MiniMax-H3-Ext / MiniMax-H3-Simple-WF /Video-Character-Replace.json
vml12's picture AiNinja94's picture
Duplicate from AiNinja94/MiniMax-H3
82f151b
Raw History Blame Contribute Delete
31.1 kB
{ "id": "e3f2b845-8f2c-4b5a-9caf-eac1029d3e7e", "revision": 0, "last_node_id": 163, "last_link_id": 336, "nodes": [ { "id": 116, "type": "MarkdownNote", "pos": [ -2030, 4850 ], "size": [ 450, 889.6875 ], "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## ComfyUI links\n- [ComfyUI#15224](https://github.com/Comfy-Org/ComfyUI/pull/15224)\n- [πŸ€— Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)\n\n## About this workflow\n\nThis template runs the **reference-to-video (ref2va)** task using the `MiniMaxH3ReferenceToVideo` node. It takes any mix of reference images, videos, and standalone audio, and weaves them into the generation to lock in a character's identity, a style, a motion, a camera move, or a voice.\n\n**Key inputs**\n\n- **ref_images / ref_videos / ref_video_audios / ref_audios**: up to 9 reference images, 3 reference videos (each may carry its own paired soundtrack), and 3 standalone reference audio clips\n- **prompt**: reference the inputs by tag, in the exact order they were connected, for example `<Picture 1>`, `<Video 1>`, `<Audio 1>`, then describe the target scene, motion, and audio\n- **ref_image_size**: `match` scales references down to the generation's resolution (faster); `max` keeps up to a 2048px short edge for stronger identity fidelity, at the cost of speed since reference tokens ride along every sampling step\n- **width / height**: set via Resolution Selector.\n- **duration (seconds)**: converted to a valid frame `length` by the Math Expression node\n\n**Sampling and decode**\n\n- Sampler: `res_multistep`. `beta` or `normal` scheduler tends to outperform `simple` for reference-heavy prompts like this one\n- The sampler's joint audio+video `LATENT` output feeds directly into both `VAEDecode` (video, `minimax_h3_video_vae_fp16`) and `VAEDecodeAudio` (audio, `minimax_h3_audio_vae_fp32`); each decode node automatically pulls its own half out of the packed latent. `CreateVideo` then muxes the two into a single MP4 with synced sound\n- The diffusion model here is `minimax_h3_ref2va_pruned_int8_convrot.safetensors`, a different set of weights from the `fl2va` model used by the t2v/i2v templates\n\nRef2va's output is very sensitive to prompt wording; matching the reference tags precisely and being explicit about which reference drives which part of the shot tends to work best." ], "color": "#222", "bgcolor": "#000" }, { "id": 117, "type": "MarkdownNote", "pos": [ -2500, 4850 ], "size": [ 440, 740 ], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [], "title": "Note: Model Links", "properties": {}, "widgets_values": [ "## Model Links\n[πŸ€— Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)\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_ref2va_pruned_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_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```\nπŸ“‚ ComfyUI/\nβ”œβ”€β”€ πŸ“‚ models/\nβ”‚ β”œβ”€β”€ πŸ“‚ vae/\nβ”‚ β”‚ β”œβ”€β”€ minimax_h3_video_vae_fp16.safetensors\nβ”‚ β”‚ └── minimax_h3_audio_vae_fp32.safetensors\nβ”‚ β”œβ”€β”€ πŸ“‚ diffusion_models/\nβ”‚ β”‚ └── minimax_h3_ref2va_pruned_int8_convrot.safetensors\nβ”‚ └── πŸ“‚ text_encoders/\nβ”‚ └── 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": 119, "type": "VAELoader", "pos": [ -1490, 5270 ], "size": [ 640, 70 ], "flags": {}, "order": 2, "mode": 0, "inputs": [], "outputs": [ { "name": "VAE", "type": "VAE", "links": [ 251, 273 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "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": 120, "type": "VAELoader", "pos": [ -1490, 5400 ], "size": [ 650, 70 ], "flags": {}, "order": 3, "mode": 0, "inputs": [], "outputs": [ { "name": "VAE", "type": "VAE", "links": [ 250, 274 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "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": 121, "type": "VAEDecodeAudio", "pos": [ 480, 5180 ], "size": [ 230, 60 ], "flags": { "collapsed": false }, "order": 21, "mode": 0, "inputs": [ { "name": "samples", "type": "LATENT", "link": 281 }, { "name": "vae", "type": "VAE", "link": 250 } ], "outputs": [ { "name": "AUDIO", "type": "AUDIO", "links": [ 259 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "VAEDecodeAudio" }, "widgets_values": [] }, { "id": 122, "type": "VAEDecode", "pos": [ 480, 5060 ], "size": [ 230, 60 ], "flags": { "collapsed": false }, "order": 20, "mode": 0, "inputs": [ { "name": "samples", "type": "LATENT", "link": 280 }, { "name": "vae", "type": "VAE", "link": 251 } ], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 258 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "VAEDecode" }, "widgets_values": [] }, { "id": 123, "type": "KSamplerSelect", "pos": [ -260, 5190 ], "size": [ 370, 70 ], "flags": {}, "order": 4, "mode": 0, "inputs": [], "outputs": [ { "name": "SAMPLER", "type": "SAMPLER", "links": [ 255 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "KSamplerSelect" }, "widgets_values": [ "res_multistep" ] }, { "id": 124, "type": "BasicScheduler", "pos": [ -260, 5310 ], "size": [ 370, 130 ], "flags": {}, "order": 14, "mode": 0, "inputs": [ { "name": "model", "type": "MODEL", "link": 336 } ], "outputs": [ { "name": "SIGMAS", "type": "SIGMAS", "links": [ 256 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "BasicScheduler" }, "widgets_values": [ "simple", 20, 1 ] }, { "id": 125, "type": "SamplerCustomAdvanced", "pos": [ 150, 5110 ], "size": [ 230, 140 ], "flags": {}, "order": 19, "mode": 0, "inputs": [ { "name": "noise", "type": "NOISE", "link": 253 }, { "name": "guider", "type": "GUIDER", "link": 254 }, { "name": "sampler", "type": "SAMPLER", "link": 255 }, { "name": "sigmas", "type": "SIGMAS", "link": 256 }, { "name": "latent_image", "type": "LATENT", "link": 271 } ], "outputs": [ { "name": "output", "type": "LATENT", "links": [ 280, 281 ] }, { "name": "denoised_output", "type": "LATENT", "links": [] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "SamplerCustomAdvanced" }, "widgets_values": [] }, { "id": 126, "type": "BasicGuider", "pos": [ -260, 5080 ], "size": [ 360, 60 ], "flags": {}, "order": 18, "mode": 0, "inputs": [ { "name": "model", "type": "MODEL", "link": 335 }, { "name": "conditioning", "type": "CONDITIONING", "link": 270 } ], "outputs": [ { "name": "GUIDER", "type": "GUIDER", "links": [ 254 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "BasicGuider" }, "widgets_values": [] }, { "id": 128, "type": "CLIPLoader", "pos": [ -1490, 5090 ], "size": [ 640, 120 ], "flags": {}, "order": 5, "mode": 0, "inputs": [], "outputs": [ { "name": "CLIP", "type": "CLIP", "links": [ 272 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "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": 129, "type": "RandomNoise", "pos": [ -260, 4940 ], "size": [ 360, 90 ], "flags": {}, "order": 6, "mode": 