{
 "2568": {
  "inputs": {
   "frame_rate": [
    "2730",
    8
   ],
   "codec": "Auto",
   "container": "MP4",
   "bit_depth": "Auto",
   "quality": 21,
   "log_level": "Standard",
   "pingpong": false,
   "save_metadata": true,
   "filename_prefix": "video/%date:yyyy-MM-dd%/%date:hhmmss%",
   "save_output": true,
   "pass_frames": false,
   "crop_to_audio": false,
   "audio_codec": "Auto",
   "audio_bitrate": "192k",
   "save_first_frame": false,
   "save_last_frame": false,
   "images": [
    "1512:2677",
    0
   ],
   "audio": [
    "1512:2675",
    0
   ]
  },
  "class_type": "DaSiWa_EnhancedVideoCombine",
  "_meta": {
   "title": "DaSiWa Enhanced Video Combine"
  }
 },
 "2678": {
  "inputs": {
   "stack_data": "[{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1},{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1},{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1},{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1},{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1},{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1},{\"on\":true,\"lora\":\"None\",\"str\":1,\"vs\":1,\"as\":1}]",
   "model_type": "Basic",
   "model": [
    "2730",
    5
   ],
   "clip": [
    "1512:2587",
    0
   ],
   "use_cache": false
  },
  "class_type": "DaSiWa_LTX2LoraLoader",
  "_meta": {
   "title": "DaSiWa Advanced LoRA Loader"
  }
 },
 "2730": {
  "inputs": {
   "mode": "REF2VA",
   "prompt": "subject_definitions:\n<Subject 1> is the young Chinese woman in <Picture 1> (front view): fair skin, dark brown hair in a high ponytail with loose strands, wearing a white short-sleeve school polo shirt with blue collar and blue side panels, and dark navy track pants with white side stripes. <Picture 1> is the front-view identity anchor for <Subject 1> - use it for her face, hairstyle and costume.\n<Picture 2> is a character turnaround sheet showing the SAME single woman from three angles (front, side, back) - the three figures are ONE person, not three different people. Use it only for costume details on the sides and back.\n<Subject 2> is the young woman in <Picture 3> (front view): twin dark ponytails, black cat-ear hair accessories, a white short-sleeve T-shirt with black trim and a small cartoon print, black shorts, and white over-the-knee stockings. <Picture 3> is the front-view identity anchor for <Subject 2>.\n<Subject 3> is the environment in <Picture 4>: a vast open white-jade viewing terrace floating above a sea of clouds, an ancient pine tree reaching in from the left, a bronze incense burner on a carved balustrade at the right, distant palace roofs emerging from mist, cool blue-grey sky with warm golden sunset light from the right. <Picture 4> is the scene anchor.\n<Picture 5> is a POSE, STAGING AND CAMERA REFERENCE ONLY. It defines the camera height, the shot size, where each person stands and the exact body poses to reproduce frame by frame. The figures visible inside <Picture 5> are featureless 3D mannequins: they must NOT appear anywhere in the output and must never be copied. Replace them completely with <Subject 1> and <Subject 2>, keeping <Subject 1>'s and <Subject 2>'s own faces, hair and costumes.\nAll human subjects are photorealistic real people - not 3D mannequins, not anime, not illustrated.