One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klein relighting.
{
"2": {"inputs": {"image": ""}, "class_type": "LoadImage", "_meta": {"title": "Picture 1"}},
"3": {"inputs": {"upscale_method": "area", "largest_size": 768, "image": ["2", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "Shrink for the describer"}},
"4": {"inputs": {"prompt": "Describe the person in this picture for a casting sheet, in one sentence of about 40 words: apparent age and gender, hair, facial hair, skin tone, build, and their complete outfit including footwear. No preamble, no background.", "max_length": 120, "sampling_mode": "off", "thinking": false, "use_default_template": true, "mtp": "auto", "clip": ["16", 0], "image": ["3", 0]}, "class_type": "TextGenerate", "_meta": {"title": "Describe picture 1"}},
"5": {"inputs": {"image": ""}, "class_type": "LoadImage", "_meta": {"title": "Picture 2"}},
"6": {"inputs": {"upscale_method": "area", "largest_size": 768, "image": ["5", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "Shrink for the describer"}},
"7": {"inputs": {"prompt": "Describe the person in this picture for a casting sheet, in one sentence of about 40 words: apparent age and gender, hair, facial hair, skin tone, build, and their complete outfit including footwear. No preamble, no background.", "max_length": 120, "sampling_mode": "off", "thinking": false, "use_default_template": true, "mtp": "auto", "clip": ["16", 0], "image": ["6", 0]}, "class_type": "TextGenerate", "_meta": {"title": "Describe picture 2"}},
"8": {"inputs": {"video": "", "force_rate": 24, "custom_width": 0, "custom_height": 0, "frame_load_cap": 0, "skip_first_frames": 0, "select_every_nth": 1, "format": "None"}, "class_type": "VHS_LoadVideo", "_meta": {"title": "Source video (people get replaced)"}},
"9": {"inputs": {"start_index": 0, "duration": 2048, "audio": ["8", 2]}, "class_type": "TrimAudioDuration", "_meta": {"title": "Soundtrack (whole video)"}},
"14": {"class_type": "H3MontagePlan", "_meta": {"title": "Swap Plan (roles, seed, size)"}, "inputs": {"clip_seconds": 6, "overlap_frames": 39, "resolution": "736p", "steps": 6, "seed": 0, "roles": "", "no_lip_sync": ["97", 0], "source_frames": ["8", 0], "picture_1": ["2", 0], "picture_2": ["5", 0], "picture_3": ["103", 0], "picture_4": ["106", 0], "picture_1_text": ["4", 0], "picture_2_text": ["7", 0], "picture_3_text": ["105", 0], "picture_4_text": ["108", 0], "track_data": ["121", 0], "labels": ["125", 0]}},
"16": {"inputs": {"clip_name": "qwen3vl_8b_int8_convrot.safetensors", "type": "stable_diffusion", "device": "default"}, "class_type": "CLIPLoader", "_meta": {"title": "Describer: Qwen3-VL 8B"}},
"18": {"inputs": {"unet_name": "minimax_h3_ref2va_pruned_int8_convrot.safetensors", "weight_dtype": "default"}, "class_type": "UNETLoader", "_meta": {"title": "H3 Diffusion Model"}},
"19": {"inputs": {"lora_name": "minimax_h3_DMAD_4step_full_lora_avg_rank_39_bf16.safetensors", "strength_model": 1, "model": ["18", 0]}, "class_type": "LoraLoaderModelOnly", "_meta": {"title": "DMAD LoRA"}},
"20": {"inputs": {"attention": "comfy kitchen attention", "model": ["19", 0]}, "class_type": "ModelAttentionBackend", "_meta": {"title": "Comfy Kitchen Attention"}},
"21": {"inputs": {"shift_video": 12, "shift_audio": 2, "model": ["20", 0]}, "class_type": "MiniMaxH3SigmaShift", "_meta": {"title": "Sigma Shift"}},
"22": {"inputs": {"clip_name": "qwen3vl_32b_minimax_h3_int4_convrot.safetensors", "type": "minimax", "device": "default"}, "class_type": "CLIPLoader", "_meta": {"title": "H3 Text Encoder"}},
