{"id":"3424b536-8ea5-4f90-843b-ce0c4bca2792","revision":0,"last_node_id":135,"last_link_id":267,"nodes":[{"id":116,"type":"MarkdownNote","pos":[-2090,4860],"size":[450,630],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[],"title":"Note: MiniMax H3","properties":{},"widgets_values":["## MiniMax H3\n\n[MiniMax H3](https://www.minimax.io/blog/minimax-h3) is MiniMax's general-purpose, omni-modal generation model. It jointly understands text, image, video, and audio, and generates video with **native stereo audio**: voice, sound effects, and music are modeled jointly in a single forward pass, not layered on afterward. Output is up to 2K resolution, 24fps, and up to about 15 seconds.\n\n## About this workflow\n\nThis template runs the **Image to Video** task (`MiniMaxH3ImageToVideo` node), which covers both:\n\n- **t2va** (text-to-video), when no images are connected\n- **fl2va** (first/last-frame image-to-video), when `first_frame` and/or `last_frame` are connected\n\n**Key inputs**\n\n- **first_frame / last_frame**: optional keyframes; the model generates the motion between them\n- **prompt**: describe the shots, motion, and the accompanying audio (dialogue, SFX, music) in one block\n- **width / height**: set via Resolution Selector. H3's native canvas is a 768px short edge, capped at 768x1344 pixels, rounded to a multiple of 32\n- **duration (seconds)**: converted to a valid frame `length` by the Math Expression node, snapping up to the model's 17-frame-per-block (17k+5) grid at 24fps"],"color":"#222","bgcolor":"#000"},{"id":117,"type":"MarkdownNote","pos":[-2570,4860],"size":[440,680],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[],"title":"Note: Model Links","properties":{},"widgets_values":["## Model Links\n\n**vae**\n\n- [minimax_h3_video_vae_fp16.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors)\n- [minimax_h3_audio_vae_fp32.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors)\n\n**diffusion_models**\n\n- [minimax_h3_fl2va_pruned_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors)\n\n**text_encoders**\n\n- [qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors)\n\n\n## Model Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│   ├── 📂 vae/\n│   │   ├── minimax_h3_video_vae_fp16.safetensors\n│   │   └── minimax_h3_audio_vae_fp32.safetensors\n│   ├── 📂 diffusion_models/\n│   │   └── minimax_h3_fl2va_pruned_int8_convrot.safetensors\n│   └── 📂 text_encoders/\n│       └── qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors\n```\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"],"color":"#222","bgcolor":"#000"},{"id":120,"type":"GetImageSize","pos":[-1490,5810],"size":[230,80],"flags":{},"order":7,"mode":0,"inputs":[{"localized_name":"图像","name":"image","type":"IMAGE","link":228}],"outputs":[{"localized_name":"宽度","name":"width","type":"INT","links":null},{"localized_name":"高度","name":"height","type":"INT","links":null},{"localized_name":"批处理大小","name":"batch_size","type":"INT","links":null}],"properties":{"Node name for S&R":"GetImageSize"},"widgets_values":[]},{"id":119,"type":"ImageScaleToTotalPixels","pos":[-1520,5610],"size":[280,150],"flags":{},"order":2,"mode":0,"showAdvanced":true,"inputs":[{"localized_name":"图像","name":"image","type":"IMAGE","link":null},{"localized_name":"缩放算法","name":"upscale_method","type":"COMBO","widget":{"name":"upscale_method"},"link":null},{"localized_name":"像素数量","name":"megapixels","type":"FLOAT","widget":{"name":"megapixels"},"link":null},{"localized_name":"分辨率步数","name":"resolution_steps","type":"INT","widget":{"name":"resolution_steps"},"link":null}],"outputs":[{"localized_name":"图像","name":"IMAGE","type":"IMAGE","links":[228]}],"properties":{"Node name for S&R":"ImageScaleToTotalPixels"},"widgets_values":["nearest-exact",1,32]},{"id":118,"type":"MarkdownNote","pos":[-1130,5460],"size":[300,520],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[],"title":"Note: Size Settings Reference","properties":{},"widgets_values":["| megapixels | Aspect | Output (multiple=32) |\n|---|---|---|\n| 0.2 | 16:9 | 608 x 352 |\n| 0.3 | 16:9 | 736 x 416 |\n| 0.4 | 16:9 | 864 x 480 |\n| 0.5 | 16:9 | 960 x 544 |\n| 0.6 | 16:9 | 1056 x 608 |\n| 0.7 | 16:9 | 1152 x 640 |\n| 0.8 | 16:9 | 1216 x 672 |\n| 0.9 | 16:9 | 1280 x 736 |\n| 0.98 | 16:9 | 1344 x 768 |\n| 1.0 | 16:9 | 1376 x 768 |\n| 1.2 | 16:9 | 1504 x 832 |\n| 1.5 | 16:9 | 1664 x 928 |\n| 1.8 | 16:9 | 1824 x 1024 |\n| 2.0 | 16:9 | 1920 x 1088 |\n"],"color":"#222","bgcolor":"#000"},{"id":92,"type":"SaveVideo","pos":[-186.20930232558146,4849.999999999999],"size":[1030,1943.4166666666667],"flags":{},"order":9,"mode":0,"inputs":[{"localized_name":"视频","name":"video","type":"VIDEO","link":194},{"localized_name":"文件名前缀","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null},{"localized_name":"格式","name":"format","type":"COMBO","widget":{"name":"format"},"link":null},{"localized_name":"编码器","name":"codec","type":"COMFY_DYNAMICCOMBO_V3","widget":{"name":"codec"},"link":null}],"outputs":[{"localized_name":"video","name":"video","type":"VIDEO","links":null}],"properties":{},"widgets_values":["video/MiniMax_H3","auto","auto"]},{"id":114,"type":"LoadImage","pos":[-1610,4860],"size":[450,630],"flags":{},"order":4,"mode":0,"inputs":[{"localized_name":"图像","name":"image","type":"COMBO","widget":{"name":"image"},"link":null},{"localized_name":"选择文件上传","name":"upload","type":"IMAGEUPLOAD","widget":{"name":"upload"},"link":null}],"outputs":[{"localized_name":"图像","name":"IMAGE","type":"IMAGE","links":[218]},{"localized_name":"遮罩","name":"MASK","type":"MASK","links":null}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["WhatsApp