\n\nsummary:\n[reference generation] A 5-second single continuous take with no cut. Reproduce the camera framing, staging and body poses of <Picture 5>, but performed by <Subject 1> and <Subject 2> on the jade terrace of <Subject 3>. <Subject 1> stands centre facing the camera with the right arm raised and the elbow bent, hand at shoulder height, the left arm relaxed at her side; she holds this gesture and sways slightly with the beat. <Subject 2> stands to her left, bent forward at the waist with the head lowered and both arms hanging down. The camera is static at chest height. The cloud sea drifts behind the balustrade. Nothing enters or leaves the frame.\n\nretention_analysis:\n<Subject 1> (appears in [Shot 1]): fully_preserved - face, high ponytail, white-and-blue school polo and navy track pants match <Picture 1>; her raised-arm pose follows <Picture 5>.\n<Picture 1> ([Shot 1] identity): fully_preserved.\n<Picture 2> ([Shot 1] costume reference): partially_preserved - costume details only; the three views are one character, never a group.\n<Subject 2> (appears in [Shot 1]): fully_preserved - twin ponytails, cat-ear accessories, white T-shirt, black shorts, white over-knee stockings; her bent-forward pose follows <Picture 5>.\n<Subject 3> (appears in [Shot 1]): fully_preserved - terrace, pine, balustrade, incense burner and cloud sea match <Picture 4>; only the clouds drift.\n<Picture 5> (appears in [Shot 1]): pose_reference_only - camera framing, staging and body poses are reproduced; the mannequin figures themselves are discarded and are NOT rendered.\n<Picture 5> mannequins and overlays: not_referenced - the red and white mannequins, and any text, logo or watermark, must never be reproduced.\n\ndetailed_description:\n[Shot 1] Photorealistic cinematic footage. Horizontal 16:9. One unbroken take for the full 5 seconds.\n00:00-00:05.000: static shot at chest height, matching the framing, shot size and staging of <Picture 5>. <Subject 1> stands at the centre of the jade terrace of <Subject 3>, framed from head to mid-thigh, in the same pose as the central figure of <Picture 5>: the torso faces the camera, the right arm is raised with the elbow bent and the hand near shoulder height, the left arm hangs relaxed. She keeps the raised hand and moves subtly with the beat - the shoulders sway, the raised hand rotates slightly, the head tilts a little, the ponytail swings. <Subject 2> stands to her left in the same bent-forward posture as the left figure of <Picture 5>: waist bent, head lowered, both arms hanging down; she holds the pose and sways gently. Only these two women are present.\nThe featureless 3D mannequins of <Picture 5> must never appear; only their poses, staging and camera framing are reproduced. No text, no subtitles, no watermark, no logo, no UI overlay anywhere in the frame. No 3D mannequin, no anime style, no illustrated look, no extra person, no duplicated person, no camera shake, no green screen.\n\noverall_soundscape:\nHigh-altitude wind, faint cloth fluttering, soft footsteps on stone. No dialogue.\n\nnon_diegetic_music:\nA steady mid-tempo electronic dance beat with a soft kick on every beat and a light synth pulse, consistent from start to finish.",
   "width": 1280,
   "height": 720,
   "duration": 5,
   "ref_image_size": "match",