"23": {"inputs": {"vae_name": "minimax_h3_video_vae_int8_convrot.safetensors"}, "class_type": "VAELoader", "_meta": {"title": "Video VAE"}},
"24": {"inputs": {"vae_name": "minimax_h3_audio_vae_fp32.safetensors"}, "class_type": "VAELoader", "_meta": {"title": "Audio VAE"}},
"25": {"inputs": {"sampler_name": "euler"}, "class_type": "KSamplerSelect", "_meta": {"title": "Sampler"}},
"26": {"inputs": {"ckpt_name": "sam3.1_multiplex_fp16.safetensors"}, "class_type": "CheckpointLoaderSimple", "_meta": {"title": "SAM 3.1"}},
"27": {"inputs": {"text": "person", "clip": ["26", 1]}, "class_type": "CLIPTextEncode", "_meta": {"title": "SAM: what to replace"}},
"28": {"inputs": {"scene_continuity": "Hard picture + protected audio", "audio_profile": "Generate audio"}, "class_type": "MiniMaxH3GenerationProfile", "_meta": {"title": "Generation Profile"}},
"29": {"inputs": {"plan_json": "{\n \"shots\": [\n {\n \"id\": \"intro\",\n \"prompt\": \"Describe the opening shot.\"\n },\n {\n \"id\": \"continuation\",\n \"prompt\": \"Continue the same take.\"\n }\n ]\n}", "run_name": ["14", 3], "generation_fingerprint": "", "width": ["14", 1], "height": ["14", 2], "encode_mode": "video", "crop": "center", "default_duration_seconds": 15, "default_steps": 6, "base_seed": 0, "segment_crf": 16, "video_blend_frames": 0, "chain_policy": ["28", 0], "plan_json_input": ["14", 0]}, "class_type": "MiniMaxH3ChainPlanModern", "_meta": {"title": "Production Plan (filled by Swap Plan)"}},
"30": {"inputs": {"video_path": "", "audio_path": "", "embedded_audio": "auto", "skip_first_frames": 0, "source_audio": ["9", 0]}, "class_type": "MiniMaxH3SourceTimeline", "_meta": {"title": "Source soundtrack"}},
"31": {"inputs": {"start_clip": 1, "scene_range": "", "verify_resume_history": true, "plan": ["29", 0], "source_timeline": ["30", 0]}, "class_type": "MiniMaxH3ChainLoopStart", "_meta": {"title": "Loop Start"}},
"32": {"inputs": {"align_audio_reference": false, "state": ["31", 1]}, "class_type": "MiniMaxH3ChainCurrent", "_meta": {"title": "Current Clip"}},
"33": {"inputs": {"expression": "round(a * 24)", "values.a": ["32", 10]}, "class_type": "ComfyMathExpression", "_meta": {"title": "Clip start frame"}},
"34": {"inputs": {"upscale_method": "area", "largest_size": 512, "image": ["8", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "Motion reference video (~512 px)"}},
"35": {"inputs": {"batch_index": ["33", 1], "length": ["32", 6], "image": ["34", 0]}, "class_type": "ImageFromBatch", "_meta": {"title": "Motion reference for this clip"}},
"36": {"inputs": {"upscale_method": "area", "largest_size": 1008, "image": ["8", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "SAM video (1008 px, SAM's own size)"}},
"37": {"inputs": {"batch_index": ["33", 1], "length": ["32", 6], "image": ["36", 0]}, "class_type": "ImageFromBatch", "_meta": {"title": "SAM frames for this clip"}},
"47": {"inputs": {"text": "hat", "clip": ["26", 1]}, "class_type": "CLIPTextEncode", "_meta": {"title": "SAM: hats"}},
"48": {"inputs": {"detection_threshold": 0.35, "max_objects": 0, "detect_interval": 1, "images": ["37", 0], "model": ["26", 0], "conditioning": ["47", 0]}, "class_type": "SAM3_VideoTrack", "_meta": {"title": "SAM 3.1 track hats"}},
"49": {"inputs": {"object_indices": "", "track_data": ["48", 0]}, "class_type": "SAM3_TrackToMask", "_meta": {"title": "All hats"}},
