{
  "1": {
    "class_type": "UNETLoader",
    "inputs": {
      "unet_name": "minimax_h3_ref2va_pruned_int8_convrot.safetensors",
      "weight_dtype": "default"
    }
  },
  "m0": {
    "class_type": "MiniMaxH3TurboLoRA",
    "inputs": {
      "lora_name": "minimax_h3_fl2v_lightx2v_turbo_8step_v1.0_comfy.safetensors",
      "strength": 1.0,
      "low_vram": false,
      "model": [
        "1",
        0
      ]
    },
    "_comment": "lightx2v Minimax-h3 Turbo **8step v1.0** 단독 @1.0 (2026-08-12 `t_4e40bb6cf50d` · CEO 승격 지시). 구 `ckpt850`(4step) 에서 교체 — 격자 4판 실측에서 **8step·캐시ON 이 최적**이었다: 6step·캐시OFF 대비 **80초 빠르고**(521~525s vs 601s) 오디오·화질이 같거나 낫다. ★6step·캐시ON 은 **오디오가 갈라진다**(CEO 육안 \"목소리 갈라지네\") — 속도만 보고 6step 으로 내리지 말 것."
  },
  "L2": {
    "class_type": "LoraLoaderModelOnly",
    "inputs": {
      "lora_name": "MysticXXX_MMH3-V4.safetensors",
      "strength_model": 0.4,
      "model": [
        "m0",
        0
      ]
    },
    "_comment": "Mystic XXX `MysticXXX_MMH3-V4` **0.4** — 2026-09-06 `t_0ae98911f9cb` 신설 슬롯. 체인은 `m0(터보) → L2(mystic 0.4) → m1(sage)`. ★★2026-09-10 CEO 판정으로 **realism(구 L1) 을 이 판에서 걷었다**(`t_2ac5b03c5db2`) — 사유 = *\"mystic 과 realism 이 같이 적용되면 영상 품질이 망가지더라. 각각 쓰면 괜찮은데\"*. ⇒ 종전 이 자리에 있던 *\"realism 을 빼고 그 칸을 쓰지 않았다\"* 는 **그 판정 이전의 입장**이라 걷었다 (이 필드는 실행 `workflow.json` 에까지 실리므로, 낡은 입장을 현재형으로 남기면 읽는 사람이 **누락으로 읽고 되넣는다**). ★realism 자체가 기각된 게 아니라 **Mystic 과의 동시 적용**이 기각됐다. ★값 0.4 의 근거 = 형제 `ref2va-minimax-h3-mystic-5090-1` 의 저작값과 같게 둔다(같은 파일을 두 판이 다른 강도로 쓰면 「어느 쪽이 정본인가」가 생긴다). 제작자 권장은 0.5~0.9 라 우리 값은 그 아래이고, 강도 확정은 CEO 육안 별건이다. ★끄려면 `spec_override.toggles {\"lora_2\": false}` — 그러면 러너 splice 가 `m1.model` 을 `[\"m0\", 0]` 로 되돌려 **LoRA 0장(터보만)** 체인이 된다."
  },
  "m1": {
    "class_type": "MiniMaxH3MemoryEfficientSageAttentionPatch",
    "inputs": {
      "model": [
        "L2",
        0
      ]
    }
  },
  "2": {
    "class_type": "CLIPLoader",
    "inputs": {
      "clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
      "type": "minimax",
      "device": "default"
    }
  },
  "3": {
    "class_type": "VAELoader",
    "inputs": {
      "vae_name": "minimax_h3_video_vae_fp16.safetensors"
    }
  },
  "4": {
    "class_type": "VAELoader",
    "inputs": {
      "vae_name": "minimax_h3_audio_vae_fp32.safetensors"
    }
  },
  "101": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457413-input_image-373b128b-4135-48ab-ba6b-d2284eb23fe3.webp"
    }
  },
  "102": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457413-picture_2-ref-3shot.webp"
    }
  },
  "103": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457413-picture_3-3880888d-5900-4a22-9749-3f92d848a988-outer.webp"
    }
  },
  "104": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457413-picture_4-fe29be2e-7395-4eb8-90bc-80feaa9b8bd8-under.webp"
    }
  },
  "6": {
    "class_type": "MiniMaxH3ReferenceToVideo",
    "inputs": {
      "prompt": "<Picture 1> is the location; keep its layout and furnishings, surfaces clear of small objects.\n<Picture 2> is <Subject 1> — this exact person; keep the same face and hair. <Picture 3> is <Subject 1>'s clothing sheet. <Picture 4> is <Subject 1>'s underwear sheet.\n\n<Subject 1> is the woman with dark brown long wavy hair. She is standing in front of the camera in the room, facing the camera, her coat already set on the chair, one hand up adjusting the white lace maid headband, at one arm's length from the viewer, wearing the black sheer chiffon maid dress, the white frilly half apron, the white lace maid headband, the black sheer thigh-high stockings and the black patent mary jane heels in <Picture 3>, over the black lace underwire bra and the black lace high-cut panties in <Picture 4>.\n\nThe viewer, a man, is the camera: his eyes are the lens, and his face, head, torso and hips are never in frame. Only his right arm and hand enter the frame from the lower edge, reaching out to set the camera down on the floor beside the bed, and later closing around <Subject 1>'s wrist. He wears only the worn leather bracelet with the faded brown strap on that wrist; his chest is bare and he is bare from the waist down.\n\n[SHOT 1]\n\nFirst-person POV from the viewer's own eyes, at one arm's length from <Subject 1> in the small room, the bed low and close on the right, the chair with her coat on it behind her. The camera holds at the viewer's eye height and moves only as his head moves — a small tilt down as his hand comes into the lower frame and sets the camera on the floor beside the bed, then a slow turn to the right and a step forward as he reaches out and takes <Subject 1>'s wrist. She is standing in front of the camera, facing the camera, adjusting her headband; when his hand closes on her wrist she turns toward the bed and walks with him, not pulled but walking the same pace, smiling, her free hand keeping the apron from swinging. The camera follows her at the same distance, staying level with her shoulder, never pushing in on her face and never cutting to a closer angle.