Image 2026-08-12 at 10.48.57 AM.jpeg","image"]},{"id":135,"type":"LoadImage","pos":[-2036.9819361817188,5557.714805300162],"size":[450,630],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"图像","name":"image","type":"COMBO","widget":{"name":"image"},"link":null},{"localized_name":"选择文件上传","name":"upload","type":"IMAGEUPLOAD","widget":{"name":"upload"},"link":null}],"outputs":[{"localized_name":"图像","name":"IMAGE","type":"IMAGE","links":[267]},{"localized_name":"遮罩","name":"MASK","type":"MASK","links":null}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["WhatsApp Image 2026-08-12 at 10.48.57 AM (1).jpeg","image"]},{"id":115,"type":"ResolutionSelector","pos":[-1110,5230],"size":[270,170],"flags":{},"order":6,"mode":0,"showAdvanced":false,"inputs":[{"localized_name":"宽高比","name":"aspect_ratio","type":"COMBO","widget":{"name":"aspect_ratio"},"link":null},{"localized_name":"百万像素","name":"megapixels","type":"FLOAT","widget":{"name":"megapixels"},"link":null},{"localized_name":"倍数","name":"multiple","type":"INT","widget":{"name":"multiple"},"link":null}],"outputs":[{"localized_name":"宽度","name":"width","type":"INT","links":[219]},{"localized_name":"高度","name":"height","type":"INT","links":[220]}],"properties":{"Node name for S&R":"ResolutionSelector"},"widgets_values":["9:16 (Portrait Widescreen)",1,32]},{"id":105,"type":"4c314f31-ecda-4b08-ae98-faaba1bf613f","pos":[-730,4850],"size":[505.873403456048,1084.8271975957914],"flags":{},"order":8,"mode":0,"inputs":[{"name":"first_frame","shape":7,"type":"IMAGE","link":218},{"name":"last_frame","shape":7,"type":"IMAGE","link":267},{"name":"prompt","type":"STRING","widget":{"name":"prompt"},"link":null},{"name":"width","type":"INT","widget":{"name":"width"},"link":219},{"name":"height","type":"INT","widget":{"name":"height"},"link":220},{"label":"duration","name":"value_1","type":"FLOAT","widget":{"name":"value_1"},"link":null},{"name":"noise_seed","type":"INT","widget":{"name":"noise_seed"},"link":null},{"name":"unet_name","type":"COMBO","widget":{"name":"unet_name"},"link":null},{"name":"clip_name","type":"COMBO","widget":{"name":"clip_name"},"link":null},{"name":"vae_name","type":"COMBO","widget":{"name":"vae_name"},"link":null},{"label":"audio_vae","name":"vae_name_1","type":"COMBO","widget":{"name":"vae_name_1"},"link":null}],"outputs":[{"localized_name":"VIDEO","name":"VIDEO","type":"VIDEO","links":[194]}],"properties":{"previewExposures":[]},"widgets_values":["For the target video, at 0.00 seconds into the target video, <Picture 1> is fully referenced as the first frame. At 10.00 seconds, <Picture 2> is fully referenced as the final frame.\n\nintegrated_multimodal_description:\n\nCreate a single continuous 10-second cinematic image-to-video shot using <Picture 1> as the exact visual starting frame and <Picture 2> as the exact visual destination frame.\n\nPreserve the same adult woman throughout the entire video. Maintain her facial identity, hairstyle, skin appearance, body proportions, black top, denim skirt, footwear, professional skydiving harness, buckles, straps, and securely attached parachute pack. Her identity and equipment must remain continuous while transitioning naturally from the aircraft doorway in <Picture 1> to the stable freefall pose and framing in <Picture 2>.\n\nThe aircraft doorway is the first spatial anchor. The woman in stable freefall is the second spatial anchor. The camera performs one smooth horizontal figure-eight, infinity-shaped trajectory connecting these two anchors. The first loop curves around the aircraft doorway and her exit movement; the central crossover occurs after she clears the aircraft; the second loop curves in the opposite direction around her body during stable freefall.\n\nUse one uninterrupted shot with no visible cuts. Camera movement has medium amplitude, controlled moderate speed, stable aerial cinematography, realistic three-dimensional parallax, consistent wide-angle lens characteristics, and a level relationship with the horizon whenever visible.\n\n0.00–1.80 seconds:\nBegin with the exact composition, pose, environment, and character appearance shown in <Picture 1>. The woman stands securely at the open aircraft doorway while holding the metal support with one hand. Her parachute harness and pack are correctly fitted and remain firmly attached.\n\nStrong airflow moves her hair and clothing naturally. She breathes, blinks, briefly looks toward the open sky, then steadies her expression and prepares to jump. Her free hand moves into a balanced position while her supporting hand maintains believable contact with the aircraft.\n\nThe camera gently pushes forward from a low angle and begins the first clockwise loop around the doorway and the woman. Preserve the aircraft interior, door frame, exterior sky, clouds, and distant landscape.\n\nA restrained number of luminous particles appear inside the airflow near the doorway. The particles follow the wind, pass naturally around her hands and harness straps, and remain correctly occluded by her body and the aircraft structure.