"50": {"inputs": {"source_fps": 24, "crop": "center", "state": ["32", 0], "latent": ["59", 1], "audio_vae": ["24", 0], "source_frames": ["8", 0], "source_audio": ["101", 0]}, "class_type": "H3SourceSlice", "_meta": {"title": "Source clip (frames + audio)"}},
"51": {"inputs": {"noise_seed": ["32", 5]}, "class_type": "RandomNoise", "_meta": {"title": "Clip Seed"}},
"52": {"inputs": {"headroom": 0.1, "hold_frames": 2, "subject": 0, "track_data": ["111", 0], "labels": ["111", 1]}, "class_type": "H3RoleMask", "_meta": {"title": "Pass 1: labelled people (+ headroom)"}},
"53": {"inputs": {"headroom": 0, "hold_frames": 1, "subject": 0, "track_data": ["111", 0], "labels": ["111", 1]}, "class_type": "H3RoleMask", "_meta": {"title": "Pass 1: labelled people, no headroom (mannequin)"}},
"54": {"inputs": {"expand": 40, "incremental_expandrate": 0, "tapered_corners": true, "flip_input": false, "blur_radius": 0, "lerp_alpha": 1, "decay_factor": 1, "fill_holes": true, "mask": ["58", 0]}, "class_type": "GrowMaskWithBlur", "_meta": {"title": "Pass 1: grow mask (~4% of the frame)"}},
"55": {"inputs": {"blur": 0.04, "face_blur": 0.05, "images": ["35", 0], "mask": ["53", 0], "size": ["53", 1], "faces": ["100", 0], "face_size": ["100", 1]}, "class_type": "H3GreyMannequins", "_meta": {"title": "Pass 1: hide them (grey mannequins)"}},
"56": {"inputs": {"expand": 60, "incremental_expandrate": 0, "tapered_corners": true, "flip_input": false, "blur_radius": 0, "lerp_alpha": 1, "decay_factor": 1, "fill_holes": true, "mask": ["52", 0]}, "class_type": "GrowMaskWithBlur", "_meta": {"title": "Pass 1: hat search area (person + 60 px)"}},
"57": {"inputs": {"x": 0, "y": 0, "operation": "multiply", "destination": ["49", 0], "source": ["56", 0]}, "class_type": "MaskComposite", "_meta": {"title": "Pass 1: only their hats"}},
"58": {"inputs": {"x": 0, "y": 0, "operation": "add", "destination": ["52", 0], "source": ["57", 0]}, "class_type": "MaskComposite", "_meta": {"title": "Pass 1: people + hats"}},
"59": {"inputs": {"prompt": ["111", 2], "width": ["32", 8], "height": ["32", 9], "length": ["32", 6], "ref_image_size": "match", "clip": ["22", 0], "vae": ["23", 0], "audio_vae": ["24", 0], "ref_images.ref_image_0": ["111", 3], "ref_videos.ref_video_0": ["55", 0], "ref_video_audios.ref_video_audio_0": ["102", 0]}, "class_type": "MiniMaxH3ReferenceToVideo", "_meta": {"title": "Pass 1: reference conditioning"}},
"61": {"inputs": {"source": ["111", 2]}, "class_type": "PreviewAny", "_meta": {"title": "Pass 1: clip prompt (what H3 gets)"}},
"63": {"inputs": {"grow": 0, "keep_audio": true, "megapixels": 0, "vae": ["23", 0], "images": ["50", 0], "mask": ["54", 0], "audio_vae": ["24", 0], "audio": ["50", 1]}, "class_type": "MiniMaxH3FantasticVideoEditLatent", "_meta": {"title": "Pass 1: edit latent (source + mask + audio)"}},
"64": {"inputs": {"mask_meaning": "white = generate", "audio_mode": "preserve source audio", "mask_conversion": "H3 exact (causal/token max)", "target_latent": ["63", 0], "mask": ["54", 0]}, "class_type": "MiniMaxH3ContexMaskedTarget", "_meta": {"title": "Pass 1: masked target"}},
"65": {"inputs": {"state": ["32", 0], "conditioning": ["59", 0], "vae": ["23", 0], "latent": ["64", 0], "audio_vae": ["24", 0]}, "class_type": "MiniMaxH3ChainContext", "_meta": {"title": "Pass 1: apply clip context"}},
"66": {"inputs": {"model": ["21", 0], "conditioning": ["65", 0]}, "class_type": "BasicGuider", "_meta": {"title": "Pass 1: guider"}},
"67": {"inputs": {"scheduler": "simple", "steps": ["32", 7], "denoise": 1, "model": ["21", 0]}, "class_type": "BasicScheduler", "_meta": {"title": "Pass 1: schedule"}},
