diff --git a/models/minimax/minimax-h3-semantic-bridge/README.md b/models/minimax/minimax-h3-semantic-bridge/README.md new file mode 100644 index 0000000..8cc390c --- /dev/null +++ b/models/minimax/minimax-h3-semantic-bridge/README.md @@ -0,0 +1,49 @@ +# MiniMax H3 Semantic Bridge + +## Summary + +Experimental MiniMax H3 conditioning adapter plus example ComfyUI workflow. This is a semantic-control path, not a new base model, and it is aimed at better prompt adherence and consistency on the standard FL2VA route. + +## Model Family + +- `minimax` + +## Status + +- `imported-only` + +## Source + +- Model card: +- Workflow JSON: +- Workflow preview: +- Original publisher: `speach1sdef178` +- Date imported: `2026-09-05` + +## Developer notes + +- The repo describes this as a compact standalone adapter distilled from a teacher bridge, with the actual inference path staying inside standard MiniMax H3 conditioning. +- The example workflow is explicitly a placement reference for ComfyUI, which makes it more useful than a thin model card drop. +- The release says Ref2VA/reference-conditioned workflows are not supported in v1. + +## Our notes + +- This is the most interesting same-day MiniMax control release because it targets semantic structure rather than just motion. +- It looks like a real prompt-adherence helper for FL2VA, but it is still MiniMax H3, so expect it to stay tight to heavy on an RTX 3070. +- Good comparison point if you care about consistency, object relationships, or long prompt obedience more than raw style. + +## Required custom nodes + +- `MiniMax H3 Image to Video + Semantic Bridge` +- `MiniMax H3 Semantic Bridge` +- `MiniMax H3 Clear Semantic Bridge Cache` + +## Required models + +- `MiniMaxAI/MiniMax-H3` +- `MiniMaxH3_SemanticBridge_v1.safetensors` + +## Notes + +- Do not treat this as a Ref2VA/reference-video fix. +- Best used as a semantic-control add-on to an otherwise normal H3 FL2VA workflow. diff --git a/models/minimax/minimax-h3-semantic-bridge/workflow.json b/models/minimax/minimax-h3-semantic-bridge/workflow.json new file mode 100644 index 0000000..436138c --- /dev/null +++ b/models/minimax/minimax-h3-semantic-bridge/workflow.json @@ -0,0 +1,1442 @@ +{ + "id": "43b6670f-acdb-4a4c-85d8-4ab857ee0bf8", + "revision": 0, + "last_node_id": 239, + "last_link_id": 435, + "nodes": [ + { + "id": 116, + "type": "MarkdownNote", + "pos": [ + -2080, + 4840 + ], + "size": [ + 450, + 740 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: MiniMax H3", + "properties": { + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "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- [๐Ÿค— Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)\n\n## About this workflow\n\n**Key inputs**\n\n- **prompt**: describe the shots, camera moves, 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\n" + ], + "widgets_values_named": { + "text": "## 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- [๐Ÿค— Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)\n\n## About this workflow\n\n**Key inputs**\n\n- **prompt**: describe the shots, camera moves, 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\n" + }, + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 117, + "type": "MarkdownNote", + "pos": [ + -2550, + 4840 + ], + "size": [ + 440, + 740 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: Model Links", + "properties": { + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "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```\n๐Ÿ“‚ ComfyUI/\nโ”œโ”€โ”€ ๐Ÿ“‚ models/\nโ”‚ โ”œโ”€โ”€ ๐Ÿ“‚ vae/\nโ”‚ โ”‚ โ”œโ”€โ”€ minimax_h3_video_vae_fp16.safetensors\nโ”‚ โ”‚ โ””โ”€โ”€ minimax_h3_audio_vae_fp32.safetensors\nโ”‚ โ”œโ”€โ”€ ๐Ÿ“‚ diffusion_models/\nโ”‚ โ”‚ โ””โ”€โ”€ minimax_h3_fl2va_pruned_int8_convrot.safetensors\nโ”‚ โ””โ”€โ”€ ๐Ÿ“‚ text_encoders/\nโ”‚ โ””โ”€โ”€ 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" + ], + "widgets_values_named": { + "text": "## 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```\n๐Ÿ“‚ ComfyUI/\nโ”œโ”€โ”€ ๐Ÿ“‚ models/\nโ”‚ โ”œโ”€โ”€ ๐Ÿ“‚ vae/\nโ”‚ โ”‚ โ”œโ”€โ”€ minimax_h3_video_vae_fp16.safetensors\nโ”‚ โ”‚ โ””โ”€โ”€ minimax_h3_audio_vae_fp32.safetensors\nโ”‚ โ”œโ”€โ”€ ๐Ÿ“‚ diffusion_models/\nโ”‚ โ”‚ โ””โ”€โ”€ minimax_h3_fl2va_pruned_int8_convrot.safetensors\nโ”‚ โ””โ”€โ”€ ๐Ÿ“‚ text_encoders/\nโ”‚ โ””โ”€โ”€ 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": 170, + "type": "ModelAttentionBackend", + "pos": [ + 53.31490456352862, + 4587.1127769137665 + ], + "size": [ + 270, + 58 + ], + "flags": {}, + "order": 15, + "mode": 4, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 435 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 361 