\n\n1.80–3.50 seconds:\nThe woman releases the metal support and performs one controlled professional exit from the aircraft. She pushes away from the doorway, clears the aircraft safely, and moves into open air.\n\nHer arms extend outward for stability while her legs move toward a balanced freefall position. Her expression transitions naturally from initial nervousness to concentration and growing excitement. Hair and clothing respond continuously to the high-speed airflow.\n\nThe camera follows her out of the aircraft while completing the first loop of the figure-eight route. The aircraft doorway moves into the background with realistic scale reduction and perspective. Do not allow her body, parachute equipment, or camera to intersect the aircraft.\n\nLuminous particles trail briefly from the doorway, flow around her arms and securely fastened harness, and extend into the surrounding air. The particle motion follows the real direction of the airflow.\n\n3.50–5.00 seconds:\nThe woman clears the aircraft completely and stabilizes her body in a belly-to-earth freefall position. She makes one small, physically believable correction with her arms and legs, then achieves stable flight.\n\nThe camera passes smoothly through the central crossover point of the figure-eight route, moving from the doorway-centered loop into the freefall-centered loop. The aircraft recedes naturally and does not remain unnaturally close.\n\nDuring the crossover, a short stream of particles flows from behind the woman, separates around her shoulders and parachute pack, and rejoins in the wake beneath her. Do not draw a visible infinity symbol or camera-path line.\n\n5.00–8.20 seconds:\nBegin the second loop in the opposite direction, orbiting counterclockwise around the woman during stable freefall. Move from a three-quarter side view toward a frontal view while maintaining safe distance and smooth aerial stabilization.\n\nThe woman holds a controlled freefall posture with arms extended, elbows slightly bent, torso stable, and legs positioned for balance. She turns her head toward the moving camera, opens her eyes naturally, and begins to smile.\n\nHer interaction is directed toward the camera and surrounding effects: she briefly follows the particles with her eyes, makes one small playful hand gesture, then returns her hand to a stable freefall position. Her movement remains physically correct and does not destabilize her body.\n\nThe luminous particles orbit gently around her without behaving like solid objects. Some pass behind her body and parachute pack, while others move across the foreground. Their direction and speed remain influenced by the airflow.\n\nCloud layers and the distant landscape produce realistic three-dimensional parallax. The horizon moves gradually according to the camera orbit but must not roll or spin excessively.\n\n8.20–10.00 seconds:\nComplete the second loop of the figure-eight trajectory and move smoothly into the exact frontal composition of <Picture 2>.\n\nThe camera approaches at a controlled speed. The woman looks directly into the lens with a joyful, confident expression while maintaining stable freefall. Her arms extend naturally to both sides, her hair flows upward and backward, and her body position transitions precisely toward the pose shown in <Picture 2>.\n\nThe luminous particles briefly gather around her harness and shoulders, flow outward along her arms, and gradually fade into the open sky.\n\nAt exactly 10.00 seconds, match <Picture 2> as closely as possible in facial identity, expression, body pose, camera distance, lens perspective, subject scale, sky, cloud placement, distant landscape, clothing, harness configuration, and overall framing. The final frame must be stable and visually coherent rather than appearing as an abrupt morph.\n\nCharacter interaction:\nOnly one clearly identifiable person appears in the two reference images. Do not introduce additional skydivers, instructors, pilots, aircraft crew, or background characters.\n\nThe woman interacts through realistic contact with the aircraft doorway, controlled body corrections in freefall, eye contact with the camera, a brief hand gesture, and subtle visual attention toward the surrounding particles.\n\nHer expression must transition smoothly:\ninitial tension at the aircraft doorway,\nfocused determination during the exit,\nrelief during stabilization,\nand a joyful smile in the final freefall shot.\n\nSkydiving and equipment behavior:\nThe woman wears a complete professional skydiving harness and securely attached parachute pack throughout the video. All straps, buckles, attachment points, and equipment remain stable and correctly positioned.\n\nThe parachute remains packed during this 10-second freefall sequence. Do not deploy the main canopy or reserve parachute. Do not remove, shrink, loosen, relocate, or transform the parachute pack.\n\nMaintain realistic gravity, airflow, body control, hair movement, fabric movement, freefall speed, cloud parallax, and aircraft separation. The sequence must portray controlled extreme-sports freefall, not an uncontrolled accident.