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": [
"13",
0
],
"image": [
"3",
0
]
},
"class_type": "TextGenerate",
"_meta": {
"title": "Describe picture 1"
}
},
"5": {
"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)"
}
},
"6": {
"inputs": {
"start_index": 0,
"duration": 2048,
"audio": [
"5",
2
]
},
"class_type": "TrimAudioDuration",
"_meta": {
"title": "Soundtrack (whole video)"
}
},
"7": {
"inputs": {
"select_every_nth": 48,
"skip_first_images": 24,
"images": [
"5",
0
]
},
"class_type": "VHS_SelectEveryNthImage",
"_meta": {
"title": "One frame every 2 s"
}
},
"8": {
"inputs": {
"batch_index": 0,
"length": 20,
"image": [
"7",
0
]
},
"class_type": "ImageFromBatch",
"_meta": {
"title": "At most 20 frames"
}
},
"9": {
"inputs": {
"upscale_method": "area",
"largest_size": 640,
"image": [
"8",
0
]
},
"class_type": "ImageScaleToMaxDimension",
"_meta": {
"title": "Shrink for the describer"
}
},
"10": {
"inputs": {
"prompt": "These are frames from one video, in time order. List the people who appear most, up to four, the person with the most screen time first. Write one numbered line per person: first their role in the video in two to four words, without gender, that stays true in every shot, then \" - \" and how they look, like \"1. the guitarist - tall man with a grey beard in a denim jacket\". Each person appears once. Output only the list.",
"max_length": 160,
"sampling_mode": "off",
"thinking": false,
"use_default_template": true,
"mtp": "auto",
"clip": [
"13",
0
],
"image": [
"9",
0
]
},
"class_type": "TextGenerate",
"_meta": {
"title": "Who is in the video"
}
},
"11": {
"inputs": {
"clip_seconds": 6,
"overlap_frames": 39,
"resolution": "736p",
"steps": 6,
"seed": 0,
"roles": "",
"no_lip_sync": [
"68",
0
],
"source_frames": [
"5",
0
],
"picture_1": [
"2",
0
],
"picture_1_text": [
"4",
0
],
"video_people": [
"10",
0
]
},
"class_type": "H3OneClickSwapPlan",
"_meta": {
"title": "Swap Plan (roles, seed, size)"
}
},
"13": {
"inputs": {
"clip_name": "qwen3vl_8b_int8_convrot.safetensors",
"type": "stable_diffusion",
"device": "default"
},
"class_type": "CLIPLoader",
"_meta": {
"title": "Describer: Qwen3-VL 8B"
}
},
"15": {
"inputs": {
"unet_name": "minimax_h3_ref2va_pruned_int8_convrot.safetensors",
"weight_dtype": "default"
},
"class_type": "UNETLoader",
"_meta": {
"title": "H3 Diffusion Model"
}
},
"16": {
"inputs": {
"lora_name": "minimax_h3_DMAD_4step_full_lora_avg_rank_39_bf16.safetensors",
"strength_model": 1,
"model": [
"15",
0
]
},
"class_type": "LoraLoaderModelOnly",
"_meta": {
"title": "DMAD LoRA"
}
},
"17": {
"inputs": {
"attention": "comfy kitchen attention",
"model": [
"16",
0
]
},
"class_type": "ModelAttentionBackend",
"_meta": {
"title": "Comfy Kitchen Attention"
}
},
"18": {
"inputs": {
"shift_video": 12,
"shift_audio": 2,
"model": [
"17",
0
]
},
"class_type": "MiniMaxH3SigmaShift",
"_meta": {
"title": "Sigma Shift"
}
},
"19": {
"inputs": {
"clip_name": "qwen3vl_32b_minimax_h3_int4_convrot.safetensors",
"type": "minimax",
"device": "default"
},
"class_type": "CLIPLoader",
"_meta": {
"title": "H3 Text Encoder"
}
},
"20": {
"inputs": {
"vae_name": "minimax_h3_video_vae_int8_convrot.safetensors"
},
"class_type": "VAELoader",
"_meta": {
"title": "Video VAE"
}
},
"21": {
"inputs": {
"vae_name": "minimax_h3_audio_vae_fp32.safetensors"
},
"class_type": "VAELoader",
"_meta": {
"title": "Audio VAE"
}
},
"22": {
"inputs": {