0, "inputs": [], "outputs": [ { "name": "NOISE", "type": "NOISE", "links": [ 253 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "RandomNoise" }, "widgets_values": [ 296996517754094, "randomize" ] }, { "id": 130, "type": "CreateVideo", "pos": [ 790, 5090 ], "size": [ 270, 110 ], "flags": {}, "order": 22, "mode": 0, "inputs": [ { "name": "images", "type": "IMAGE", "link": 258 }, { "name": "audio", "shape": 7, "type": "AUDIO", "link": 259 } ], "outputs": [ { "name": "VIDEO", "type": "VIDEO", "links": [ 260 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "CreateVideo" }, "widgets_values": [ 24, 8 ] }, { "id": 131, "type": "ComfyMathExpression", "pos": [ -1448.2183770501144, 5941.1878211298945 ], "size": [ 225, 74 ], "flags": { "collapsed": true }, "order": 15, "mode": 0, "inputs": [ { "label": "a", "name": "values.a", "type": "FLOAT,INT,BOOLEAN", "link": 261 }, { "label": "b", "name": "values.b", "shape": 7, "type": "FLOAT,INT,BOOLEAN", "link": null } ], "outputs": [ { "name": "FLOAT", "type": "FLOAT", "links": [] }, { "name": "INT", "type": "INT", "links": [ 275 ] }, { "name": "BOOL", "type": "BOOLEAN", "links": [] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "ComfyMathExpression" }, "widgets_values": [ "max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17" ] }, { "id": 140, "type": "MarkdownNote", "pos": [ -1890, 5830 ], "size": [ 300, 520 ], "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": 92, "type": "SaveVideo", "pos": [ 1150, 4880 ], "size": [ 1418, 106 ], "flags": {}, "order": 23, "mode": 0, "inputs": [ { "name": "video", "type": "VIDEO", "link": 260 } ], "outputs": [ { "name": "video", "type": "VIDEO", "links": null } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "SaveVideo" }, "widgets_values": [ "video/MiniMax_H3", "auto", "auto" ] }, { "id": 115, "type": "ResolutionSelector", "pos": [ -1482.138067159315, 5611.841062941608 ], "size": [ 270, 170 ], "flags": {}, "order": 8, "mode": 0, "showAdvanced": false, "inputs": [], "outputs": [ { "name": "width", "type": "INT", "links": [ 276 ] }, { "name": "height", "type": "INT", "links": [ 277 ] } ], "title": "Resolution Selector (Size)", "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "ResolutionSelector" }, "widgets_values": [ "16:9 (Widescreen)", 0.2, 32 ], "color": "#322", "bgcolor": "#533" }, { "id": 136, "type": "MiniMaxH3ReferenceToVideo", "pos": [ -576.722303511993, 4115.869445495487 ], "size": [ 410, 384 ], "flags": {}, "order": 17, "mode": 0, "inputs": [ { "name": "clip", "type": "CLIP", "link": 272 }, { "name": "vae", "type": "VAE", "link": 273 }, { "name": "audio_vae", "type": "VAE", "link": 274 }, { "label": "ref_image_0", "name": "ref_images.ref_image_0", "shape": 7, "type": "IMAGE", "link": 318 }, { "label": "ref_image_1", "name": "ref_images.ref_image_1", "shape": 7, "type": "IMAGE", "link": null }, { "label": "ref_video_0", "name": "ref_videos.ref_video_0", "shape": 7, "type": "IMAGE", "link": 319 }, { "label": "ref_video_1", "name": "ref_videos.ref_video_1", "shape": 7, "type": "IMAGE", "link": null }, { "label": "ref_video_audio_0", "name": "ref_video_audios.ref_video_audio_0", "shape": 7, "type": "AUDIO", "link": 320 }, { "label": "ref_video_audio_1", "name": "ref_video_audios.ref_video_audio_1", "shape": 7, "type": "AUDIO", "link": null }, { "label": "ref_audio_0", "name": "ref_audios.ref_audio_0", "shape": 7, "type": "AUDIO", "link": null }, { "name": "prompt", "type": "STRING", "widget": { "name": "prompt" }, "link": 