\n\nParticle interaction:\nUse sparse, elegant luminous particles as an atmospheric effect. Particles respond to the airflow, move around the aircraft doorway, follow the woman’s exit, flow along her arms and harness, and create short trails behind her during freefall.\n\nMaintain correct particle depth and occlusion. Do not cover her face, eyes, hands, harness buckles, or parachute equipment. Do not transform particles into fire, smoke, lightning, wings, energy beams, or magical powers.\n\nScene consistency:\nPreserve the spatial scope, environmental atmosphere, lighting character, visual tone, color relationships, contrast, exposure, depth, material appearance, and overall mood established by the reference images throughout the entire video. Maintain the existing visual balance without assigning a new color style, introducing a separate color grade, or replacing the original lighting conditions.\n\nThe aircraft scene must transition naturally into the open-air environment. All added movement and effects must remain consistent with the existing light direction, sky conditions, cloud layers, and high-altitude atmosphere.\n\nStrict visual constraints:\nDo not change the woman’s identity, facial structure, hairstyle, clothing, footwear, body proportions, or skydiving equipment. Do not generate a second face, duplicated person, extra arms, hands, fingers, legs, feet, harness straps, or parachute packs.\n\nPrevent facial warping, body stretching, detached limbs, broken joints, hand deformation, fused fingers, floating equipment, sliding harnesses, or straps passing through the body. Maintain anatomically correct arms, hands, legs, feet, torso, and head throughout the action.\n\nKeep her clothing properly fitted and physically consistent under airflow. No wardrobe malfunction, disappearing clothing, unintended exposure, transparent fabric, torn clothing, or transformation into a different outfit.\n\nDo not depict panic after leaving the aircraft, unconsciousness, equipment failure, parachute failure, collision, uncontrolled tumbling, aircraft impact, injury, blood, falling debris, or dangerous proximity to the ground.\n\nDo not duplicate or deform the aircraft. Do not create additional aircraft, wings intersecting the subject, impossible cloud motion, ground rushing upward, rapid horizon spinning, or unnatural freefall acceleration.\n\nNo cuts, scene replacements, teleportation, abrupt pose changes, sudden zooms, excessive camera shake, rolling frame, unstable geometry, extreme fisheye distortion, focus pumping, exposure flicker, inconsistent shadows, visible camera-path lines, captions, subtitles, logos, watermarks, borders, or interface elements.\n\noverall_soundscape:\nBegin with the low mechanical vibration of the aircraft interior, engine noise, metal resonance, and powerful wind entering through the open doorway. As the woman exits, transition naturally into strong open-air rushing wind with subtle fabric flutter, harness movement, and distant atmospheric depth. Keep the sound physically coherent with the camera distance and movement. Add delicate spatial chimes when luminous particles pass around her hands and harness.\n\nnon_diegetic_music:\nCinematic extreme-sports instrumental music with a restrained suspenseful opening, a rising pulse during the exit, a brief uplifting transition during stabilization, and an energetic but spacious resolution during the final freefall shot. Keep the music beneath the aircraft and wind sounds. No vocals.",1344,768,12,242412351246812,"minimax_h3_fl2va_pruned_fp8_scaled.safetensors","qwen3vl_32b_h3_ultra_uncensored_heretic_int8_convrot.safetensors","minimax_h3_video_vae_fp16.safetensors","minimax_h3_audio_vae_fp32.safetensors"]}],"links":[[194,105,0,92,0,"VIDEO"],[218,114,0,105,0,"IMAGE"],[219,115,0,105,3,"INT"],[220,115,1,105,4,"INT"],[228,119,0,120,0,"IMAGE"],[267,135,0,105,1,"IMAGE"]],"groups":[{"id":5,"title":"Use Image Size","bounding":[-1530,5540,296.484375,354],"color":"#3f789e","flags":{}}],"definitions":{"subgraphs":[{"id":"4c314f31-ecda-4b08-ae98-faaba1bf613f","version":1,"state":{"lastGroupId":5,"lastNodeId":135,"lastLinkId":267,"lastRerouteId":0},"revision":0,"config":{},"name":"Image to Video (MiniMax H3)","inputNode":{"id":-10,"bounding":[-2560,4720,128,268]},"outputNode":{"id":-20,"bounding":[690,4810,128,68]},"inputs":[{"id":"d6eaa195-2266-4016-b7ed-b2d17a3e53c2","name":"first_frame","type":"IMAGE","linkIds":[195],"pos":[-2456,4744]},{"id":"03b95567-f496-4279-9d38-989dd34fa882","name":"last_frame","type":"IMAGE","linkIds":[196],"pos":[-2456,4764]},{"id":"d7302ca7-24ed-44c4-8ac9-736540dab7fb","name":"prompt","type":"STRING","linkIds":[197],"pos":[-2456,4784]},{"id":"709e2d94-3172-496f-ad86-7d672f3df568","name":"width","type":"INT","linkIds":[200],"pos":[-2456,4804]},{"id":"8205b85b-19bb-47f6-8418-89cd42940c1d","name":"height","type":"INT","linkIds":[201],"pos":[-2456,4824]},{"id":"a40e5e96-4307-4a8e-a4f8-13a27d4bc9d3","name":"value_1","type":"FLOAT","linkIds":[206],"label":"duration","pos":[-2456,4844]},{"id":"9f8734bc-c2b3-43b0-911e-e89560e8b777","name":"noise_seed","type":"INT","linkIds":[207],"pos":[-2456,4864]},{"id":"9a6d2811-673c-47e0-aa94-dda7c83621e4","name":"unet_name","type":"COMBO","linkIds":[221],"pos":[-2456,4884]},{"id":"7100a787-5536-4002-840b-1d2fd071010a","name":"clip_name","type":"COMBO","linkIds":[227],"pos":[-2456,4904]},{"id":"d40632fd-e0ae-4319-b85d-5479db4d6e11","name":"vae_name","type":"COMBO","linkIds":[223],"pos":[-2456,4924]},{"id":"2992852c-4b20-439a-8771-c866ec1996e6","name":"vae_name_1","type":"COMBO","linkIds":[224],"label":"audio_vae","pos":[-2456,4944]}],"outputs":[{"id":"adb2611c-e490-4fca-8067-b718c992f8cc","name":"VIDEO","type":"VIDEO","linkIds":[168],"localized_name":"VIDEO","pos":[714,4834]}],"widgets":[],"nodes":[{"id":11,"type":"VAELoader","pos":[-2020,5020],"size":[640,70],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"vae名称","name":"vae_name","type":"COMBO","widget":{"name":"vae_name"},"link":223}],"outputs":[{"localized_name":"VAE","name":"VAE","type":"VAE","links":[8,190]}],"properties":{"Node