\n\nThe viewer says, off-screen, his mouth never in frame: <d>[Korean] 손으로 해줘. 천천히.</d>\n\n<Subject 1> (<Picture 2>) is the ONLY one who speaks in this shot, speaking to the viewer as she walks beside him, turning her head toward the camera, amused and teasing, a small laugh under the words: <d>[Korean] 어머, 촬영 끝나니까 성질이 급해지셨네. 네네, 알겠어요.</d>\n\nMatch visible mouth motion to each spoken phrase, then let the mouth rest naturally between phrases. Speak the line as one flowing thought, with natural breath spacing and one brief hesitation before the agreement.\n\nSubtle early reflections from nearby walls. The dialogue is naturally embedded in the environment rather than sounding close-miked or studio-recorded. Soft environmental ambience continuously fills the space. Very subtle natural reverberation. No artificial narration quality.\n\nDialogue and faint room tone only. No music, no lyrics, no singing, no subtitles, no captions, no text overlays, no watermark, no extra people, no camera shake, no jump cuts, no split screen, no scene changes.",
      "width": 512,
      "height": 896,
      "length": 345,
      "ref_image_size": "match",
      "clip": [
        "2",
        0
      ],
      "vae": [
        "3",
        0
      ],
      "audio_vae": [
        "4",
        0
      ],
      "ref_images.ref_image_0": [
        "101",
        0
      ],
      "ref_images.ref_image_1": [
        "102",
        0
      ],
      "ref_images.ref_image_2": [
        "103",
        0
      ],
      "ref_images.ref_image_3": [
        "104",
        0
      ]
    }
  },
  "7": {
    "class_type": "BasicGuider",
    "inputs": {
      "model": [
        "mS",
        0
      ],
      "conditioning": [
        "6",
        0
      ]
    }
  },
  "8": {
    "inputs": {
      "sampler_name": "er_sde"
    },
    "class_type": "KSamplerSelect",
    "_meta": {
      "title": "KSampler (선택)"
    }
  },
  "9": {
    "class_type": "BasicScheduler",
    "inputs": {
      "scheduler": "beta",
      "steps": 8,
      "denoise": 1.0,
      "model": [
        "mS",
        0
      ]
    }
  },
  "10": {
    "class_type": "RandomNoise",
    "inputs": {
      "noise_seed": 4256990
    }
  },
  "11": {
    "class_type": "SamplerCustomAdvanced",
    "inputs": {
      "noise": [
        "10",
        0
      ],
      "guider": [
        "7",
        0
      ],
      "sampler": [
        "8",
        0
      ],
      "sigmas": [
        "9",
        0
      ],
      "latent_image": [
        "6",
        1
      ]
    }
  },
  "12": {
    "class_type": "VAEDecode",
    "inputs": {
      "samples": [
        "11",
        0
      ],
      "vae": [
        "vb",
        0
      ]
    }
  },
  "13": {
    "class_type": "VAEDecodeAudio",
    "inputs": {
      "samples": [
        "11",
        0
      ],
      "vae": [
        "4",
        0
      ]
    }
  },
  "14": {
    "class_type": "CreateVideo",
    "inputs": {
      "fps": 24,
      "bit_depth": 8,
      "images": [
        "wm",
        0
      ],
      "audio": [
        "13",
        0
      ]
    }
  },
  "15": {
    "class_type": "SaveVideo",
    "inputs": {
      "filename_prefix": "h3_r2v_v384_j457413",
      "format": "auto",
      "video": [
        "14",
        0
      ],
      "codec": "auto"
    }
  },
  "vb": {
    "class_type": "H3VideoVAEBatchDecode",
    "inputs": {
      "vae": [
        "3",
        0
      ],
      "enabled": true
    }
  },
  "mL": {
    "inputs": {
      "head_chunks": 4,
      "model": [
        "m1",
        0
      ]
    },
    "class_type": "MiniMaxLowVRAMAttention",
    "_meta": {
      "title": "MiniMax H3 Low VRAM Attention"
    }
  },
  "mC": {
    "inputs": {
      "chunks": 2,
      "seq_threshold": 4096,
      "model": [
        "mL",
        0
      ]
    },
    "class_type": "MiniMaxChunkFeedForward",
    "_meta": {
      "title": "MiniMax H3 Chunk FeedForward"
    }
  },
  "mS": {
    "inputs": {
      "shift_video": 12.0,
      "shift_audio": 6.0,
      "model": [
        "mC",
        0
      ]
    },
    "class_type": "MiniMaxH3SigmaShift",
    "_meta": {
      "title": "ModelSamplingMiniMaxH3"
    }
  },
  "wm": {
    "inputs": {
      "images": [
        "12",
        0
      ],
      "line1": "AI",
      "line2": "yusti.net",
      "height_px": 12,
      "alpha": 0.85,
      "margin_px": 13,
      "shadow_px": 1,
      "line3": "d29a5698"
    },
    "class_type": "DockContentWatermark",
    "_meta": {
      "title": "법정 표시 워터마크 (t_88479c752c44)"
    }
  }
}