322 }, { "name": "width", "type": "INT", "widget": { "name": "width" }, "link": 276 }, { "name": "height", "type": "INT", "widget": { "name": "height" }, "link": 277 }, { "name": "length", "type": "INT", "widget": { "name": "length" }, "link": 275 } ], "outputs": [ { "name": "positive", "type": "CONDITIONING", "links": [ 270 ] }, { "name": "LATENT", "type": "LATENT", "links": [ 271 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "MiniMaxH3ReferenceToVideo" }, "widgets_values": [ "", 1344, 768, 124, "match" ] }, { "id": 127, "type": "UNETLoader", "pos": [ -1490, 4940 ], "size": [ 640, 90 ], "flags": {}, "order": 9, "mode": 0, "inputs": [], "outputs": [ { "name": "MODEL", "type": "MODEL", "links": [ 335, 336 ] } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "UNETLoader", "models": [ { "name": "minimax_h3_ref2va_pruned_int8_convrot.safetensors", "url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors", "directory": "diffusion_models" } ] }, "widgets_values": [ "minimax_h3_ref2va_pruned_int8_convrot.safetensors", "default" ] }, { "id": 139, "type": "LoadImage", "pos": [ -949.4341019080288, 3627.4035449394714 ], "size": [ 290, 330 ], "flags": {}, "order": 10, "mode": 0, "inputs": [], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 318 ] }, { "name": "MASK", "type": "MASK", "links": null } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "LoadImage" }, "widgets_values": [ "Clipboard_Image_2.jpg", "image" ] }, { "id": 156, "type": "PreviewAudio", "pos": [ -1036.0443645625392, 4111.358249099259 ], "size": [ 344.1139099633126, 88 ], "flags": {}, "order": 16, "mode": 0, "inputs": [ { "name": "audio", "type": "AUDIO", "link": 311 } ], "outputs": [ { "name": "audio", "type": "AUDIO", "links": null } ], "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "PreviewAudio" }, "widgets_values": [] }, { "id": 158, "type": "PrimitiveStringMultiline", "pos": [ -1639.6439036106224, 4403.919854860954 ], "size": [ 559.5333674296926, 294.1604012654452 ], "flags": {}, "order": 11, "mode": 0, "inputs": [], "outputs": [ { "name": "STRING", "type": "STRING", "links": [ 322 ] } ], "title": "Input Text (Prompt)", "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "PrimitiveStringMultiline" }, "widgets_values": [ "Use <Picture 1> as the exact replacement dinosaur design: preserve its dark armored scales, tall jagged sail, electric-blue glowing markings, sharp teeth, heavy tail, and muscular silhouette.\n\nUse <Audio 1> as the synchronized soundtrack reference for <Video 1>. Use <Video 1> as the motion, timing, framing, and background reference.\n\nReplace only the Tyrannosaurus Rex in <Video 1> with the dinosaur from <Picture 1>. Preserve the original video’s leftward walking direction, pace, camera angle, lighting, plain background, and 8-second timing. From 0 to 5 seconds, the blue lightning dinosaur walks steadily toward the left, matching the original body movement, leg rhythm, head motion, and tail sway. At 5 seconds, it opens its jaws and roars in exact sync with the roar in <Audio 1>, continuing through 7.5 seconds while it keeps moving left. Its blue markings glow subtly brighter during the roar, without changing the original scene lighting. From 7.5 to 8 seconds, it closes its jaws and continues the same leftward walk.