   "timeline_data": "{\"version\": 1, \"items\": [{\"id\": \"image-1789323620575-0\", \"enabled\": true, \"order\": 0, \"slot\": 0, \"start\": 0, \"duration\": 1, \"type\": \"image\", \"value\": \"v18pipe_20260914_0220_姿态参考测试_方案A_pic1_front.jpg\", \"thumbnail\": null, \"source_width\": 0, \"source_height\": 0}, {\"id\": \"image-1789323620575-1\", \"enabled\": true, \"order\": 1, \"slot\": 1, \"start\": 0, \"duration\": 1, \"type\": \"image\", \"value\": \"v18pipe_20260914_0220_姿态参考测试_方案A_pic2_ref_pic2_pic2_full.jpg\", \"thumbnail\": null, \"source_width\": 0, \"source_height\": 0}, {\"id\": \"image-1789323620575-2\", \"enabled\": true, \"order\": 2, \"slot\": 2, \"start\": 0, \"duration\": 1, \"type\": \"image\", \"value\": \"v18pipe_20260914_0220_姿态参考测试_方案A_pic3_ref_pic3_pic1_front.jpg\", \"thumbnail\": null, \"source_width\": 0, \"source_height\": 0}, {\"id\": \"image-1789323620575-3\", \"enabled\": true, \"order\": 3, \"slot\": 3, \"start\": 0, \"duration\": 1, \"type\": \"image\", \"value\": \"v18pipe_20260914_0220_姿态参考测试_方案A_pic4_ref_pic4_scene_songxia_guanyuntai.png\", \"thumbnail\": null, \"source_width\": 0, \"source_height\": 0}, {\"id\": \"image-1789323620575-4\", \"enabled\": true, \"order\": 4, \"slot\": 4, \"start\": 0, \"duration\": 1, \"type\": \"image\", \"value\": \"v18pipe_20260914_0220_姿态参考测试_方案A_pic5_ref_pic5_f21.0.png\", \"thumbnail\": null, \"source_width\": 0, \"source_height\": 0}], \"prompt_blocks\": []}",
   "builder_state": "{\"version\": 2, \"mode\": \"REF2VA\", \"duration\": 5, \"ref\": {\"subject_definitions\": \"\", \"summary\": \"\", \"retention_analysis\": \"\", \"detailed_description\": \"\", \"soundscape\": \"\", \"music\": \"\"}, \"prompt_mode\": \"simple\", \"simple_prompt\": \"subject_definitions:\\n<Subject 1> is the young Chinese woman in <Picture 1> (front view): fair skin, dark brown hair in a high ponytail with loose strands, wearing a white short-sleeve school polo shirt with blue collar and blue side panels, and dark navy track pants with white side stripes. <Picture 1> is the front-view identity anchor for <Subject 1> - use it for her face, hairstyle and costume.\\n<Picture 2> is a character turnaround sheet showing the SAME single woman from three angles (front, side, back) - the three figures are ONE person, not three different people. Use it only for costume details on the sides and back.\\n<Subject 2> is the young woman in <Picture 3> (front view): twin dark ponytails, black cat-ear hair accessories, a white short-sleeve T-shirt with black trim and a small cartoon print, black shorts, and white over-the-knee stockings. <Picture 3> is the front-view identity anchor for <Subject 2>.\\n<Subject 3> is the environment in <Picture 4>: a vast open white-jade viewing terrace floating above a sea of clouds, an ancient pine tree reaching in from the left, a bronze incense burner on a carved balustrade at the right, distant palace roofs emerging from mist, cool blue-grey sky with warm golden sunset light from the right. <Picture 4> is the scene anchor.\\n<Picture 5> is a POSE, STAGING AND CAMERA REFERENCE ONLY. It defines the camera height, the shot size, where each person stands and the exact body poses to reproduce frame by frame. The figures visible inside <Picture 5> are featureless 3D mannequins: they must NOT appear anywhere in the output and must never be copied. Replace them completely with <Subject 1> and <Subject 2>, keeping <Subject 1>'s and <Subject 2>'s own faces, hair and costumes.\\nAll human subjects are photorealistic real people - not 3D mannequins, not anime, not illustrated.