"68": {"inputs": {"noise": ["51", 0], "guider": ["66", 0], "sampler": ["25", 0], "sigmas": ["67", 0], "latent_image": ["65", 3]}, "class_type": "SamplerCustomAdvanced", "_meta": {"title": "Pass 1: sample video + audio"}},
"69": {"inputs": {"samples": ["68", 0], "vae": ["23", 0]}, "class_type": "VAEDecode", "_meta": {"title": "Pass 1: decode video"}},
"70": {"inputs": {"upscale_method": "area", "largest_size": 512, "image": ["69", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "Pass 2: motion reference from pass 1 (~512 px)"}},
"71": {"inputs": {"headroom": 0.1, "hold_frames": 2, "subject": 0, "track_data": ["112", 0], "labels": ["112", 1]}, "class_type": "H3RoleMask", "_meta": {"title": "Pass 2: labelled people (+ headroom)"}},
"72": {"inputs": {"headroom": 0, "hold_frames": 1, "subject": 0, "track_data": ["112", 0], "labels": ["112", 1]}, "class_type": "H3RoleMask", "_meta": {"title": "Pass 2: labelled people, no headroom (mannequin)"}},
"73": {"inputs": {"expand": 40, "incremental_expandrate": 0, "tapered_corners": true, "flip_input": false, "blur_radius": 0, "lerp_alpha": 1, "decay_factor": 1, "fill_holes": true, "mask": ["77", 0]}, "class_type": "GrowMaskWithBlur", "_meta": {"title": "Pass 2: grow mask (~4% of the frame)"}},
"74": {"inputs": {"blur": 0.04, "face_blur": 0.05, "images": ["70", 0], "mask": ["72", 0], "size": ["72", 1], "faces": ["100", 0], "face_size": ["100", 1]}, "class_type": "H3GreyMannequins", "_meta": {"title": "Pass 2: hide them (grey mannequins)"}},
"75": {"inputs": {"expand": 60, "incremental_expandrate": 0, "tapered_corners": true, "flip_input": false, "blur_radius": 0, "lerp_alpha": 1, "decay_factor": 1, "fill_holes": true, "mask": ["71", 0]}, "class_type": "GrowMaskWithBlur", "_meta": {"title": "Pass 2: hat search area (person + 60 px)"}},
"76": {"inputs": {"x": 0, "y": 0, "operation": "multiply", "destination": ["49", 0], "source": ["75", 0]}, "class_type": "MaskComposite", "_meta": {"title": "Pass 2: only their hats"}},
"77": {"inputs": {"x": 0, "y": 0, "operation": "add", "destination": ["71", 0], "source": ["76", 0]}, "class_type": "MaskComposite", "_meta": {"title": "Pass 2: people + hats"}},
"78": {"inputs": {"prompt": ["112", 2], "width": ["32", 8], "height": ["32", 9], "length": ["32", 6], "ref_image_size": "match", "clip": ["22", 0], "vae": ["23", 0], "audio_vae": ["24", 0], "ref_images.ref_image_0": ["112", 3], "ref_videos.ref_video_0": ["74", 0], "ref_video_audios.ref_video_audio_0": ["102", 0]}, "class_type": "MiniMaxH3ReferenceToVideo", "_meta": {"title": "Pass 2: reference conditioning"}},
"82": {"inputs": {"grow": 0, "keep_audio": true, "megapixels": 0, "vae": ["23", 0], "images": ["69", 0], "mask": ["73", 0], "audio_vae": ["24", 0], "audio": ["50", 1]}, "class_type": "MiniMaxH3FantasticVideoEditLatent", "_meta": {"title": "Pass 2: edit latent (source + mask + audio)"}},
"83": {"inputs": {"mask_meaning": "white = generate", "audio_mode": "preserve source audio", "mask_conversion": "H3 exact (causal/token max)", "target_latent": ["82", 0], "mask": ["73", 0]}, "class_type": "MiniMaxH3ContexMaskedTarget", "_meta": {"title": "Pass 2: masked target"}},
"84": {"inputs": {"state": ["32", 0], "conditioning": ["78", 0], "vae": ["23", 0], "latent": ["83", 0], "audio_vae": ["24", 0]}, "class_type": "MiniMaxH3ChainContext", "_meta": {"title": "Pass 2: apply clip context"}},