\n\nRemove the original Tyrannosaurus Rex completely. No text, captions, watermark, logo, additional animals, camera changes, or background changes." ], "color": "#322", "bgcolor": "#533" }, { "id": 132, "type": "PrimitiveFloat", "pos": [ -1478.2183770501144, 5831.1878211298945 ], "size": [ 270, 70 ], "flags": {}, "order": 12, "mode": 0, "inputs": [], "outputs": [ { "name": "FLOAT", "type": "FLOAT", "links": [ 261 ] } ], "title": "Float (Duration)", "properties": { "cnr_id": "comfy-core", "ver": "0.30.0", "Node name for S&R": "PrimitiveFloat" }, "widgets_values": [ 4 ], "color": "#322", "bgcolor": "#533" }, { "id": 155, "type": "VHS_LoadVideo", "pos": [ -1401.0253329483758, 3849.300379974716 ], "size": [ 309.81935340959626, 486.89846415780755 ], "flags": {}, "order": 13, "mode": 0, "inputs": [ { "name": "meta_batch", "shape": 7, "type": "VHS_BatchManager", "link": null }, { "name": "vae", "shape": 7, "type": "VAE", "link": null } ], "outputs": [ { "name": "IMAGE", "type": "IMAGE", "links": [ 319 ] }, { "name": "frame_count", "type": "INT", "links": null }, { "name": "audio", "type": "AUDIO", "links": [ 311, 320 ] }, { "name": "video_info", "type": "VHS_VIDEOINFO", "links": null } ], "properties": { "cnr_id": "comfyui-videohelpersuite", "ver": "1.7.9", "Node name for S&R": "VHS_LoadVideo" }, "widgets_values": { "video": "T-Rex walk and roar (720p_30fps_H264-128kbit_AAC).mp4", "force_rate": 24, "custom_width": 0, "custom_height": 0, "frame_load_cap": 96, "skip_first_frames": 591, "select_every_nth": 1, "format": "AnimateDiff", "videopreview": { "hidden": false, "paused": false, "params": { "filename": "T-Rex walk and roar (720p_30fps_H264-128kbit_AAC).mp4", "type": "input", "format": "video/mp4", "force_rate": 24, "custom_width": 0, "custom_height": 0, "frame_load_cap": 96, "skip_first_frames": 591, "select_every_nth": 1 } } } } ], "links": [ [ 250, 120, 0, 121, 1, "VAE" ], [ 251, 119, 0, 122, 1, "VAE" ], [ 253, 129, 0, 125, 0, "NOISE" ], [ 254, 126, 0, 125, 1, "GUIDER" ], [ 255, 123, 0, 125, 2, "SAMPLER" ], [ 256, 124, 0, 125, 3, "SIGMAS" ], [ 258, 122, 0, 130, 0, "IMAGE" ], [ 259, 121, 0, 130, 1, "AUDIO" ], [ 260, 130, 0, 92, 0, "VIDEO" ], [ 261, 132, 0, 131, 0, "FLOAT" ], [ 270, 136, 0, 126, 1, "CONDITIONING" ], [ 271, 136, 1, 125, 4, "LATENT" ], [ 272, 128, 0, 136, 0, "CLIP" ], [ 273, 119, 0, 136, 1, "VAE" ], [ 274, 120, 0, 136, 2, "VAE" ], [ 275, 131, 1, 136, 13, "INT" ], [ 276, 115, 0, 136, 11, "INT" ], [ 277, 115, 1, 136, 12, "INT" ], [ 280, 125, 0, 122, 0, "LATENT" ], [ 281, 125, 0, 121, 0, "LATENT" ], [ 311, 155, 2, 156, 0, "AUDIO" ], [ 318, 139, 0, 136, 3, "IMAGE" ], [ 319, 155, 0, 136, 5, "IMAGE" ], [ 320, 155, 2, 136, 7, "AUDIO" ], [ 322, 158, 0, 136, 10, "STRING" ], [ 335, 127, 0, 126, 0, "MODEL" ], [ 336, 127, 0, 124, 0, "MODEL" ] ], "groups": [ { "id": 1, "title": "Models", "bounding": [ -1520, 4840, 700, 670 ], "color": "#3f789e", "flags": {} }, { "id": 2, "title": "Sampling", "bounding": [ -280, 4840, 690, 670 ], "color": "#3f789e", "flags": {} }, { "id": 3, "title": "Conditioning", "bounding": [ -790, 4840, 480, 670 ], "color": "#3f789e", "flags": {} }, { "id": 4, "title": "Decoding and create video", "bounding": [ 440, 4840, 670, 670 ], "color": "#3f789e", "flags": {} }, { "id": 5, "title": "User Inputs", "bounding": [ -1518.2183770501144, 5541.1878211298945, 1930, 900 ], "color": "#3f789e", "flags": {} } ], "config": {}, "extra": { "ds": { "scale": 1.0204888367607132, "offset": [ 1811.3854815464474, -3467.121078280455 ] }, "frontendVersion": "1.47.12", "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "VHS_MetadataImage": true, "VHS_KeepIntermediate": true }, "version": 0.4 }
{