\\n\\nsummary:\\n[reference generation] A 5-second single continuous take with no cut. Reproduce the camera framing, staging and body poses of <Picture 5>, but performed by <Subject 1> and <Subject 2> on the jade terrace of <Subject 3>. <Subject 1> stands centre facing the camera with the right arm raised and the elbow bent, hand at shoulder height, the left arm relaxed at her side; she holds this gesture and sways slightly with the beat. <Subject 2> stands to her left, bent forward at the waist with the head lowered and both arms hanging down. The camera is static at chest height. The cloud sea drifts behind the balustrade. Nothing enters or leaves the frame.\\n\\nretention_analysis:\\n<Subject 1> (appears in [Shot 1]): fully_preserved - face, high ponytail, white-and-blue school polo and navy track pants match <Picture 1>; her raised-arm pose follows <Picture 5>.\\n<Picture 1> ([Shot 1] identity): fully_preserved.\\n<Picture 2> ([Shot 1] costume reference): partially_preserved - costume details only; the three views are one character, never a group.\\n<Subject 2> (appears in [Shot 1]): fully_preserved - twin ponytails, cat-ear accessories, white T-shirt, black shorts, white over-knee stockings; her bent-forward pose follows <Picture 5>.\\n<Subject 3> (appears in [Shot 1]): fully_preserved - terrace, pine, balustrade, incense burner and cloud sea match <Picture 4>; only the clouds drift.\\n<Picture 5> (appears in [Shot 1]): pose_reference_only - camera framing, staging and body poses are reproduced; the mannequin figures themselves are discarded and are NOT rendered.\\n<Picture 5> mannequins and overlays: not_referenced - the red and white mannequins, and any text, logo or watermark, must never be reproduced.\\n\\ndetailed_description:\\n[Shot 1] Photorealistic cinematic footage. Horizontal 16:9. One unbroken take for the full 5 seconds.\\n00:00-00:05.000: static shot at chest height, matching the framing, shot size and staging of <Picture 5>. <Subject 1> stands at the centre of the jade terrace of <Subject 3>, framed from head to mid-thigh, in the same pose as the central figure of <Picture 5>: the torso faces the camera, the right arm is raised with the elbow bent and the hand near shoulder height, the left arm hangs relaxed. She keeps the raised hand and moves subtly with the beat - the shoulders sway, the raised hand rotates slightly, the head tilts a little, the ponytail swings. <Subject 2> stands to her left in the same bent-forward posture as the left figure of <Picture 5>: waist bent, head lowered, both arms hanging down; she holds the pose and sways gently. Only these two women are present.\\nThe featureless 3D mannequins of <Picture 5> must never appear; only their poses, staging and camera framing are reproduced. No text, no subtitles, no watermark, no logo, no UI overlay anywhere in the frame. No 3D mannequin, no anime style, no illustrated look, no extra person, no duplicated person, no camera shake, no green screen.\\n\\noverall_soundscape:\\nHigh-altitude wind, faint cloth fluttering, soft footsteps on stone. No dialogue.\\n\\nnon_diegetic_music:\\nA steady mid-tempo electronic dance beat with a soft kick on every beat and a light synth pulse, consistent from start to finish.\", \"resolution\": {\"aspect\": \"auto\", \"resolution\": \"0.52 MP - SD\", \"input_scaling\": \"Auto\", \"custom_aspect_w\": 16, \"custom_aspect_h\": 9, \"custom_mp\": 1, \"custom_width\": 1280, \"custom_height\": 720}}",
   "frame_rate": 24,
   "fl2va_model": [
    "1512:1536",
    0
   ],
   "ref2va_model": [
    "1512:2663",
    0
   ]
  },
  "class_type": "DaSiWaMiniMaxH3DirectorLegacy",
  "_meta": {
   "title": "MiniMax H3 Director"