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "ModelAttentionBackend", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + }, + "widgets_values": [ + "comfy kitchen attention" + ], + "widgets_values_named": { + "attention": "comfy kitchen attention" + } + }, + { + "id": 205, + "type": "MiniMaxH3SigmaShift", + "pos": [ + 362.4571167154204, + 4565.360154079092 + ], + "size": [ + 277.2857421875, + 82 + ], + "flags": {}, + "order": 16, + "mode": 4, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 361 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 409, + 410 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.0", + "Node name for S&R": "MiniMaxH3SigmaShift" + }, + "widgets_values": [ + 6, + 8 + ], + "widgets_values_named": { + "shift_video": 6, + "shift_audio": 8 + } + }, + { + "id": 150, + "type": "BasicGuider", + "pos": [ + 586.0724402397555, + 4781.461072906307 + ], + "size": [ + 171.650390625, + 46 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 410 + }, + { + "name": "conditioning", + "type": "CONDITIONING", + "link": 431 + } + ], + "outputs": [ + { + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 299 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "BasicGuider", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + } + }, + { + "id": 151, + "type": "RandomNoise", + "pos": [ + 779.0542418187488, + 4788.14787160052 + ], + "size": [ + 360, + 90 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "NOISE", + "type": "NOISE", + "links": [ + 298 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "RandomNoise", + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 123456993, + "fixed" + ], + "widgets_values_named": { + "noise_seed": 123456993, + "control_after_generate": "fixed" + } + }, + { + "id": 162, + "type": "SamplerCustomAdvanced", + "pos": [ + 786.1741739974468, + 4621.220632361431 + ], + "size": [ + 299.11875, + 106 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "name": "noise", + "type": "NOISE", + "link": 298 + }, + { + "name": "guider", + "type": "GUIDER", + "link": 299 + }, + { + "name": "sampler", + "type": "SAMPLER", + "link": 300 + }, + { + "name": "sigmas", + "type": "SIGMAS", + "link": 301 + }, + { + "name": "latent_image", + "type": "LATENT", + "link": 432 + } + ], + "outputs": [ + { + "name": "output", + "type": "LATENT", + "links": [ + 303 + ] + }, + { + "name": "denoised_output", + "type": "LATENT", + "links": [ + 403 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "SamplerCustomAdvanced", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + } + }, + { + "id": 152, + "type": "KSamplerSelect", + "pos": [ + 783.1349611179514, + 4933.567930076317 + ], + "size": [ + 370, + 70 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 300 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "KSamplerSelect", + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "res_multistep" + ], + "widgets_values_named": { + "sampler_name": "res_multistep" + } + }, + { + "id": 118, + "type": "MarkdownNote", + "pos": [ + -975.2614015726922, + 4806.501681008329 + ], + "size": [ + 300, + 520 + ], + "flags": { + "collapsed": false + }, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "title": "Note: Size Settings Reference", + "properties": { + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "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" + ], + "widgets_values_named": { + "text": "| 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": 148, + "type": "VAEDecode", + "pos": [ + 1180.863423421403, + 4629.747924945288 + ], + "size": [ + 174.439453125, + 46 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 303 + }, + { + "name": "vae", + "type": "VAE", + "link": 271 + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 336 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "VAEDecode", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + } + }, + { + "id": 147, + "type": "VAEDecodeAudio", + "pos": [ + 1182.8262175410307, + 4734.918256222926 + ], + "size": [ + 189.8052734375, + 46 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 403 + }, + { + "name": "vae", + "type": "VAE", + "link": 358 + } + ], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 405 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "VAEDecodeAudio", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + } + }, + { + "id": 197, + "type": "CreateVideo", + "pos": [ + 1188.763245556849, + 4873.493938382309 + ], + "size": [ + 270, + 102 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 336 + }, + { + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 405 + } + ], + "outputs": [ + { + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 338 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.0", + "Node name for