"85": {"inputs": {"model": ["21", 0], "conditioning": ["84", 0]}, "class_type": "BasicGuider", "_meta": {"title": "Pass 2: guider"}},
"86": {"inputs": {"scheduler": "simple", "steps": ["32", 7], "denoise": 1, "model": ["21", 0]}, "class_type": "BasicScheduler", "_meta": {"title": "Pass 2: schedule"}},
"87": {"inputs": {"noise": ["51", 0], "guider": ["85", 0], "sampler": ["25", 0], "sigmas": ["86", 0], "latent_image": ["84", 3]}, "class_type": "SamplerCustomAdvanced", "_meta": {"title": "Pass 2: sample video + audio"}},
"88": {"inputs": {"samples": ["113", 0], "vae": ["23", 0]}, "class_type": "VAEDecode", "_meta": {"title": "Decode video"}},
"89": {"inputs": {"cell_selection": "runtime exact (latent max)", "cell_adjust": 0, "preview_frame": 0, "overlay_opacity": 0.38, "show_grid": true, "show_source_outline": true, "mask_meaning": "white = generate", "image": ["50", 0], "mask": ["54", 0]}, "class_type": "MiniMaxH3ContexMaskGridPreview", "_meta": {"title": "Mask preview"}},
"90": {"inputs": {"images": ["89", 1]}, "class_type": "PreviewImage", "_meta": {"title": "Mask preview (white = regenerated)"}},
"91": {"inputs": {"samples": ["113", 0], "vae": ["24", 0]}, "class_type": "VAEDecodeAudio", "_meta": {"title": "Decode Audio"}},
"92": {"inputs": {"trim_frames": ["65", 1], "fps": 24, "match_tail": true, "audio_trim_mode": "sync_with_video", "images": ["88", 0], "audio": ["91", 0], "state": ["32", 0]}, "class_type": "MiniMaxH3LoopTrim", "_meta": {"title": "Trim Overlap"}},
"93": {"inputs": {"state": ["32", 0], "images": ["92", 0], "sampled_latent": ["113", 0], "audio": ["92", 1], "images_with_overlap": ["92", 2]}, "class_type": "MiniMaxH3ChainSegmentSave", "_meta": {"title": "Save Clip + Checkpoint"}},
"94": {"inputs": {"enabled": false, "play_notification_sound": false, "auto_continue_timeout_minutes": 0, "unload_models_while_waiting": false, "assemble_partial_on_stop": true, "partial_audio_source": "checkpointed", "candidate_count": 1, "review_each_candidate": false, "state": ["32", 0], "segment": ["93", 0], "audio": ["92", 1]}, "class_type": "MiniMaxH3ChainReview", "_meta": {"title": "Review (off = no pause)"}},
"95": {"inputs": {"between_scene_cleanup": "off", "execution_mode": "recursive", "flow": ["31", 0], "state": ["32", 0], "images": ["92", 0], "sampled_latent": ["113", 0], "segment": ["94", 0]}, "class_type": "MiniMaxH3ChainLoopEnd", "_meta": {"title": "Loop End"}},
"96": {"inputs": {"audio_source": "source", "filename": "montage_swap_%date:yyyy-MM-dd%", "audio_bitrate": 256, "copy_to_output": true, "output_subfolder": "h3_oneclick_swap", "blend_schedule": "plan", "boundary_tone_match": "off", "color_stabilization": "off", "delete_checkpoints_after_assembly": false, "generated_audio_join": "av_overlap", "manifest": ["95", 0]}, "class_type": "MiniMaxH3ChainAssemble", "_meta": {"title": "Final Video"}},
"97": {"inputs": {"value": true}, "class_type": "PrimitiveBoolean", "_meta": {"title": "No lip-sync in the prompt"}},
"98": {"inputs": {"text": "face", "clip": ["26", 1]}, "class_type": "CLIPTextEncode", "_meta": {"title": "SAM: faces"}},
"99": {"inputs": {"detection_threshold": 0.2, "max_objects": 0, "detect_interval": 1, "images": ["37", 0], "model": ["26", 0], "conditioning": ["98", 0]}, "class_type": "SAM3_VideoTrack", "_meta": {"title": "SAM 3.1 track faces"}},
"100": {"inputs": {"headroom": 0, "hold_frames": 0, "max_people": 0, "track_data": ["99", 0]}, "class_type": "H3PeopleMask", "_meta": {"title": "Faces (shown on the mannequins)"}},
