_summary",
          "type": "STRING",
          "links": [
            4
          ]
        },
        {
          "name": "audio",
          "type": "AUDIO",
          "links": null
        }
      ],
      "properties": {
        "Node name for S&R": "AudioWaveSegments"
      },
      "widgets_values": [
        "audio.wav",
        24,
        6,
        "",
        "[]"
      ]
    },
    {
      "id": 4,
      "type": "QwenVLImageJudge",
      "pos": [
        540,
        40
      ],
      "size": [
        420,
        640
      ],
      "flags": {},
      "order": 3,
      "mode": 0,
      "inputs": [
        {
          "name": "reference_image",
          "type": "IMAGE",
          "link": 1
        },
        {
          "name": "generated_image",
          "type": "IMAGE",
          "link": 2,
          "shape": 7
        },
        {
          "name": "axes",
          "type": "STRING",
          "link": null,
          "shape": 7
        },
        {
          "name": "reference_description",
          "type": "STRING",
          "link": null,
          "shape": 7
        },
        {
          "name": "system_prompt",
          "type": "STRING",
          "link": 3,
          "shape": 7
        },
        {
          "name": "user_prompt",
          "type": "STRING",
          "link": 4,
          "shape": 7
        }
      ],
      "outputs": [
        {
          "name": "overall_score",
          "type": "FLOAT",
          "links": null
        },
        {
          "name": "axis_scores_json",
          "type": "STRING",
          "links": null
        },
        {
          "name": "analysis",
          "type": "STRING",
          "links": null
        },
        {
          "name": "raw",
          "type": "STRING",
          "links": null
        },
        {
          "name": "report_path",
          "type": "STRING",
          "links": null
        }
      ],
      "properties": {
        "Node name for S&R": "QwenVLImageJudge"
      },
      "widgets_values": [
        "chat",
        "general",
        "(manual — use model_path below)",
        "3.5-9b",
        "bf16",
        3072,
        0.4,
        false,
        false,
        true,
        true,
        true,
        "/media/p5/Comfyui/output/ltx",
        "ltx"
      ]
    }
  ],
  "links": [
    [
      1,
      1,
      0,
      4,
      0,
      "IMAGE"
    ],
    [
      2,
      2,
      0,
      4,
      1,
      "IMAGE"
    ],
    [
      3,
      3,
      0,
      4,
      4,
      "STRING"
    ],
    [
      4,
      2,
      1,
      4,
      5,
      "STRING"
    ]
  ],
  "groups": [],
  "config": {},
  "extra": {},
  "version": 0.4
}