{ "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-453184-input_image-373b128b-4135-48ab-ba6b-d2284eb23fe3.webp" } }, "102": { "class_type": "LoadImage", "inputs": { "image": "dockaiq-input-453184-picture_2-ref-3shot.webp" } }, "103": { "class_type": "LoadImage", "inputs": { "image": "dockaiq-input-453184-picture_3-3880888d-5900-4a22-9749-3f92d848a988-outer.webp" } }, "104": { "class_type": "LoadImage", "inputs": { "image": "dockaiq-input-453184-picture_4-fe29be2e-7395-4eb8-90bc-80feaa9b8bd8-under.webp" } }, "6": { "class_type": "MiniMaxH3ReferenceToVideo", "inputs": { "prompt": " is the location; keep its layout and furnishings, surfaces clear of small objects.\n is — this exact person; keep the same face and hair. is 's clothing sheet. is 's underwear sheet.\n\n is the woman with dark brown long wavy hair. She is lying on her back on the bed, close to the viewer, facing the camera, wearing a black sheer chiffon maid dress zipped up at the back, a white frilly half apron tied at the waist with the ribbon knotted at the back, a white lace maid headband set on her head, black sheer thigh-high stockings pulled up from the toes over the calves, and black patent mary jane heels; underneath, hidden, a black lace underwire bra and black lace high-cut panties. During this shot the dress is peeled away: the sheer chiffon slides off her shoulders and down her arms, the apron ribbon comes undone and the apron falls aside, the headband is lifted off her head, the bra is unhooked and taken off, the panties are drawn down her legs, and the heels are slipped off her feet, so the black lace drops away to her thighs and the removed garments gather on the bed below her. Her stockings are pulled down and bunched at the ankles, toes brushing the bedsheet. Her bare skin is uncovered as the layers come off, and she is laid back onto the bed.\n\nThe viewer, a man, is the camera: this is his point of view, and his face, head, torso and hips are never in frame. Only his hands enter at the edges of the frame, touching her waist and her thighs, and the worn black hoodie sleeve and the faded brown leather bracelet on his wrist are the only clothing seen on him.\n\nCamera: first-person point of view from the viewer's own eyes, looking down at lying on her back one body-length away, facing the camera. The camera stays at the height of a person lying down, and moves only as the viewer's head moves — a slow tilt down and a slight lean closer as the clothes are peeled away, ending on her bare shoulders and the black lace sliding down her thighs, still from the same eye position, no push-in to her face and no cut to a close-up.\n\nSubtle early reflections from nearby walls.\nThe room is naturally embedded in the environment rather than sounding close-miked or studio-recorded.\nSoft environmental ambience continuously fills the space.\nVery subtle natural reverberation.\nNo artificial narration quality.\n\nNo dialogue, no speech, no lip movement from anyone. No music, no lyrics, no singing, no narration, no subtitles, no captions, no text overlays, no watermark, no extra people, no camera shake, no jump cuts, no scene changes, no split screen.\nThe soundtrack is the room itself and nothing else: only the natural ambient sound of this place, no music. It sounds like a real place recorded on location, not a studio.", "width": 384, "height": 672, "length": 158, "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": 1497426091 } }, "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_j453184", "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": "ccb27080" }, "class_type": "DockContentWatermark", "_meta": { "title": "법정 표시 워터마크 (t_88479c752c44)" } } }