name for S&R":"VAELoader","models":[{"name":"minimax_h3_video_vae_fp16.safetensors","url":"https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors","directory":"vae"}]},"widgets_values":["minimax_h3_video_vae_fp16.safetensors"]},{"id":24,"type":"VAELoader","pos":[-2020,5160],"size":[650,70],"flags":{},"order":11,"mode":0,"inputs":[{"localized_name":"vae名称","name":"vae_name","type":"COMBO","widget":{"name":"vae_name"},"link":224}],"outputs":[{"localized_name":"VAE","name":"VAE","type":"VAE","links":[23]}],"properties":{"Node name for S&R":"VAELoader","models":[{"name":"minimax_h3_audio_vae_fp32.safetensors","url":"https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors","directory":"vae"}]},"widgets_values":["minimax_h3_audio_vae_fp32.safetensors"]},{"id":13,"type":"CLIPLoader","pos":[-2020,4830],"size":[640,120],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"CLIP名称","name":"clip_name","type":"COMBO","widget":{"name":"clip_name"},"link":227},{"localized_name":"类型","name":"type","type":"COMBO","widget":{"name":"type"},"link":null},{"localized_name":"设备","name":"device","shape":7,"type":"COMBO","widget":{"name":"device"},"link":null}],"outputs":[{"localized_name":"CLIP","name":"CLIP","type":"CLIP","links":[189]}],"properties":{"Node name for S&R":"CLIPLoader","models":[{"name":"qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors","url":"https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors","directory":"text_encoders"}]},"widgets_values":["qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors","minimax","default"]},{"id":107,"type":"ComfyMathExpression","pos":[-1710,5410],"size":[360,160],"flags":{"collapsed":false},"order":14,"mode":0,"inputs":[{"label":"a","localized_name":"values.a","name":"values.a","type":"FLOAT,INT,BOOLEAN","link":205},{"label":"b","localized_name":"values.b","name":"values.b","shape":7,"type":"FLOAT,INT,BOOLEAN","link":null},{"localized_name":"表达式","name":"expression","type":"STRING","widget":{"name":"expression"},"link":null}],"outputs":[{"localized_name":"浮点","name":"FLOAT","type":"FLOAT","links":null},{"localized_name":"整数","name":"INT","type":"INT","links":[199]},{"localized_name":"布尔值","name":"BOOL","type":"BOOLEAN","links":null}],"properties":{"Node name for S&R":"ComfyMathExpression"},"widgets_values":["max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17"]},{"id":111,"type":"PrimitiveFloat","pos":[-2020,5410],"size":[270,70],"flags":{},"order":15,"mode":0,"inputs":[{"localized_name":"值","name":"value","type":"FLOAT","widget":{"name":"value"},"link":206}],"outputs":[{"localized_name":"浮点","name":"FLOAT","type":"FLOAT","links":[205]}],"title":"Float (duration)","properties":{"Node name for S&R":"PrimitiveFloat"},"widgets_values":[2]},{"id":91,"type":"CreateVideo","pos":[300,4890],"size":[270,110],"flags":{},"order":12,"mode":0,"inputs":[{"localized_name":"图像","name":"images","type":"IMAGE","link":230},{"localized_name":"音频","name":"audio","shape":7,"type":"AUDIO","link":166},{"localized_name":"帧率","name":"fps","type":"FLOAT","widget":{"name":"fps"},"link":null},{"localized_name":"bit_depth","name":"bit_depth","shape":7,"type":"INT","widget":{"name":"bit_depth"},"link":null}],"outputs":[{"localized_name":"视频","name":"VIDEO","type":"VIDEO","links":[168]}],"properties":{"Node name for S&R":"CreateVideo"},"widgets_values":[24,8]},{"id":121,"type":"RTXVideoSuperResolution","pos":[240.61886572578587,4606.8458595572865],"size":[285.81015625,106],"flags":{},"order":16,"mode":0,"inputs":[{"localized_name":"images","name":"images","type":"IMAGE","link":229},{"localized_name":"resize_type","name":"resize_type","type":"COMFY_DYNAMICCOMBO_V3","widget":{"name":"resize_type"},"link":null},{"localized_name":"resize_type.scale","name":"resize_type.scale","type":"FLOAT","widget":{"name":"resize_type.scale"},"link":null},{"localized_name":"quality","name":"quality","type":"COMBO","widget":{"name":"quality"},"link":null}],"outputs":[{"localized_name":"upscaled_images","name":"upscaled_images","type":"IMAGE","links":[230]}],"properties":{"Node name for S&R":"RTXVideoSuperResolution"},"widgets_values":["scale by multiplier",2,"ULTRA"]},{"id":15,"type":"RandomNoise","pos":[-780,4660],"size":[360,90],"flags":{},"order":8,"mode":0,"inputs":[{"localized_name":"噪波随机种","name":"noise_seed","type":"INT","widget":{"name":"noise_seed"},"link":207}],"outputs":[{"localized_name":"噪波","name":"NOISE","type":"NOISE","links":[40]}],"properties":{"Node name for