"sampler_name": "euler"
},
"class_type": "KSamplerSelect",
"_meta": {
"title": "Sampler"
}
},
"23": {
"inputs": {
"ckpt_name": "sam3.1_multiplex_fp16.safetensors"
},
"class_type": "CheckpointLoaderSimple",
"_meta": {
"title": "SAM 3.1"
}
},
"24": {
"inputs": {
"text": "person",
"clip": [
"23",
1
]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "SAM: what to replace"
}
},
"25": {
"inputs": {
"scene_continuity": "Hard picture + protected audio",
"audio_profile": "Generate audio"
},
"class_type": "MiniMaxH3GenerationProfile",
"_meta": {
"title": "Generation Profile"
}
},
"26": {
"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": [
"11",
3
],
"generation_fingerprint": "",
"width": [
"11",
1
],
"height": [
"11",
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": [
"25",
0
],
"plan_json_input": [
"11",
0
]
},
"class_type": "MiniMaxH3ChainPlanModern",
"_meta": {
"title": "Production Plan (filled by Swap Plan)"
}
},
"27": {
"inputs": {
"video_path": "",
"audio_path": "",
"embedded_audio": "auto",
"skip_first_frames": 0,
"source_audio": [
"6",
0
]
},
"class_type": "MiniMaxH3SourceTimeline",
"_meta": {
"title": "Source soundtrack"
}
},
"28": {
"inputs": {
"start_clip": 1,
"scene_range": "",
"verify_resume_history": true,
"plan": [
"26",
0
],
"source_timeline": [
"27",
0
]
},
"class_type": "MiniMaxH3ChainLoopStart",
"_meta": {
"title": "Loop Start"
}
},
"29": {
"inputs": {
"align_audio_reference": false,
"state": [
"28",
1
]
},
"class_type": "MiniMaxH3ChainCurrent",
"_meta": {
"title": "Current Clip"
}
},
"30": {
"inputs": {
"prompt": [
"45",
0
],
"width": [
"29",
8
],
"height": [
"29",
9
],
"length": [
"29",
6
],
"ref_image_size": "match",
"clip": [
"19",
0
],
"vae": [
"20",
0
],
"audio_vae": [
"21",
0
],
"ref_images.ref_image_0": [
"2",
0
],
"ref_videos.ref_video_0": [
"41",
0
],
"ref_video_audios.ref_video_audio_0": [
"73",
0
]
},
"class_type": "MiniMaxH3ReferenceToVideo",
"_meta": {
"title": "Reference Conditioning"
}
},
"31": {
"inputs": {
"source_fps": 24,
"crop": "center",
"state": [
"29",
0
],
"latent": [
"30",
1
],
"audio_vae": [
"21",
0
],
"source_frames": [
"5",
0
],
"source_audio": [
"72",
0
]
},
"class_type": "H3SourceSlice",
"_meta": {
"title": "Source clip (frames + audio)"
}
},
"32": {
"inputs": {
"upscale_method": "area",
"largest_size": 512,
"image": [
"5",
0
]
},
"class_type": "ImageScaleToMaxDimension",
"_meta": {
"title": "Motion reference video (~512 px)"
}
},
"33": {
"inputs": {
"expression": "round(a * 24)",
"values.a": [
"29",
10
]
},
"class_type": "ComfyMathExpression",
"_meta": {
"title": "Clip start frame"
}
},
"34": {
"inputs": {
"batch_index": [
"33",
1
],
"length": [
"29",
6
],
"image": [
"32",
0
]
},
"class_type": "ImageFromBatch",
"_meta": {
"title": "Motion reference for this clip"
}
},
"35": {
"inputs": {
"upscale_method": "area",
"largest_size": 1008,
"image": [
"5",
0
]
},
"class_type": "ImageScaleToMaxDimension",
"_meta": {
"title": "SAM video (1008 px, SAM's own size)"
}
},
"36": {
"inputs": {
"batch_index": [
"33",
1
],
"length": [
"29",
6
],
"image": [
"35",
0
]
},
"class_type": "ImageFromBatch",
"_meta": {
"title": "SAM frames for this clip"
}
},
"37": {
"inputs": {
"noise_seed": [
"29",
5
]
},
"class_type": "RandomNoise",
"_meta": {
"title": "Clip Seed"
}
},
"38": {
"inputs": {
"detection_threshold": 0.35,
"max_objects": 0,
"detect_interval": 1,
"images": [
"36",
0
],
"model": [
"23",
0
],
