{
  "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-460445-input_image-373b128b-4135-48ab-ba6b-d2284eb23fe3.webp"
    }
  },
  "102": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-460445-picture_2-ref-3shot.webp"
    }
  },
  "103": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-460445-picture_3-3880888d-5900-4a22-9749-3f92d848a988-outer.webp"
    }
  },
  "104": {
    "class_type": "LoadImage",
    "inputs": {
      "image": "dockaiq-input-460445-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 sitting on the edge of the bed at the center of the frame, legs crossed one over the other, the white frilly half apron hem pulled up and pinned over her lap with one hand, her back turned to the camera, 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>, with the black lace underwire bra and the black lace high-cut panties in <Picture 4> hidden underneath.\n\nThe viewer, a man, is standing close behind her at the back of the bed, his hands at the apron ribbon. His face, head, torso and hips are never in frame — the camera is his place. Only his hands enter the frame from the foreground, at her waist and at the ribbon of the apron.\n\nThe viewer says, off-screen, his mouth never in frame: <d>[Korean] 다음 컷은 앞치마 빼고 가자. 뒤에 리본 내가 풀어줄게.</d>\n\n[SHOT 1]\n\nThis is the viewer's point of view — the camera sits at his two eyes, there is no third position beside, behind or over the shoulder. <Subject 1> is close to those eyes, seen from behind, her back and the apron ribbon filling the frame, her face turned away from the camera and never visible. The camera only moves as much as the viewer's head actually moves — a slight tilt and a small lean in.\n\n<Subject 1> sits on the edge of the bed, legs crossed one over the other, the apron hem pulled up and pinned over her lap with one hand. She arches her back slightly toward the viewer and waits, holding still, while the viewer's hands work the ribbon loose at her back. The bow comes undone and the white frilly half apron slips off her; she lifts it away and lays it down on the bed beside her, and the thin sheer chiffon of the dress shows the black lace bra line underneath. She shows no surprise — she straightens her waist and smooths the skirt hem once with her fingertips.\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 view, no mirror.",
      "width": 512,
      "height": 896,
      "length": 226,
      "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": 137611772
    }
  },
  "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_j460445",
      "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": "fe4f8658"
    },
    "class_type": "DockContentWatermark",
    "_meta": {
      "title": "법정 표시 워터마크 (t_88479c752c44)"
    }
  }
}