diff --git a/models/minimax/minimax-h3-turbo-gguf-i2va/README.md b/models/minimax/minimax-h3-turbo-gguf-i2va/README.md new file mode 100644 index 0000000..1b097e5 --- /dev/null +++ b/models/minimax/minimax-h3-turbo-gguf-i2va/README.md @@ -0,0 +1,49 @@ +# MiniMax H3 Turbo GGUF I2VA + +## Summary + +`MiniMax H3` image-plus-audio-to-video workflow from the same-day `ChrisColeTech` turbo GGUF repo. + +## Model Family + +- `minimax` + +## Status + +- `imported-only` + +## Source + +- Model card: +- Workflow file: +- Original publisher: `ChrisColeTech` +- Date imported: `2026-08-18` + +## Developer notes + +- The source repo says this is a turbo merge with the `FL2VA` and `REF2VA` pruned DiTs baked into a GGUF package. +- The workflow uses the `Q6_K` turbo GGUF path in the source JSON, but the repo also ships other quantized variants. +- The workflow includes an audio decode path plus an `EmptyMiniMaxH3LatentAV` node, so this is the audio-aware MiniMax lane rather than a plain T2V demo. + +## Our notes + +- This is the most useful same-day MiniMax workflow source I found because it is real, importable, and clearly aimed at lower-memory local testing. +- On an `RTX 3070` with `8 GB` VRAM it is still tight, but the workflow's bundled Q4/Q6/Q8 split files make it a better practical bet than a raw full-precision stack. +- If you want a fast MiniMax test that is not just a model dump, this is the one I would open first. + +## Required custom nodes + +- `CCTechClipProjLoader` +- current MiniMax H3 ComfyUI support + +## Required models + +- `minimax_h3_fl2va_turbo_Q6_K.gguf` +- `qwen3vl_8b_fp8_scaled.safetensors` +- `mmh3-8b-ClipProj-v3-mlp.safetensors` +- `minimax_h3_video_vae_fp16.safetensors` +- `minimax_h3_audio_vae_fp32.safetensors` + +## Notes + +- Best same-day workflow import from Hugging Face today. diff --git a/models/minimax/minimax-h3-turbo-gguf-i2va/workflow.json b/models/minimax/minimax-h3-turbo-gguf-i2va/workflow.json new file mode 100644 index 0000000..6bdc116 --- /dev/null +++ b/models/minimax/minimax-h3-turbo-gguf-i2va/workflow.json @@ -0,0 +1,874 @@ +{ + "id": "366280af-df34-46de-8ff6-1989d1c9d0bd", + "revision": 0, + "last_node_id": 83, + "last_link_id": 177, + "nodes": [ + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 1038.464663261795, + -140.15562367064052 + ], + "size": [ + 225, + 71.640625 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 159 + }, + { + "name": "vae", + "type": "VAE", + "link": 168 + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "slot_index": 0, + "links": [ + 166 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "Node name for S&R": "VAEDecode", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.8", + "input_ue_unconnectable": {} + } + } + }, + { + "id": 7, + "type": "CLIPTextEncode", + "pos": [ + 180.8418644617353, + 122.42057434601358 + ], + "size": [ + 423.28125, + 178.59375 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 177 + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "slot_index": 0, + "links": [ + 162 + ] + } + ], + "title": "CLIP Text Encode (Negative Prompt)", + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "Node name for S&R": "CLIPTextEncode", + "ue_properties": { + "widget_ue_connectable": { + "text": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "low quality, blurry" + ], + "widgets_values_named": { + "text": "low quality, blurry" + }, + "color": "#322", + "bgcolor": "#533" + }, + { + "id": 51, + "type": "VAEDecodeAudio", + "pos": [ + 1037.861720864651, + -20.78073128535177 + ], + "size": [ + 225, + 53.984375 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 160 + }, + { + "name": "vae", + "type": "VAE", + "link": 169 + } + ], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 167 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "Node