{ "id": "e3f2b845-8f2c-4b5a-9caf-eac1029d3e7e", "revision": 0, "last_node_id": 144, "last_link_id": 264, "nodes": [ { "id": 125, "type": "VAEDecodeAudio", "pos": [ 1504.3436741920136, 5102.84180850804 ], "size": [ 230, 60 ], "flags": { "collapsed": false }, "order": 21, "mode": 0, "inputs": [ { "name": "samples", "type": "LATENT", "link": 250 }, { "name": "vae", "type": "VAE", "link": 232 } ], "outputs": [ { "name": "AUDIO", "type": "AUDIO", "links": [ 241 ] } ], "properties": { "Node name for S&R": "VAEDecodeAudio" }, "widgets_values": [] }, { "id": 126, "type": "VAEDecode", "pos": [ 1504.3436741920136, 4982.84180850804 ], "size": [ 230, 60 ], "flags": { "collapsed": false }, "order": 20, "mode": 0, "inputs": [ { "name": "samples", "type": "LATENT", "link": 249 }, { "name": "vae", "type": "VAE", "link": 233 } ], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 240 ] } ], "properties": { "Node name for S&R": "VAEDecode" }, "widgets_values": [] }, { "id": 127, "type": "KSamplerSelect", "pos": [ 754.3436741920119, 5082.84180850804 ], "size": [ 370, 70 ], "flags": {}, "order": 0, "mode": 0, "inputs": [], "outputs": [ { "name": "SAMPLER", "type": "SAMPLER", "links": [ 236 ] } ], "properties": { "Node name for S&R": "KSamplerSelect" }, "widgets_values": [ "res_multistep" ] }, { "id": 128, "type": "BasicScheduler", "pos": [ 754.3436741920119, 5232.84180850804 ], "size": [ 370, 130 ], "flags": {}, "order": 13, "mode": 0, "inputs": [ { "name": "model", "type": "MODEL", "link": 252 } ], "outputs": [ { "name": "SIGMAS", "type": "SIGMAS", "links": [ 237 ] } ], "properties": { "Node name for S&R": "BasicScheduler" }, "widgets_values": [ "simple", 20, 1 ] }, { "id": 129, "type": "SamplerCustomAdvanced", "pos": [ 1174.343674192014, 4992.84180850804 ], "size": [ 230, 326 ], "flags": {}, "order": 19, "mode": 0, "inputs": [ { "name": "noise", "type": "NOISE", "link": 234 }, { "name": "guider", "type": "GUIDER", "link": 235 }, { "name": "sampler", "type": "SAMPLER", "link": 236 }, { "name": "sigmas", "type": "SIGMAS", "link": 237 }, { "name": "latent_image", "type": "LATENT", "link": 238 } ], "outputs": [ { "name": "output", "type": "LATENT", "links": [ 249, 250 ] }, { "name": "denoised_output", "type": "LATENT", "links": [] } ], "properties": { "Node name for S&R": "SamplerCustomAdvanced" }, "widgets_values": [] }, { "id": 130, "type": "BasicGuider", "pos": [ 754.3436741920119, 4952.84180850804 ], "size": [ 360, 60 ], "flags": {}, "order": 18, "mode": 0, "inputs": [ { "name": "model", "type": "MODEL", "link": 251 }, { "name": "conditioning", "type": "CONDITIONING", "link": 239 } ], "outputs": [ { "name": "GUIDER", "type": "GUIDER", "links": [ 235 ] } ], "properties": { "Node name for S&R": "BasicGuider" }, "widgets_values": [] }, { "id": 131, "type": "RandomNoise", "pos": [ 754.3436741920119, 4792.84180850804 ], "size": [ 360, 90 ], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [ { "name": "NOISE", "type": "NOISE", "links": [ 234 ] } ], "properties": { "Node name for S&R": "RandomNoise" }, "widgets_values": [ 377090417907782, "randomize" ] }, { "id": 132, "type": "CreateVideo", "pos": [ 1834.3436741920134, 5022.84180850804 ], "size": [ 270, 110 ], "flags": {}, "order": 22, "mode": 0, "inputs": [ { "name": "images", "type": "IMAGE", "link": 240 }, { "name": "audio", "shape": 7, "type": "AUDIO", "link": 241 } ], "outputs": [ { "name": "VIDEO", "type": "VIDEO", "links": [ 243 ] } ], "properties": { "Node name for