S&R":"RandomNoise"},"widgets_values":[1,"randomize"]},{"id":16,"type":"BasicGuider","pos":[-780,4820],"size":[360,60],"flags":{},"order":9,"mode":0,"inputs":[{"localized_name":"模型","name":"model","type":"MODEL","link":241},{"localized_name":"条件","name":"conditioning","type":"CONDITIONING","link":187}],"outputs":[{"localized_name":"引导器","name":"GUIDER","type":"GUIDER","links":[12]}],"properties":{"Node name for S&R":"BasicGuider"},"widgets_values":[]},{"id":17,"type":"KSamplerSelect","pos":[-780,4950],"size":[370,70],"flags":{},"order":0,"mode":0,"inputs":[{"localized_name":"采样器名称","name":"sampler_name","type":"COMBO","widget":{"name":"sampler_name"},"link":null}],"outputs":[{"localized_name":"采样器","name":"SAMPLER","type":"SAMPLER","links":[16]}],"properties":{"Node name for S&R":"KSamplerSelect"},"widgets_values":["res_multistep"]},{"id":104,"type":"MiniMaxH3ImageToVideo","pos":[-1290,4630],"size":[430,550],"flags":{},"order":13,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":189},{"localized_name":"vae","name":"vae","type":"VAE","link":190},{"localized_name":"first_frame","name":"first_frame","shape":7,"type":"IMAGE","link":195},{"localized_name":"last_frame","name":"last_frame","shape":7,"type":"IMAGE","link":196},{"localized_name":"prompt","name":"prompt","type":"STRING","widget":{"name":"prompt"},"link":197},{"localized_name":"width","name":"width","type":"INT","widget":{"name":"width"},"link":200},{"localized_name":"height","name":"height","type":"INT","widget":{"name":"height"},"link":201},{"localized_name":"length","name":"length","type":"INT","widget":{"name":"length"},"link":199}],"outputs":[{"localized_name":"positive","name":"positive","type":"CONDITIONING","links":[187]},{"localized_name":"Latent","name":"LATENT","type":"LATENT","links":[259]}],"properties":{"Node name for S&R":"MiniMaxH3ImageToVideo"},"widgets_values":["Vaporwave title sequence look: pink and blue gradient palette, VHS tracking artifacts, Greek statue motifs, chrome palm trees, RGB chromatic aberration, lo-fi retro atmosphere, mood languid and nostalgic.\n\nTimeline:\n[0s-1s] VHS static opens the frame, the title \"COMFYUI\" appears with RGB split and a slight horizontal jitter.\n[1s-2.5s] Hard cut, a Greek plaster bust close-up, pink-purple gradient sky, a pixelated sun.\n[2.5s-4s] Clean \"STARRING\" credits appear, \"LATENT\" and \"CONTROLNET\" each shown exactly once.\n[4s-5s] Final card \"DIRECTED BY COMFYUI\" holds, one VHS tracking glitch settling into stability.\n\nHard cuts only, transitions landing with tape jumps, no push-ins, no dissolves.\n\nAudio: lo-fi vaporwave score, slow drum machine with soft bass, VHS tape-noise sample joins at 2.5s, melody fading for the last 1s.\n\nAll text must be clearly legible, do not misspell English, no Chinese characters, do not repeat names or job titles, no soft dissolves, no subtitle bars.",1344,768,73]},{"id":124,"type":"LoraLoaderModelOnly","pos":[-761.431782641629,4385.017915979882],"size":[270,82],"flags":{},"order":1,"mode":4,"inputs":[{"localized_name":"模型","name":"model","type":"MODEL","link":null},{"localized_name":"LoRA名称","name":"lora_name","type":"COMBO","widget":{"name":"lora_name"},"link":null},{"localized_name":"模型强度","name":"strength_model","type":"FLOAT","widget":{"name":"strength_model"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[]}],"properties":{"Node name for S&R":"LoraLoaderModelOnly"},"widgets_values":["minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors",1],"color":"#232","bgcolor":"#353"},{"id":14,"type":"SamplerCustomAdvanced","pos":[-325.6237884708977,4837.15391075302],"size":[230,326],"flags":{},"order":7,"mode":0,"inputs":[{"localized_name":"噪波","name":"noise","type":"NOISE","link":40},{"localized_name":"引导器","name":"guider","type":"GUIDER","link":12},{"localized_name":"采样器","name":"sampler","type":"SAMPLER","link":16},{"localized_name":"西格玛","name":"sigmas","type":"SIGMAS","link":18},{"localized_name":"Latent图像","name":"latent_image","type":"LATENT","link":259}],"outputs":[{"localized_name":"Latent","name":"output","type":"LATENT","links":[261]},{"localized_name":"降噪Latent","name":"denoised_output","type":"LATENT","links":null}],"properties":{"Node name for S&R":"SamplerCustomAdvanced"},"widgets_values":[]},{"id":9,"type":"BasicScheduler","pos":[-780,5100],"size":[370,130],"flags":{},"order":3,"mode":0,"inputs":[{"localized_name":"模型","name":"model","type":"MODEL","link":242},{"localized_name":"调度器","name":"scheduler","type":"COMBO","widget":{"name":"scheduler"},"link":null},{"localized_name":"步数","name":"steps","type":"INT","widget":{"name":"steps"},"link":null},{"localized_name":"降噪","name":"denoise","type":"FLOAT","widget":{"name":"denoise"},"link":null}],"outputs":[{"localized_name":"Sigmas","name":"SIGMAS","type":"SIGMAS","links":[18]}],"properties":{"Node name for S&R":"BasicScheduler"},"widgets_values":["simple",8,1]},{"id":23,"type":"VAEDecodeAudio","pos":[22.7336053259788,4967.061789046978],"size":[230,60],"flags":{"collapsed":false},"order":10,"mode":0,"inputs":[{"localized_name":"Latent","name":"samples","type":"LATENT","link":263},{"localized_name":"vae","name":"vae","type":"VAE","link":23}],"outputs":[{"localized_name":"音频","name":"AUDIO","type":"AUDIO","links":[166]}],"properties":{"Node name for