  }
 },
 "2737": {
  "inputs": {
   "max_resolution": 512,
   "jpeg_quality": 80,
   "suppress_default_preview": true,
   "preview_frames": 120,
   "preview_fps": 8,
   "tiny_vae": "taeh3.safetensors",
   "model": [
    "1512:2736",
    0
   ]
  },
  "class_type": "ModelPreviewOverrideKJ",
  "_meta": {
   "title": "Model Preview Override"
  }
 },
 "2739": {
  "inputs": {
   "seed_value": 20260916,
   "seed_control_state": "{\"mode\": \"fixed\", \"last_seed\": \"20260916\", \"recent\": [\"20260916\"]}"
  },
  "class_type": "DaSiWa_SeedControl",
  "_meta": {
   "title": "Seed Control"
  }
 },
 "1512:2586": {
  "inputs": {
   "unet_name": "MiniMaxH3/dasiwa_minimax_h3_ref2va_v1_pruned_hybrid_bf16_m_8turbo_int8_row-wise_convrot_runtime_mixed.safetensors",
   "weight_dtype": "default"
  },
  "class_type": "UNETLoader",
  "_meta": {
   "title": "UNet加载器"
  }
 },
 "1512:2669": {
  "inputs": {
   "samples": [
    "1512:2668",
    0
   ],
   "vae": [
    "1512:2585",
    0
   ]
  },
  "class_type": "VAEDecodeAudio",
  "_meta": {
   "title": "VAE解码（音频）"
  }
 },
 "1512:2587": {
  "inputs": {
   "clip_name": "qwen3vl_32b_minimax_h3_int4_convrot.safetensors",
   "type": "minimax",
   "device": "default"
  },
  "class_type": "CLIPLoader",
  "_meta": {
   "title": "加载CLIP"
  }
 },
 "1512:2598": {
  "inputs": {
   "sampler_name": "euler"
  },
  "class_type": "KSamplerSelect",
  "_meta": {
   "title": "K采样器选择"
  }
 },
 "1512:2590": {
  "inputs": {
   "scheduler": "simple",
   "steps": 8,
   "denoise": 1.0,
   "model": [
    "2678",
    0
   ]
  },
  "class_type": "BasicScheduler",
  "_meta": {
   "title": "基本调度器"
  }
 },
 "1512:2679": {
  "inputs": {
   "scheduler": "simple",
   "steps": 8,
   "denoise": 1.0,
   "model": [
    "2678",
    0
   ]
  },
  "class_type": "BasicScheduler",
  "_meta": {
   "title": "基本调度器"
  }
 },
 "1512:2630": {
  "inputs": {
   "samples": [
    "1512:2591",
    0
   ],
   "vae": [
    "1512:2584",
    0
   ]
  },
  "class_type": "VAEDecode",
  "_meta": {
   "title": "VAE解码"
  }
 },
 "1512:2631": {
  "inputs": {
   "samples": [
    "1512:2591",
    0
   ],
   "vae": [
    "1512:2585",
    0
   ]
  },
  "class_type": "VAEDecodeAudio",
  "_meta": {
   "title": "VAE解码（音频）"
  }
 },
 "1512:2584": {
  "inputs": {
   "vae_name": "MiniMaxH3/minimax_h3_video_vae_int8_convrot.safetensors"
  },
  "class_type": "VAELoader",
  "_meta": {
   "title": "Load VAE Video"
  }
 },
 "1512:2720": {
  "inputs": {
   "attention": "comfy kitchen attention",
   "model": [
    "1512:2588",
    0
   ]
  },
  "class_type": "ModelAttentionBackend",
  "_meta": {
   "title": "ModelAttentionBackend"
  }
 },
 "1512:2585": {
  "inputs": {
   "vae_name": "MiniMaxH3/minimax_h3_audio_vae_fp32.safetensors"
  },
  "class_type": "VAELoader",
  "_meta": {
   "title": "Load VAE Audio"
  }
 },
 "1512:2675": {
  "inputs": {
   "switch": [
    "2730",
    6
   ],
   "on_false": [
    "1512:2669",
    0
   ],
   "on_true": [
    "1512:2631",
    0
   ]
  },
  "class_type": "ComfySwitchNode",
  "_meta": {
   "title": "切换"
  }
 },
 "1512:2691": {
  "inputs": {
   "shift_video": 12.0,
   "shift_audio": 3.0,
   "model": [
    "2678",
    0
   ]
  },
  "class_type": "MiniMaxH3SigmaShift",
  "_meta": {
   "title": "ModelSamplingMiniMaxH3"
  }
 },
 "1512:2692": {
  "inputs": {
   "shift_video": 12.0,
   "shift_audio": 3.0,
   "model": [
    "2678",
    0
   ]
  },
  "class_type": "MiniMaxH3SigmaShift",
  "_meta": {