"conditioning": [
"24",
0
]
},
"class_type": "SAM3_VideoTrack",
"_meta": {
"title": "SAM 3.1 track every person"
}
},
"39": {
"inputs": {
"headroom": 0.1,
"hold_frames": 2,
"max_people": 1,
"track_data": [
"38",
0
]
},
"class_type": "H3PeopleMask",
"_meta": {
"title": "Main person (+ headroom)"
}
},
"40": {
"inputs": {
"headroom": 0,
"hold_frames": 1,
"max_people": 1,
"track_data": [
"38",
0
]
},
"class_type": "H3PeopleMask",
"_meta": {
"title": "Main person, no headroom (for the mannequin)"
}
},
"41": {
"inputs": {
"blur": 0.04,
"face_blur": 0.05,
"images": [
"34",
0
],
"mask": [
"40",
0
],
"size": [
"40",
1
],
"faces": [
"71",
0
],
"face_size": [
"71",
1
]
},
"class_type": "H3GreyMannequins",
"_meta": {
"title": "Hide the main person (grey mannequin)"
}
},
"42": {
"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": [
"52",
0
]
},
"class_type": "GrowMaskWithBlur",
"_meta": {
"title": "Grow mask (~4% of the frame)"
}
},
"43": {
"inputs": {
"cut_threshold": 40,
"images": [
"34",
0
],
"shot_prompt": [
"11",
4
]
},
"class_type": "H3ClipShots",
"_meta": {
"title": "Find this clip's cuts"
}
},
"44": {
"inputs": {
"prompt": [
"43",
1
],
"max_length": 500,
"sampling_mode": "off",
"thinking": false,
"use_default_template": true,
"mtp": "auto",
"clip": [
"13",
0
],
"image": [
"43",
0
]
},
"class_type": "TextGenerate",
"_meta": {
"title": "Write this clip's shot list (Qwen3-VL)"
}
},
"45": {
"inputs": {
"prompt": [
"29",
4
],
"shots": [
"44",
0
]
},
"class_type": "H3FillShots",
"_meta": {
"title": "Insert shot list into prompt"
}
},
"46": {
"inputs": {
"source": [
"45",
0
]
},
"class_type": "PreviewAny",
"_meta": {
"title": "Clip prompt (what H3 gets)"
}
},
"47": {
"inputs": {
"text": "hat",
"clip": [
"23",
1
]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "SAM: hats"
}
},
"48": {
"inputs": {
"detection_threshold": 0.35,
"max_objects": 0,
"detect_interval": 1,
"images": [
"36",
0
],
"model": [
"23",
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": {
"expand": 60,
"incremental_expandrate": 0,
"tapered_corners": true,
"flip_input": false,
"blur_radius": 0,
"lerp_alpha": 1,
"decay_factor": 1,
"fill_holes": true,
"mask": [
"39",
0
]
},
"class_type": "GrowMaskWithBlur",
"_meta": {
"title": "Hat search area (person + 60 px)"
}
},
"51": {
"inputs": {
"x": 0,
"y": 0,
"operation": "multiply",
"destination": [
"49",
0
],
"source": [
"50",
0
]
},
"class_type": "MaskComposite",
"_meta": {
"title": "Only the main person's hat"
}
},
"52": {
"inputs": {
"x": 0,
"y": 0,
"operation": "add",
"destination": [
"39",
0
],
"source": [
"51",
0
]
},
"class_type": "MaskComposite",
"_meta": {
"title": "People + hats"
}
},
"53": {
"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": [
"31",
0
],
"mask": [
"42",
0
]
},
"class_type": "MiniMaxH3ContexMaskGridPreview",
"_meta": {
"title": "Mask preview"
}
},
"54": {
"inputs": {
"images": [
"53",
1
]
},
"class_type": "PreviewImage",
"_meta": {
"title": "Mask preview (white = regenerated)"
}
},
"55": {
"inputs": {
"grow": 0,
"keep_audio": true,
"megapixels": 0,
"vae": [
"20",
0
],
"images": [
"31",
0
],
"mask": [
"42",
0
],
"audio_vae": [
"21",
0
],
"audio": [
"31",
1
]
},
"class_type": "MiniMaxH3FantasticVideoEditLatent",
"_meta": {
"title": "Edit latent (source + mask + audio)"
}
},
"56": {
"inputs": {
"mask_meaning": "white = generate",
"audio_mode": "preserve source audio",
"mask_conversion": "H3 exact (causal/token max)",