S&R":"VAEDecodeAudio"},"widgets_values":[]},{"id":10,"type":"VAEDecode","pos":[27.068108947639807,4825.115152132564],"size":[230,60],"flags":{"collapsed":false},"order":4,"mode":0,"inputs":[{"localized_name":"Latent","name":"samples","type":"LATENT","link":262},{"localized_name":"vae","name":"vae","type":"VAE","link":8}],"outputs":[{"localized_name":"图像","name":"IMAGE","type":"IMAGE","links":[229]}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":6,"type":"UNETLoader","pos":[-2020,4670],"size":[640,90],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"UNet名称","name":"unet_name","type":"COMBO","widget":{"name":"unet_name"},"link":221},{"localized_name":"数据类型","name":"weight_dtype","type":"COMBO","widget":{"name":"weight_dtype"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[235]}],"properties":{"Node name for S&R":"UNETLoader","models":[{"name":"minimax_h3_fl2va_pruned_int8_convrot.safetensors","url":"https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors","directory":"diffusion_models"}]},"widgets_values":["minimax_h3_fl2va_pruned_int8_convrot.safetensors","default"]},{"id":123,"type":"SolAttnPatch","pos":[-1241.2321888026906,4140.091597981784],"size":[270,342],"flags":{},"order":18,"mode":4,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":235},{"localized_name":"tau_profile","name":"tau_profile","shape":7,"type":"STRING","link":null},{"localized_name":"tau","name":"tau","type":"FLOAT","widget":{"name":"tau"},"link":null},{"localized_name":"start_percent","name":"start_percent","type":"FLOAT","widget":{"name":"start_percent"},"link":null},{"localized_name":"end_percent","name":"end_percent","type":"FLOAT","widget":{"name":"end_percent"},"link":null},{"localized_name":"min_tokens","name":"min_tokens","type":"INT","widget":{"name":"min_tokens"},"link":null},{"localized_name":"int8_qk","name":"int8_qk","type":"BOOLEAN","widget":{"name":"int8_qk"},"link":null},{"localized_name":"sink_conditioning","name":"sink_conditioning","type":"COMBO","widget":{"name":"sink_conditioning"},"link":null},{"localized_name":"morton","name":"morton","type":"BOOLEAN","widget":{"name":"morton"},"link":null},{"localized_name":"morton_curve","name":"morton_curve","type":"COMBO","widget":{"name":"morton_curve"},"link":null},{"localized_name":"int8_pv","name":"int8_pv","type":"BOOLEAN","widget":{"name":"int8_pv"},"link":null},{"localized_name":"verbose","name":"verbose","type":"BOOLEAN","widget":{"name":"verbose"},"link":null},{"localized_name":"use_tma","name":"use_tma","type":"BOOLEAN","widget":{"name":"use_tma"},"link":null},{"localized_name":"dense_blocks","name":"dense_blocks","type":"STRING","widget":{"name":"dense_blocks"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[255]}],"properties":{"Node name for S&R":"SolAttnPatch"},"widgets_values":[1.3,0.2,0.9,4096,true,"exact_kv",false,"2d_frame",true,false,false,""]},{"id":125,"type":"MiniMaxH3SigmaShift","pos":[-354.69782397774964,4365.793427274241],"size":[270,82],"flags":{},"order":19,"mode":4,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":266},{"localized_name":"shift_video","name":"shift_video","type":"FLOAT","widget":{"name":"shift_video"},"link":null},{"localized_name":"shift_audio","name":"shift_audio","type":"FLOAT","widget":{"name":"shift_audio"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[241,242]}],"properties":{"Node name for S&R":"MiniMaxH3SigmaShift"},"widgets_values":[12,3],"color":"#323","bgcolor":"#535"},{"id":122,"type":"MiniMaxH3TurboLoRA","pos":[-887.4078062272528,4142.256056750595],"size":[270,106],"flags":{},"order":17,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":255},{"localized_name":"lora_name","name":"lora_name","type":"COMBO","widget":{"name":"lora_name"},"link":null},{"localized_name":"strength","name":"strength","type":"FLOAT","widget":{"name":"strength"},"link":null},{"localized_name":"low_vram","name":"low_vram","type":"BOOLEAN","widget":{"name":"low_vram"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[265]}],"properties":{"Node name for S&R":"MiniMaxH3TurboLoRA"},"widgets_values":["minimax_h3_turbo_v4_step600_ema.safetensors",1,false]},{"id":134,"type":"MiniMaxH3MemoryEfficientSolAttentionPatch","pos":[-420.1805988994206,4039.2454029126825],"size":[430,250],"flags":{},"order":21,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":265},{"localized_name":"enabled","name":"enabled","type":"BOOLEAN","widget":{"name":"enabled"},"link":null},{"localized_name":"tau","name":"tau","type":"FLOAT","widget":{"name":"tau"},"link":null},{"localized_name":"min_tokens","name":"min_tokens","type":"INT","widget":{"name":"min_tokens"},"link":null},{"localized_name":"strict","name":"strict","type":"BOOLEAN","widget":{"name":"strict"},"link":null},{"localized_name":"thresh_type","name":"thresh_type","type":"COMBO","widget":{"name":"thresh_type"},"link":null},{"localized_name":"int8_qk","name":"int8_qk","type":"BOOLEAN","widget":{"name":"int8_qk"},"link":null},{"localized_name":"int8_pv","name":"int8_pv","type":"BOOLEAN","widget":{"name":"int8_pv"},"link":null},{"localized_name":"sink_conditioning","name":"sink_conditioning","type":"COMBO","widget":{"name":"sink_conditioning"},"link":null},{"localized_name":"dense_blocks","name":"dense_blocks","type":"STRING","widget":{"name":"dense_blocks"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[266]}],"properties":{"Node name for