"101": {"inputs": {"volume": -100, "audio": ["9", 0]}, "class_type": "AudioAdjustVolume", "_meta": {"title": "Mute the clip audio H3 hears"}},
"102": {"inputs": {"volume": -100, "audio": ["32", 12]}, "class_type": "AudioAdjustVolume", "_meta": {"title": "Mute the reference audio H3 hears"}},
"103": {"inputs": {"image": "example.png"}, "class_type": "LoadImage", "_meta": {"title": "Picture 3"}},
"104": {"inputs": {"upscale_method": "area", "largest_size": 768, "image": ["103", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "Shrink for the describer"}},
"105": {"inputs": {"prompt": "Describe the person in this picture for a casting sheet, in one sentence of about 40 words: apparent age and gender, hair, facial hair, skin tone, build, and their complete outfit including footwear. No preamble, no background.", "max_length": 120, "sampling_mode": "off", "thinking": false, "use_default_template": true, "mtp": "auto", "clip": ["16", 0], "image": ["104", 0]}, "class_type": "TextGenerate", "_meta": {"title": "Describe picture 3"}},
"106": {"inputs": {"image": "example.png"}, "class_type": "LoadImage", "_meta": {"title": "Picture 4"}},
"107": {"inputs": {"upscale_method": "area", "largest_size": 768, "image": ["106", 0]}, "class_type": "ImageScaleToMaxDimension", "_meta": {"title": "Shrink for the describer"}},
"108": {"inputs": {"prompt": "Describe the person in this picture for a casting sheet, in one sentence of about 40 words: apparent age and gender, hair, facial hair, skin tone, build, and their complete outfit including footwear. No preamble, no background.", "max_length": 120, "sampling_mode": "off", "thinking": false, "use_default_template": true, "mtp": "auto", "clip": ["16", 0], "image": ["107", 0]}, "class_type": "TextGenerate", "_meta": {"title": "Describe picture 4"}},
"109": {"inputs": {"file": "", "source_frames": ["8", 0]}, "class_type": "H3MontageTracks", "_meta": {"title": "Tracks from Find people"}},
"111": {"class_type": "H3MontagePass", "_meta": {"title": "Pass 1: this clip's person"}, "inputs": {"pass_number": 1, "montage": ["14", 4], "track_data": ["121", 0], "clip_index": ["32", 1], "picture_1": ["2", 0], "picture_2": ["5", 0], "picture_3": ["103", 0], "picture_4": ["106", 0]}},
"112": {"class_type": "H3MontagePass", "_meta": {"title": "Pass 2: this clip's second person"}, "inputs": {"pass_number": 2, "montage": ["14", 4], "track_data": ["121", 0], "clip_index": ["32", 1], "picture_1": ["2", 0], "picture_2": ["5", 0], "picture_3": ["103", 0], "picture_4": ["106", 0]}},
"113": {"class_type": "ComfySwitchNode", "_meta": {"title": "Pass 2 only where the piece has a second person"}, "inputs": {"switch": ["111", 4], "on_false": ["68", 0], "on_true": ["87", 0]}},
"121": {"inputs": {"detection_threshold": 0.35, "max_objects": 0, "detect_interval": 1, "images": ["36", 0], "model": ["26", 0], "conditioning": ["27", 0]}, "class_type": "SAM3_VideoTrack", "_meta": {"title": "SAM 3.1 track every person (whole video)"}},
"122": {"inputs": {"cut_threshold": 40, "max_crops": 32, "people": "<Subject 1>: the main person", "track_data": ["121", 0], "images": ["36", 0]}, "class_type": "H3TrackCrops", "_meta": {"title": "Show each track per shot"}},
"124": {"inputs": {"clip": ["16", 0], "crops": ["122", 0], "segments": ["122", 1]}, "class_type": "H3TrackRoles", "_meta": {"title": "Who is each track (Qwen3-VL)"}},
"125": {"inputs": {"track_data": ["121", 0], "labels": ["124", 0]}, "class_type": "H3MontagePicks", "_meta": {"title": "Picks without review"}}
}