S&R": "CreateVideo" + }, + "widgets_values": [ + 24, + 8 + ], + "widgets_values_named": { + "fps": 24, + "bit_depth": 8 + } + }, + { + "id": 128, + "type": "CLIPLoader", + "pos": [ + -581.4145154465326, + 4875.213711466285 + ], + "size": [ + 617.4670737190092, + 110.98686043188081 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [ + { + "label": "CLIP", + "name": "CLIP", + "type": "CLIP", + "links": [ + 425 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "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", + "directory_invalid": true + } + ], + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors", + "minimax", + "default" + ], + "widgets_values_named": { + "clip_name": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors", + "type": "minimax", + "device": "default" + } + }, + { + "id": 119, + "type": "VAELoader", + "pos": [ + -600.5673983484397, + 5029.1610758331135 + ], + "size": [ + 640, + 70 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "VAE", + "type": "VAE", + "links": [ + 271, + 426 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "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", + "directory_invalid": true + } + ], + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "MiniMax-H3-video_vae_fp16.safetensors" + ], + "widgets_values_named": { + "vae_name": "MiniMax-H3-video_vae_fp16.safetensors" + } + }, + { + "id": 120, + "type": "VAELoader", + "pos": [ + -610.7072190429201, + 5147.894651372963 + ], + "size": [ + 650, + 70 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "VAE", + "type": "VAE", + "links": [ + 358 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "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", + "directory_invalid": true + } + ], + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "minimax_h3_audio_vae_fp32.safetensors" + ], + "widgets_values_named": { + "vae_name": "minimax_h3_audio_vae_fp32.safetensors" + } + }, + { + "id": 235, + "type": "UNETLoader", + "pos": [ + -1171.314186320214, + 5419.245642770581 + ], + "size": [ + 614.0871850613107, + 84.36667172888701 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "label": "ๆจกๅž‹", + "name": "MODEL", + "type": "MODEL", + "links": [] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "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", + "directory_invalid": true + } + ], + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "Minimax_H3\\minimax_h3_fl2va_pruned_int8_convrot.safetensors", + "default" + ], + "widgets_values_named": { + "unet_name": "Minimax_H3\\minimax_h3_fl2va_pruned_int8_convrot.safetensors", + "weight_dtype": "default" + } + }, + { + "id": 196, + "type": "SaveVideo", + "pos": [ + 1199.2717238879377, + 5042.446588426282 + ], + "size": [ + 742.4220960601197, + 106 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "name": "video", + "type": "VIDEO", + "link": 338 + } + ], + "outputs": [ + { + "name": "video", + "type": "VIDEO", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.0", + "Node name for S&R": "SaveVideo" + }, + "widgets_values": [ + "video/minimaxH3", + "auto", + "auto", + "auto" + ], + "widgets_values_named": { + "filename_prefix": "video/minimaxH3", + "format": "auto", + "format.codec": "auto", + "codec": "auto" + } + }, + { + "id": 132, + "type": "ComfyMathExpression", + "pos": [ + -338.6494575187939, + 5267.632205790555 + ], + "size": [ + 360, + 160 + ], + "flags": { + "collapsed": false + }, + "order": 12, + "mode": 0, + "inputs": [ + { + "label": "values.a", + "name": "values.a", + "type": "FLOAT,INT,BOOLEAN", + "link": 242 + }, + { + "label": "b", + "name": "values.b", + "shape": 7, + "type": "FLOAT,INT,BOOLEAN", + "link": null + } + ], + "outputs": [ + { + "label": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": null + }, + { + "label": "INT", + "name": "INT", + "type": "INT", + "links": [ + 430 + ] + }, + { + "label": "BOOL", + "name": "BOOL", + "type": "BOOLEAN", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "ComfyMathExpression", + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17" + ], + "widgets_values_named": { + "expression": "max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17" + } + }, + { + "id": 133, + "type": "PrimitiveFloat", + "pos": [ + -629.1688479412676, + 5278.692791388266 + ], + "size": [ + 270, + 70 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [], + "outputs": [ + { + "label": "FLOAT", + "name": "FLOAT", + "type": "FLOAT", + "links": [ + 242 + ] + } + ], + "title": "Float (duration)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "PrimitiveFloat", + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 5 + ], + "widgets_values_named": { + "value": 5 + } + }, + { + "id": 124, + "type": "BasicScheduler", + "pos": [ + 789.9361952530854, + 5068.446969956297 + ], + "size": [ + 370, + 130 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "label": "ๆจกๅž‹", + "name": "model", + "type": "MODEL", + "link": 409 + } + ], + "outputs": [ + { + "label": "Sigmas", + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 301 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "BasicScheduler", + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "simple", + 20, + 1 + ], + "widgets_values_named": { + "scheduler": "simple", + "steps": 20, + "denoise": 1 + } + }, + { + "id": 138, + "type": "LoraLoaderModelOnly", + "pos": [ + -589.5862089476325, + 4589.910052544407 + ], + "size": [ + 623.011582632911, + 84.41041630292693 + ], + "flags": {}, + "order": 13, + "mode": 4, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 368 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 435 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "LoraLoaderModelOnly", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + }, + "widgets_values": [ + "mimimax H3\\minimax_h3_fl2v_lightx2v_turbo_4step_v0.1_comfy_resized_avg_rank_21_bf16.safetensors", + 0.9000000000000001 + ], + "widgets_values_named": { + "lora_name": "mimimax H3\\minimax_h3_fl2v_lightx2v_turbo_4step_v0.1_comfy_resized_avg_rank_21_bf16.safetensors", + "strength_model": 0.9000000000000001 + } + }, + { + "id": 127, + "type": "UNETLoader", + "pos": [ + -575.8443004602091, + 4742.539399308252 + ], + "size": [ + 614.0871850613107, + 84.36667172888701 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [], + "outputs": [ + { + "label": "ๆจกๅž‹", + "name": "MODEL", + "type": "MODEL", + "links": [ + 368 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "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", + "directory_invalid": true + } + ], + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "Minimax_H3\\minimax_h3_fl2va_pruned_int8_convrot.safetensors", + "default" + ], + "widgets_values_named": { + "unet_name": "Minimax_H3\\minimax_h3_fl2va_pruned_int8_convrot.safetensors", + "weight_dtype": "default" + } + }, + { + "id": 115, + "type": "ResolutionSelector", + "pos": [ + -355.2746547972036, + 5495.456907333554 + ], + "size": [ + 270, + 170 + ], + "flags": {}, + "order": 11, + "mode": 0, + "showAdvanced": true, + "inputs": [], + "outputs": [ + { + "label": "width", + "name": "width", + "type": "INT", + "links": [ + 428 + ] + }, + { + "label": "height", + "name": "height", + "type": "INT", + "links": [ + 429 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.1", + "Node name for S&R": "ResolutionSelector", + "ue_properties": { + "version": "7.8", + "widget_ue_connectable": {}, + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "16:9 (Widescreen)", + 0.8, + 32 + ], + "widgets_values_named": { + "aspect_ratio": "16:9 (Widescreen)", + "megapixels": 0.8, + "multiple": 32 + } + }, + { + "id": 237, + "type": "MiniMaxH3DistilledImageToVideo", + "pos": [ + 85.60989044668027, + 4763.3298400278445 + ], + "size": [ + 482.43930428152805, + 705.2932582786834 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 425 + }, + { + "name": "vae", + "type": "VAE", + "link": 426 + }, + { + "name": "first_frame", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "name": "last_frame", + "shape": 7, + "type": "IMAGE", + "link": null + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 428 + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 429 + }, + { + "name": "length", + "type": "INT", + "widget": { + "name": "length" + }, + "link": 430 + } + ], + "outputs": [ + { + "name": "positive", + "type": "CONDITIONING", + "links": [ + 431 + ] + }, + { + "name": "latent", + "type": "LATENT", + "links": [ + 432 + ] + } + ], + "properties": { + "Node name for S&R": "MiniMaxH3DistilledImageToVideo" + }, + "widgets_values": [ + "A cinematic medium-wide shot of a young woman standing behind a transparent glass table in a sophisticated modern apartment at night. She is wearing a fitted black sleeveless dress and a thin silver necklace.\n\nHer left hand holds a polished stainless-steel cup by its handle at chest height. Her right hand rests flat on the glass tabletop with all five fingers naturally separated and clearly visible. Her hands must remain anatomically correct and attached naturally to her arms.\n\nOn the table in front of her are three distinct objects arranged from left to right: a clear glass bottle filled halfway with water, a small red ceramic bowl, and a folded white paper card with the words \"NIGHT SHIFT\" printed in large clean black letters.\n\nA large wall mirror directly behind the woman reflects the back of her head, shoulders, the room behind the camera, and the warm floor lamp standing on the left side of the room. The reflected objects must correspond logically to their real positions.