"id": "e3f2b845-8f2c-4b5a-9caf-eac1029d3e7e",
"revision": 0,
"last_node_id": 163,
"last_link_id": 336,
"nodes": [
{
"id": 116,
"type": "MarkdownNote",
"pos": [
-2030,
4850
],
"size": [
450,
889.6875
],
"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## ComfyUI links\n- [ComfyUI#15224](https://github.com/Comfy-Org/ComfyUI/pull/15224)\n- [πŸ€— Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)\n\n## About this workflow\n\nThis template runs the **reference-to-video (ref2va)** task using the `MiniMaxH3ReferenceToVideo` node. It takes any mix of reference images, videos, and standalone audio, and weaves them into the generation to lock in a character's identity, a style, a motion, a camera move, or a voice.\n\n**Key inputs**\n\n- **ref_images / ref_videos / ref_video_audios / ref_audios**: up to 9 reference images, 3 reference videos (each may carry its own paired soundtrack), and 3 standalone reference audio clips\n- **prompt**: reference the inputs by tag, in the exact order they were connected, for example `<Picture 1>`, `<Video 1>`, `<Audio 1>`, then describe the target scene, motion, and audio\n- **ref_image_size**: `match` scales references down to the generation's resolution (faster); `max` keeps up to a 2048px short edge for stronger identity fidelity, at the cost of speed since reference tokens ride along every sampling step\n- **width / height**: set via Resolution Selector.\n- **duration (seconds)**: converted to a valid frame `length` by the Math Expression node\n\n**Sampling and decode**\n\n- Sampler: `res_multistep`. `beta` or `normal` scheduler tends to outperform `simple` for reference-heavy prompts like this one\n- The sampler's joint audio+video `LATENT` output feeds directly into both `VAEDecode` (video, `minimax_h3_video_vae_fp16`) and `VAEDecodeAudio` (audio, `minimax_h3_audio_vae_fp32`); each decode node automatically pulls its own half out of the packed latent. `CreateVideo` then muxes the two into a single MP4 with synced sound\n- The diffusion model here is `minimax_h3_ref2va_pruned_int8_convrot.safetensors`, a different set of weights from the `fl2va` model used by the t2v/i2v templates\n\nRef2va's output is very sensitive to prompt wording; matching the reference tags precisely and being explicit about which reference drives which part of the shot tends to work best."
],
"color": "#222",
"bgcolor": "#000"
},
{
"id": 117,
"type": "MarkdownNote",
"pos": [
-2500,
4850
],
"size": [
440,
740
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Note: Model Links",
"properties": {},
"widgets_values": [
"## Model Links\n[πŸ€— Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)\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_ref2va_pruned_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_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```\nπŸ“‚ ComfyUI/\nβ”œβ”€β”€ πŸ“‚ models/\nβ”‚ β”œβ”€β”€ πŸ“‚ vae/\nβ”‚ β”‚ β”œβ”€β”€ minimax_h3_video_vae_fp16.safetensors\nβ”‚ β”‚ └── minimax_h3_audio_vae_fp32.safetensors\nβ”‚ β”œβ”€β”€ πŸ“‚ diffusion_models/\nβ”‚ β”‚ └── minimax_h3_ref2va_pruned_int8_convrot.safetensors\nβ”‚ └── πŸ“‚ text_encoders/\nβ”‚ └── 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": 119,
"type": "VAELoader",
"pos": [
-1490,
5270
],
"size": [
640,
70
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
251,
273
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.0",
"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": 120,
"type": "VAELoader",
"pos": [
-1490,