S&R": "CreateVideo" }, "widgets_values": [ 24, 8 ] }, { "id": 137, "type": "CLIPLoader", "pos": [ -1028.614205605988, 4914.079072013463 ], "size": [ 640, 120 ], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [ { "name": "CLIP", "type": "CLIP", "links": [ 253 ] } ], "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": 123, "type": "VAELoader", "pos": [ -1027.2448705901845, 5082.007892845488 ], "size": [ 640, 70 ], "flags": {}, "order": 3, "mode": 0, "inputs": [], "outputs": [ { "name": "VAE", "type": "VAE", "links": [ 233, 242 ] } ], "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": 124, "type": "VAELoader", "pos": [ -1022.8303604967551, 5198.831335948759 ], "size": [ 650, 70 ], "flags": {}, "order": 4, "mode": 0, "inputs": [], "outputs": [ { "name": "VAE", "type": "VAE", "links": [ 232 ] } ], "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": 116, "type": "MarkdownNote", "pos": [ -2090, 4859.170828307019 ], "size": [ 450, 630 ], "flags": {}, "order": 5, "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": 139, "type": "MarkdownNote", "pos": [ -2553.008105306386, 4859.170828307019 ], "size": [ 440, 740 ], "flags": {}, "order": 6, "mode": 0, "inputs": [], "outputs": [], "title": "Note: Model Links", "properties": {}, "widgets_values": [ "## Model Links\n\n**custom node**\n- [molbal/comfyui-gguf](https://github.com/molbal/ComfyUI-GGUF)\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- [huggingface.co/molbal/MiniMax-H3-GGUF](https://huggingface.co/molbal/MiniMax-H3-GGUF/tree/main)\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```\nšŸ“‚ ComfyUI/\nā”œā”€ā”€ šŸ“‚ models/\nā”‚ ā”œā”€ā”€ šŸ“‚ vae/\nā”‚ ā”‚ ā”œā”€ā”€ minimax_h3_video_vae_fp16.safetensors\nā”‚ ā”‚ ā””ā”€ā”€ minimax_h3_audio_vae_fp32.safetensors\nā”‚ ā”œā”€ā”€ šŸ“‚ diffusion_models/\nā”‚ ā”‚ ā””ā”€ā”€ minimax_h3_fl2va_pruned_fp8_Q4_0.gguf (for 12GB VRAM)\nā”‚ ā”‚ ā””ā”€ā”€ minimax_h3_fl2va_pruned_fp8_U16G.gguf (for 16GB VRAM)\nā”‚ ā”‚ ā””ā”€ā”€ minimax_h3_fl2va_pruned_fp8_Q8_CR.gguf (for 24GB VRAM)\nā”‚ ā””ā”€ā”€ šŸ“‚ text_encoders/\nā”‚ ā””ā”€ā”€ qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors\n```\n" ], "color": "#222", "bgcolor": "#000" }, { "id": 140, "type": "MarkdownNote", "pos": [ -1617.7462785417983, 4859.170828307019 ], "size": [ 311.69225934899896, 717.4700138836661 ], "flags": {}, "order": 7, "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": 136, "type": "UnetLoaderGGUFDynamicVRAM", "pos": [ -1023.49266491632, 4760.1717907100365 ], "size": [ 643.942726048325, 81.51696798516332 ], "flags": {}, "order": 8, "mode": 0, "inputs": [], "outputs": [ { "name": "MODEL", "type": "MODEL", "links": [ 251, 252 ] } ], "properties": { "Node name for S&R": "UnetLoaderGGUFDynamicVRAM" }, "widgets_values": [ "minimax_h3_fl2va_pruned_fp8_Q8_CR.gguf" ] }, { "id": 115, "type": "ResolutionSelector", "pos": [ 185.0814504107869, 5277.830565943016 ], "size": [ 270, 170 ], "flags": {}, "order": 9, "mode": 0, "showAdvanced": false, "inputs": [], "outputs": [ { "name": "width", "type": "INT", "links": [ 246, 257, 260 ] }, { "name": "height", "type": "INT", "links": [ 247, 258, 261 ] } ], "properties": { "Node name for S&R": "ResolutionSelector" }, "widgets_values": [ "16:9 (Widescreen)", 0.5, 32 ], "color": "#432", "bgcolor": "#653" }, { "id": 135, "type": "PrimitiveFloat", "pos": [ 189.82228558245396, 5490.663557276217 ], "size": [ 270, 70 ], "flags": {}, "order": 10, "mode": 0, "inputs": [], "outputs": [ { "name": "FLOAT", "type": "FLOAT", "links": [ 248 ] } ], "title": "Float (duration)", "properties": { "Node name for S&R": "PrimitiveFloat" }, "widgets_values": [ 5 ], "color": "#432", "bgcolor": "#653" }, { "id": 133, "type": "MiniMaxH3ImageToVideo", "pos": [ 184.04923000076874, 4770.9411635818215 ], "size": [ 425.9868090059731, 468.73165762357075 ], "flags": {}, "order": 17, "mode": 0, "inputs": [ { "name": "clip", "type": "CLIP", "link": 253 }, { "name": "vae", "type": "VAE", "link": 242 }, { "name": "first_frame", "shape": 7, "type": "IMAGE", "link": 263 }, { "name": "last_frame", "shape": 7, "type": "IMAGE", "link": 264 }, { "name": "width", "type": "INT", "widget": { "name": "width" }, "link": 246 }, { "name": "height", "type": "INT", "widget": { "name": "height" }, "link": 247 }, { "name": "length", "type": "INT", "widget": { "name": "length" }, "link": 245 } ], "outputs": [ { "name": "positive", "type": "CONDITIONING", "links": [ 239 ] }, { "name": "LATENT", "type": "LATENT", "links": [ 238 ] } ], "properties": { "Node name for S&R": "MiniMaxH3ImageToVideo" }, "widgets_values": [ "Animation based on the starship Cerritors orbiting over a planet.\n\nTimeline:\n- [0s-1s] Camera pans right following the animated starship as it flies across deep space.\n- [1s-3.5s] The ship's nacelles glow brightly before the ship instantly accelerates forward at incredibly fast warp speed among a brief flash.\n- [3.5s-5s] The title card appears displaying the text 'Minimax H3' and secondary title 'GGUF U16G'.\n\nStyle & Constraints:\n- Cinematic cuts between scenes only.\n- All text rendered cleanly in clear English fonts without subtitle bars.\n- Audio: Orchestral dramatic sci-fi theme song.", 1344, 768, 73 ], "color": "#432", "bgcolor": "#653" }, { "id": 142, "type": "ResizeImageMaskNode", "pos": [ -59.039312201001934, 5238.886169328033 ], "size": [ 270, 117 ], "flags": { "collapsed": true }, "order": 16, "mode": 0, "inputs": [ { "name": "input", "type": "IMAGE,MASK", "link": 255 }, { "name": "resize_type.width", "type": "INT", "widget": { "name": "resize_type.width" }, "link": 257 }, { "name": "resize_type.height", "type": "INT", "widget": { "name": "resize_type.height" }, "link": 258 } ], "outputs": [ { "name": "resized", "type": "IMAGE", "links": [ 264 ] } ], "properties": { "Node name for S&R": "ResizeImageMaskNode" }, "widgets_values": [ "scale dimensions", 512, 512, "center", "nearest-exact" ] }, { "id": 144, "type": "ResizeImageMaskNode", "pos": [ -62.51383357231729, 4803.6972738032 ], "size": [ 270, 117 ], "flags": { "collapsed": true }, "order": 15, "mode": 0, "inputs": [ { "name": "input", "type": "IMAGE,MASK", "link": 262 }, { "name": "resize_type.width", "type": "INT", "widget": { "name": "resize_type.width" }, "link": 260 }, { "name": "resize_type.height", "type": "INT", "widget": { "name": "resize_type.height" }, "link": 261 } ], "outputs": [ { "name": "resized", "type": "IMAGE", "links": [ 263 ] } ], "properties": { "Node name for S&R": "ResizeImageMaskNode" }, "widgets_values": [ "scale dimensions", 512, 512, "center", "nearest-exact" ] }, { "id": 114, "type": "LoadImage", "pos": [ -314.36613710564006, 4754.095595328364 ], "size": [ 444.2348204252912, 408.3079543923486 ], "flags": {}, "order": 11, "mode": 0, "inputs": [], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 262 ] }, { "name": "MASK", "type": "MASK", "links": null } ], "title": "First Frame", "properties": { "Node name for