\n\nWarm amber light from the floor lamp passes through the glass bottle, creating subtle refraction and a bright caustic pattern on the tabletop. Cool blue city light enters through a window on the right and produces contrasting highlights along the polished metal cup.\n\nThe transparent tabletop must remain visibly transparent, with the woman's lower body partially visible through the glass. The metal cup should have realistic sharp reflections, the bottle should refract the background, the ceramic bowl should remain opaque and matte, and the mirror should behave as a true reflective surface.\n\nNatural human proportions, coherent spatial relationships, physically plausible reflections and transparency, realistic hands, detailed material differences, clear readable text.", + "MiniMaxH3_SemanticBridge_v1.safetensors", + 0.15, + "per_token", + 1344, + 768, + 124 + ], + "widgets_values_named": { + "prompt": "A cinematic medium-wide shot of a young woman standing behind a transparent glass table in a sophisticated modern apartment at night. She is wearing a fitted black sleeveless dress and a thin silver necklace.\n\nHer left hand holds a polished stainless-steel cup by its handle at chest height. Her right hand rests flat on the glass tabletop with all five fingers naturally separated and clearly visible. Her hands must remain anatomically correct and attached naturally to her arms.\n\nOn the table in front of her are three distinct objects arranged from left to right: a clear glass bottle filled halfway with water, a small red ceramic bowl, and a folded white paper card with the words \"NIGHT SHIFT\" printed in large clean black letters.\n\nA large wall mirror directly behind the woman reflects the back of her head, shoulders, the room behind the camera, and the warm floor lamp standing on the left side of the room. The reflected objects must correspond logically to their real positions.\n\nWarm amber light from the floor lamp passes through the glass bottle, creating subtle refraction and a bright caustic pattern on the tabletop. Cool blue city light enters through a window on the right and produces contrasting highlights along the polished metal cup.\n\nThe transparent tabletop must remain visibly transparent, with the woman's lower body partially visible through the glass. The metal cup should have realistic sharp reflections, the bottle should refract the background, the ceramic bowl should remain opaque and matte, and the mirror should behave as a true reflective surface.\n\nNatural human proportions, coherent spatial relationships, physically plausible reflections and transparency, realistic hands, detailed material differences, clear readable text.", + "distilled_adapter": "MiniMaxH3_SemanticBridge_v1.safetensors", + "alpha": 0.15, + "magnitude_match": "per_token", + "width": 1344, + "height": 768, + "length": 124 + }, + "color": "#233", + "bgcolor": "#355" + } + ], + "links": [ + [ + 242, + 133, + 0, + 132, + 0, + "FLOAT" + ], + [ + 271, + 119, + 0, + 148, + 1, + "VAE" + ], + [ + 281, + 136, + 0, + 150, + 0, + "MODEL" + ], + [ + 298, + 151, + 0, + 162, + 0, + "NOISE" + ], + [ + 299, + 150, + 0, + 162, + 1, + "GUIDER" + ], + [ + 300, + 152, + 0, + 162, + 2, + "SAMPLER" + ], + [ + 301, + 124, + 0, + 162, + 3, + "SIGMAS" + ], + [ + 303, + 162, + 0, + 148, + 0, + "LATENT" + ], + [ + 336, + 148, + 0, + 197, + 0, + "IMAGE" + ], + [ + 338, + 197, + 0, + 196, + 0, + "VIDEO" + ], + [ + 358, + 120, + 0, + 147, + 1, + "VAE" + ], + [ + 361, + 170, + 0, + 205, + 0, + "MODEL" + ], + [ + 368, + 127, + 0, + 138, + 0, + "MODEL" + ], + [ + 403, + 162, + 1, + 147, + 0, + "LATENT" + ], + [ + 405, + 147, + 0, + 197, + 1, + "AUDIO" + ], + [ + 409, + 205, + 0, + 124, + 0, + "MODEL" + ], + [ + 410, + 205, + 0, + 150, + 0, + "MODEL" + ], + [ + 425, + 128, + 0, + 237, + 0, + "CLIP" + ], + [ + 426, + 119, + 0, + 237, + 1, + "VAE" + ], + [ + 428, + 115, + 0, + 237, + 4, + "INT" + ], + [ + 429, + 115, + 1, + 237, + 5, + "INT" + ], + [ + 430, + 132, + 1, + 237, + 6, + "INT" + ], + [ + 431, + 237, + 0, + 150, + 1, + "CONDITIONING" + ], + [ + 432, + 237, + 1, + 162, + 4, + "LATENT" + ], + [ + 435, + 138, + 0, + 170, + 0, + "MODEL" + ] + ], + "groups": [], + "config": {}, + "extra": { + "frontendVersion": "1.49.6", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ds": { + "scale": 0.4594972986357282, + "offset": [ + 842.6823938177896, + -4110.148796204213 + ] + }, + "0246.VERSION": [ + 0, + 0, + 4 + ], + "ue_links": [], + "links_added_by_ue": [], + "KKvideo_latentpreview": false, + "KKvideo_latentpreviewrate": 0 + }, + "version": 0.4 +} \ No newline at end of file