   "title": "ModelSamplingMiniMaxH3"
  }
 },
 "1512:2592": {
  "inputs": {
   "model": [
    "2737",
    0
   ],
   "conditioning": [
    "1512:2701",
    0
   ]
  },
  "class_type": "BasicGuider",
  "_meta": {
   "title": "基本引导器"
  }
 },
 "1512:2719": {
  "inputs": {
   "attention": "comfy kitchen attention",
   "model": [
    "1512:2586",
    0
   ]
  },
  "class_type": "ModelAttentionBackend",
  "_meta": {
   "title": "ModelAttentionBackend"
  }
 },
 "1512:1536": {
  "inputs": {
   "enable_fp16_accumulation": true,
   "model": [
    "1512:2719",
    0
   ]
  },
  "class_type": "ModelPatchTorchSettings",
  "_meta": {
   "title": "Model Patch Torch Settings"
  }
 },
 "1512:2663": {
  "inputs": {
   "enable_fp16_accumulation": true,
   "model": [
    "1512:2720",
    0
   ]
  },
  "class_type": "ModelPatchTorchSettings",
  "_meta": {
   "title": "Model Patch Torch Settings"
  }
 },
 "1512:2667": {
  "inputs": {
   "model": [
    "2737",
    0
   ],
   "conditioning": [
    "1512:2700",
    0
   ]
  },
  "class_type": "BasicGuider",
  "_meta": {
   "title": "基本引导器"
  }
 },
 "1512:2591": {
  "inputs": {
   "noise": [
    "2739",
    1
   ],
   "guider": [
    "1512:2592",
    0
   ],
   "sampler": [
    "1512:2598",
    0
   ],
   "sigmas": [
    "1512:2590",
    0
   ],
   "latent_image": [
    "1512:2701",
    1
   ]
  },
  "class_type": "SamplerCustomAdvanced",
  "_meta": {
   "title": "自定义采样器（高级）"
  }
 },
 "1512:2700": {
  "inputs": {
   "clip": [
    "1512:2587",
    0
   ],
   "vae": [
    "1512:2584",
    0
   ],
   "guide": [
    "2730",
    0
   ],
   "audio_vae": [
    "1512:2585",
    0
   ]
  },
  "class_type": "MiniMaxH3DirectorGuide",
  "_meta": {
   "title": "MiniMax H3 Director Guide"
  }
 },
 "1512:2668": {
  "inputs": {
   "noise": [
    "2739",
    1
   ],
   "guider": [
    "1512:2667",
    0
   ],
   "sampler": [
    "1512:2598",
    0
   ],
   "sigmas": [
    "1512:2679",
    0
   ],
   "latent_image": [
    "1512:2700",
    1
   ]
  },
  "class_type": "SamplerCustomAdvanced",
  "_meta": {
   "title": "自定义采样器（高级）"
  }
 },
 "1512:2701": {
  "inputs": {
   "clip": [
    "2678",
    1
   ],
   "vae": [
    "1512:2584",
    0
   ],
   "guide": [
    "2730",
    0
   ],
   "audio_vae": [
    "1512:2585",
    0
   ]
  },
  "class_type": "MiniMaxH3DirectorGuide",
  "_meta": {
   "title": "MiniMax H3 Director Guide"
  }
 },
 "1512:2736": {
  "inputs": {
   "switch": false,
   "on_false": [
    "1512:2691",
    0
   ],
   "on_true": [
    "1512:2692",
    0
   ]
  },
  "class_type": "ComfySwitchNode",
  "_meta": {
   "title": "If/Else Switch PREVIEW"
  }
 },
 "1512:2671": {
  "inputs": {
   "samples": [
    "1512:2668",
    0
   ],
   "vae": [
    "1512:2584",
    0
   ]
  },
  "class_type": "VAEDecode",
  "_meta": {
   "title": "VAE解码"
  }
 },
 "1512:2756": {
  "inputs": {
   "source": [
    "2730",
    7
   ]
  },
  "class_type": "PreviewAny",
  "_meta": {
   "title": "预览任意"
  }
 },
 "1512:2677": {
  "inputs": {
   "switch": [
    "2730",
    6
   ],
   "on_false": [
    "1512:2671",
    0
   ],
   "on_true": [
    "1512:2630",
    0
   ]
  },
  "class_type": "ComfySwitchNode",
  "_meta": {
   "title": "If/Else Switch FL2VA / REF2VA"
  }
 },
 "1512:2588": {
  "inputs": {
   "unet_name": "MiniMaxH3/dasiwa_minimax_h3_ref2va_v1_pruned_hybrid_bf16_m_8turbo_int8_row-wise_convrot_runtime_mixed.safetensors",
   "weight_dtype": "default"
  },
  "class_type": "UNETLoader",
  "_meta": {
   "title": "UNet加载器"
  }
 }
}