S&R": "LoadImage" }, "widgets_values": [ "bg-cerritos-exterior-01.jpg", "image" ], "color": "#432", "bgcolor": "#653" }, { "id": 134, "type": "ComfyMathExpression", "pos": [ 493.8546644686473, 5518.962889604648 ], "size": [ 360, 160 ], "flags": { "collapsed": true }, "order": 14, "mode": 0, "inputs": [ { "label": "a", "name": "values.a", "type": "FLOAT,INT,BOOLEAN", "link": 248 }, { "label": "b", "name": "values.b", "shape": 7, "type": "FLOAT,INT,BOOLEAN", "link": null } ], "outputs": [ { "name": "FLOAT", "type": "FLOAT", "links": [] }, { "name": "INT", "type": "INT", "links": [ 245 ] }, { "name": "BOOL", "type": "BOOLEAN", "links": [] } ], "properties": { "Node name for S&R": "ComfyMathExpression" }, "widgets_values": [ "max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17" ] }, { "id": 92, "type": "SaveVideo", "pos": [ 2174.95681408446, 4719.961416797485 ], "size": [ 1030, 681.6666666666666 ], "flags": {}, "order": 23, "mode": 0, "inputs": [ { "name": "video", "type": "VIDEO", "link": 243 } ], "outputs": [ { "name": "video", "type": "VIDEO", "links": null } ], "properties": {}, "widgets_values": [ "video/MiniMax_H3", "auto", "auto" ], "color": "#322", "bgcolor": "#533" }, { "id": 141, "type": "LoadImage", "pos": [ -314.36613710564006, 5218.850739362215 ], "size": [ 443.231446130073, 344.0959416540245 ], "flags": {}, "order": 12, "mode": 0, "inputs": [], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 255 ] }, { "name": "MASK", "type": "MASK", "links": null } ], "title": "Last Frame", "properties": { "Node name for S&R": "LoadImage" }, "widgets_values": [ "bg-cerritos-exterior-01.jpg", "image" ], "color": "#432", "bgcolor": "#653" } ], "links": [ [ 232, 124, 0, 125, 1, "VAE" ], [ 233, 123, 0, 126, 1, "VAE" ], [ 234, 131, 0, 129, 0, "NOISE" ], [ 235, 130, 0, 129, 1, "GUIDER" ], [ 236, 127, 0, 129, 2, "SAMPLER" ], [ 237, 128, 0, 129, 3, "SIGMAS" ], [ 238, 133, 1, 129, 4, "LATENT" ], [ 239, 133, 0, 130, 1, "CONDITIONING" ], [ 240, 126, 0, 132, 0, "IMAGE" ], [ 241, 125, 0, 132, 1, "AUDIO" ], [ 242, 123, 0, 133, 1, "VAE" ], [ 243, 132, 0, 92, 0, "VIDEO" ], [ 245, 134, 1, 133, 6, "INT" ], [ 246, 115, 0, 133, 4, "INT" ], [ 247, 115, 1, 133, 5, "INT" ], [ 248, 135, 0, 134, 0, "FLOAT" ], [ 249, 129, 0, 126, 0, "LATENT" ], [ 250, 129, 0, 125, 0, "LATENT" ], [ 251, 136, 0, 130, 0, "MODEL" ], [ 252, 136, 0, 128, 0, "MODEL" ], [ 253, 137, 0, 133, 0, "CLIP" ], [ 255, 141, 0, 142, 0, "IMAGE" ], [ 257, 115, 0, 142, 1, "INT" ], [ 258, 115, 1, 142, 2, "INT" ], [ 260, 115, 0, 144, 1, "INT" ], [ 261, 115, 1, 144, 2, "INT" ], [ 262, 114, 0, 144, 0, "IMAGE" ], [ 263, 144, 0, 133, 2, "IMAGE" ], [ 264, 142, 0, 133, 3, "IMAGE" ] ], "groups": [ { "id": 1, "title": "Models", "bounding": [ -1059.4521256368994, 4685.884889742085, 700, 800 ], "color": "#3f789e", "flags": {} }, { "id": 2, "title": "Sampling", "bounding": [ 724.3436741920119, 4672.84180850804, 700, 800 ], "color": "#3f789e", "flags": {} }, { "id": 3, "title": "Conditioning", "bounding": [ -337.4785076249539, 4689.898128577804, 1037.942458830953, 891.2011202160556 ], "color": "#b58b2a", "flags": {} }, { "id": 4, "title": "Decoding and create video", "bounding": [ 1444.3436741920134, 4672.84180850804, 700, 800 ], "color": "#3f789e", "flags": {} } ], "config": {}, "extra": { "frontendVersion": "1.47.11", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true, "ds": { "scale": 0.6589738064516181, "offset": [ 1789.6737618047343, -4320.981954487378 ] } }, "version": 0.4 }