S&R":"MiniMaxH3MemoryEfficientSolAttentionPatch","aux_id":"Saganaki22/ComfyUI-sol-attn","ver":"e2fc225f8642585cfa11a31d52fe7b2db7290efa","ue_properties":{"widget_ue_connectable":{},"input_ue_unconnectable":{},"version":"7.8"}},"widgets_values":[true,1.3,4096,true,"diag",false,"exact_kv","exact_kv",""]},{"id":132,"type":"VRAM_Debug","pos":[-42.48402569722041,5130.165095053926],"size":[304.470703125,186],"flags":{},"order":20,"mode":0,"inputs":[{"localized_name":"any_input","name":"any_input","shape":7,"type":"*","link":261},{"localized_name":"image_pass","name":"image_pass","shape":7,"type":"IMAGE","link":null},{"localized_name":"model_pass","name":"model_pass","shape":7,"type":"MODEL","link":null},{"localized_name":"empty_cache","name":"empty_cache","type":"BOOLEAN","widget":{"name":"empty_cache"},"link":null},{"localized_name":"gc_collect","name":"gc_collect","type":"BOOLEAN","widget":{"name":"gc_collect"},"link":null},{"localized_name":"unload_all_models","name":"unload_all_models","type":"BOOLEAN","widget":{"name":"unload_all_models"},"link":null}],"outputs":[{"localized_name":"any_output","name":"any_output","type":"*","links":[262,263]},{"localized_name":"image_pass","name":"image_pass","type":"IMAGE","links":null},{"localized_name":"model_pass","name":"model_pass","type":"MODEL","links":null},{"label":"31,524,017,008   freemem_before","localized_name":"freemem_before","name":"freemem_before","type":"INT","links":null},{"label":"32,147,681,532      freemem_after","localized_name":"freemem_after","name":"freemem_after","type":"INT","links":null}],"properties":{"Node name for S&R":"VRAM_Debug"},"widgets_values":[true,true,true]}],"groups":[{"id":1,"title":"Models","bounding":[-2050,4540,700,800],"color":"#3f789e","flags":{}},{"id":2,"title":"Sampling","bounding":[-810,4540,700,800],"color":"#3f789e","flags":{}},{"id":3,"title":"Conditioning","bounding":[-1320,4540,480,800],"color":"#3f789e","flags":{}},{"id":4,"title":"Decoding and create video","bounding":[-90,4540,700,800],"color":"#3f789e","flags":{}}],"links":[{"id":23,"origin_id":24,"origin_slot":0,"target_id":23,"target_slot":1,"type":"VAE"},{"id":8,"origin_id":11,"origin_slot":0,"target_id":10,"target_slot":1,"type":"VAE"},{"id":40,"origin_id":15,"origin_slot":0,"target_id":14,"target_slot":0,"type":"NOISE"},{"id":12,"origin_id":16,"origin_slot":0,"target_id":14,"target_slot":1,"type":"GUIDER"},{"id":16,"origin_id":17,"origin_slot":0,"target_id":14,"target_slot":2,"type":"SAMPLER"},{"id":18,"origin_id":9,"origin_slot":0,"target_id":14,"target_slot":3,"type":"SIGMAS"},{"id":187,"origin_id":104,"origin_slot":0,"target_id":16,"target_slot":1,"type":"CONDITIONING"},{"id":166,"origin_id":23,"origin_slot":0,"target_id":91,"target_slot":1,"type":"AUDIO"},{"id":189,"origin_id":13,"origin_slot":0,"target_id":104,"target_slot":0,"type":"CLIP"},{"id":190,"origin_id":11,"origin_slot":0,"target_id":104,"target_slot":1,"type":"VAE"},{"id":168,"origin_id":91,"origin_slot":0,"target_id":-20,"target_slot":0,"type":"VIDEO"},{"id":195,"origin_id":-10,"origin_slot":0,"target_id":104,"target_slot":2,"type":"IMAGE"},{"id":196,"origin_id":-10,"origin_slot":1,"target_id":104,"target_slot":3,"type":"IMAGE"},{"id":197,"origin_id":-10,"origin_slot":2,"target_id":104,"target_slot":4,"type":"STRING"},{"id":199,"origin_id":107,"origin_slot":1,"target_id":104,"target_slot":7,"type":"INT"},{"id":200,"origin_id":-10,"origin_slot":3,"target_id":104,"target_slot":5,"type":"INT"},{"id":201,"origin_id":-10,"origin_slot":4,"target_id":104,"target_slot":6,"type":"INT"},{"id":205,"origin_id":111,"origin_slot":0,"target_id":107,"target_slot":0,"type":"FLOAT"},{"id":206,"origin_id":-10,"origin_slot":5,"target_id":111,"target_slot":0,"type":"FLOAT"},{"id":207,"origin_id":-10,"origin_slot":6,"target_id":15,"target_slot":0,"type":"INT"},{"id":221,"origin_id":-10,"origin_slot":7,"target_id":6,"target_slot":0,"type":"COMBO"},{"id":223,"origin_id":-10,"origin_slot":9,"target_id":11,"target_slot":0,"type":"COMBO"},{"id":224,"origin_id":-10,"origin_slot":10,"target_id":24,"target_slot":0,"type":"COMBO"},{"id":227,"origin_id":-10,"origin_slot":8,"target_id":13,"target_slot":0,"type":"COMBO"},{"id":229,"origin_id":10,"origin_slot":0,"target_id":121,"target_slot":0,"type":"IMAGE"},{"id":230,"origin_id":121,"origin_slot":0,"target_id":91,"target_slot":0,"type":"IMAGE"},{"id":235,"origin_id":6,"origin_slot":0,"target_id":123,"target_slot":0,"type":"MODEL"},{"id":241,"origin_id":125,"origin_slot":0,"target_id":16,"target_slot":0,"type":"MODEL"},{"id":242,"origin_id":125,"origin_slot":0,"target_id":9,"target_slot":0,"type":"MODEL"},{"id":255,"origin_id":123,"origin_slot":0,"target_id":122,"target_slot":0,"type":"MODEL"},{"id":259,"origin_id":104,"origin_slot":1,"target_id":14,"target_slot":4,"type":"LATENT"},{"id":261,"origin_id":14,"origin_slot":0,"target_id":132,"target_slot":0,"type":"LATENT"},{"id":262,"origin_id":132,"origin_slot":0,"target_id":10,"target_slot":0,"type":"LATENT"},{"id":263,"origin_id":132,"origin_slot":0,"target_id":23,"target_slot":0,"type":"LATENT"},{"id":265,"origin_id":122,"origin_slot":0,"target_id":134,"target_slot":0,"type":"MODEL"},{"id":266,"origin_id":134,"origin_slot":0,"target_id":125,"target_slot":0,"type":"MODEL"}],"extra":{}}]},"config":{},"extra":{"frontendVersion":"1.48.7","VHS_latentpreview":false,"VHS_latentpreviewrate":0,"VHS_MetadataImage":true,"VHS_KeepIntermediate":true,"ds":{"scale":0.4665330984144085,"offset":[4303.0538923812865,-3760.0078675557006]}},"version":0.4}