{
  "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-457654-input_image-c35ca322-46b1-4bcd-ae5f-72496bdf805f.webp"
    }
  },
  "102": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457654-picture_2-ref-3shot.webp"
    }
  },
  "103": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457654-picture_3-3880888d-5900-4a22-9749-3f92d848a988-outer.webp"
    }
  },
  "104": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-457654-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 kneeling astride the viewer on the wooden floor in front of the mirrored wall, straddling him with her hands on his chest and her hips lowered, riding him with her hips moving in a slow rhythm, facing the camera, wearing the white lace maid headband in <Picture 3> and the black lace underwire bra in <Picture 4>, its straps slipped off both shoulders and hanging against her arms with the cups hanging loose — her chest bare, bare from the waist down.\n\nThe viewer, a man, lies on his back on the wooden floor beneath her, looking up at her, his body pressed close against hers. His face, head, torso and hips are never in frame — the camera is where his eyes are. Only his chest is at the edge of the frame, under her hands.\n\n[SHOT 1] The camera is the viewer's own point of view, low at his eye level as he lies on his back, looking straight up at her. She is directly above him, close, facing the camera, her face and shoulders filling the upper frame. The camera moves only as the viewer's head moves — a slow, slight push upward toward her as she leans down over him, no separate move toward her face and no cut to a close-up.\n\nShe lowers her hips slowly and rises again, her waist taking up a steady rhythm, the loose bra cups rising and falling with her. She closes her eyes, opens them, and catches the viewer's gaze in the mirror behind him. Then she presses her nails into his chest and sinks her hips deeper; the wooden floor creaks and the two shadows in the mirror overlap and sway.\n\n<Subject 1> (<Picture 2>) is the ONLY one who speaks in this shot, speaking to the viewer with her face turned away from the camera, her eyes on the mirror rather than on the lens, her tone low, teasing and possessive at first, then firm and almost warning: <d>[Korean] …업무 연장이니까. 진짜 — 이런 표정은 회사에서 보여주지 마요. 나만 보는 거예요.</d>\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\nNo text overlays, no subtitles, no watermark, no extra people in the background, no camera shake, no jump cuts, no third-person angle, no over-the-shoulder shot, no mirror reflection of the viewer's face.",
      "width": 512,
      "height": 896,
      "length": 294,
      "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": 17270396
    }
  },
  "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_j457654",
      "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": "a43c469e"
    },
    "class_type": "DockContentWatermark",
    "_meta": {
      "title": "법정 표시 워터마크 (t_88479c752c44)"
    }
  }
}