"target_latent": [
"55",
0
],
"mask": [
"42",
0
]
},
"class_type": "MiniMaxH3ContexMaskedTarget",
"_meta": {
"title": "Masked target"
}
},
"57": {
"inputs": {
"state": [
"29",
0
],
"conditioning": [
"30",
0
],
"vae": [
"20",
0
],
"latent": [
"56",
0
],
"audio_vae": [
"21",
0
]
},
"class_type": "MiniMaxH3ChainContext",
"_meta": {
"title": "Apply Clip Context"
}
},
"58": {
"inputs": {
"model": [
"18",
0
],
"conditioning": [
"57",
0
]
},
"class_type": "BasicGuider",
"_meta": {
"title": "Guider"
}
},
"59": {
"inputs": {
"scheduler": "simple",
"steps": [
"29",
7
],
"denoise": 1,
"model": [
"18",
0
]
},
"class_type": "BasicScheduler",
"_meta": {
"title": "Schedule"
}
},
"60": {
"inputs": {
"noise": [
"37",
0
],
"guider": [
"58",
0
],
"sampler": [
"22",
0
],
"sigmas": [
"59",
0
],
"latent_image": [
"57",
3
]
},
"class_type": "SamplerCustomAdvanced",
"_meta": {
"title": "Sample Video + Audio"
}
},
"61": {
"inputs": {
"samples": [
"60",
0
],
"vae": [
"20",
0
]
},
"class_type": "VAEDecode",
"_meta": {
"title": "Decode Video"
}
},
"62": {
"inputs": {
"samples": [
"60",
0
],
"vae": [
"21",
0
]
},
"class_type": "VAEDecodeAudio",
"_meta": {
"title": "Decode Audio"
}
},
"63": {
"inputs": {
"trim_frames": [
"57",
1
],
"fps": 24,
"match_tail": true,
"audio_trim_mode": "sync_with_video",
"images": [
"61",
0
],
"audio": [
"62",
0
],
"state": [
"29",
0
]
},
"class_type": "MiniMaxH3LoopTrim",
"_meta": {
"title": "Trim Overlap"
}
},
"64": {
"inputs": {
"state": [
"29",
0
],
"images": [
"63",
0
],
"sampled_latent": [
"60",
0
],
"audio": [
"63",
1
],
"images_with_overlap": [
"63",
2
]
},
"class_type": "MiniMaxH3ChainSegmentSave",
"_meta": {
"title": "Save Clip + Checkpoint"
}
},
"65": {
"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": [
"29",
0
],
"segment": [
"64",
0
],
"audio": [
"63",
1
]
},
"class_type": "MiniMaxH3ChainReview",
"_meta": {
"title": "Review (off = no pause)"
}
},
"66": {
"inputs": {
"between_scene_cleanup": "off",
"execution_mode": "recursive",
"flow": [
"28",
0
],
"state": [
"29",
0
],
"images": [
"63",
0
],
"sampled_latent": [
"60",
0
],
"segment": [
"65",
0
]
},
"class_type": "MiniMaxH3ChainLoopEnd",
"_meta": {
"title": "Loop End"
}
},
"67": {
"inputs": {
"audio_source": "source",
"filename": "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": [
"66",
0
]
},
"class_type": "MiniMaxH3ChainAssemble",
"_meta": {
"title": "Final Video"
}
},
"68": {
"inputs": {
"value": true
},
"class_type": "PrimitiveBoolean",
"_meta": {
"title": "No lip-sync in the prompt"
}
},
"69": {
"inputs": {
"text": "face",
"clip": [
"23",
1
]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "SAM: faces"
}
},
"70": {
"inputs": {
"detection_threshold": 0.2,
"max_objects": 0,
"detect_interval": 1,
"images": [
"36",
0
],
"model": [
"23",
0
],
"conditioning": [
"69",
0
]
},
"class_type": "SAM3_VideoTrack",
"_meta": {
"title": "SAM 3.1 track faces"
}
},
"71": {
"inputs": {
"headroom": 0,
"hold_frames": 0,
"max_people": 0,
"track_data": [
"70",
0
]
},
"class_type": "H3PeopleMask",
"_meta": {
"title": "Faces (shown on the mannequin)"
}
},
"72": {
"inputs": {
"volume": -100,
"audio": [
"6",
0
]
},
"class_type": "AudioAdjustVolume",
"_meta": {
"title": "Mute the clip audio H3 hears"
}
},
"73": {
"inputs": {
"volume": -100,
"audio": [
"29",
12
]
},
"class_type": "AudioAdjustVolume",
"_meta": {
"title": "Mute the reference audio H3 hears"
}
}
}