name for S&R": "VAEDecodeAudio", + "ue_properties": { + "widget_ue_connectable": {}, + "version": "7.8", + "input_ue_unconnectable": {} + } + } + }, + { + "id": 68, + "type": "EmptyMiniMaxH3LatentAV", + "pos": [ + 679.7989659858497, + 231.97445926051296 + ], + "size": [ + 292.109375, + 117.96875 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 163 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "Node name for S&R": "EmptyMiniMaxH3LatentAV", + "ue_properties": { + "widget_ue_connectable": { + "width": true, + "height": true, + "length": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 1024, + 736, + 243 + ], + "widgets_values_named": { + "width": 1024, + "height": 736, + "length": 243 + } + }, + { + "id": 73, + "type": "UnetLoaderGGUFAdvanced", + "pos": [ + 543.8469076597547, + -420.8560007799525 + ], + "size": [ + 336.09375, + 169.921875 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 164 + ] + } + ], + "properties": { + "cnr_id": "comfyui-gguf-loader", + "ver": "1.0.1", + "Node name for S&R": "UnetLoaderGGUFAdvanced", + "ue_properties": { + "widget_ue_connectable": { + "unet_name": true, + "dequant_dtype": true, + "patch_dtype": true, + "patch_on_device": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "minimax_h3_fl2va_turbo_Q6_K.gguf", + "target", + "float16", + true + ], + "widgets_values_named": { + "unet_name": "minimax_h3_fl2va_turbo_Q6_K.gguf", + "dequant_dtype": "target", + "patch_dtype": "float16", + "patch_on_device": true + } + }, + { + "id": 75, + "type": "KSamplerAdvanced", + "pos": [ + 669.4151164039017, + -147.00295822030066 + ], + "size": [ + 312.34375, + 333.984375 + ], + "flags": {}, + "order": 7, + "mode": 0, + "showAdvanced": false, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 164 + }, + { + "name": "positive", + "type": "CONDITIONING", + "link": 172 + }, + { + "name": "negative", + "type": "CONDITIONING", + "link": 162 + }, + { + "name": "latent_image", + "type": "LATENT", + "link": 163 + } + ], + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 159, + 160 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "Node name for S&R": "KSamplerAdvanced", + "ue_properties": { + "widget_ue_connectable": { + "add_noise": true, + "noise_seed": true, + "steps": true, + "cfg": true, + "sampler_name": true, + "scheduler": true, + "start_at_step": true, + "end_at_step": true, + "return_with_leftover_noise": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "enable", + 44443814813405, + "randomize", + 12, + 1, + "res_multistep", + "simple", + 0, + 10000, + "disable" + ], + "widgets_values_named": { + "add_noise": "enable", + "noise_seed": 44443814813405, + "control_after_generate": "randomize", + "steps": 12, + "cfg": 1, + "sampler_name": "res_multistep", + "scheduler": "simple", + "start_at_step": 0, + "end_at_step": 10000, + "return_with_leftover_noise": "disable" + } + }, + { + "id": 77, + "type": "CreateVideo", + "pos": [ + 1528.6918424554513, + -114.52591649363228 + ], + "size": [ + 270, + 109.921875 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 166 + }, + { + "name": "audio", + "shape": 7, + "type": "AUDIO", + "link": 167 + } + ], + "outputs": [ + { + "name": "VIDEO", + "type": "VIDEO", + "links": [ + 165 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "Node name for S&R": "CreateVideo", + "ue_properties": { + "widget_ue_connectable": { + "fps": true, + "bit_depth": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + 24, + 8 + ], + "widgets_values_named": { + "fps": 24, + "bit_depth": 8 + } + }, + { + "id": 78, + "type": "SaveVideo", + "pos": [ + 1534.5082743775135, + 48.335029345701784 + ], + "size": [ + 270, + 357.78125 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "video", + "type": "VIDEO", + "link": 165 + } + ], + "outputs": [ + { + "name": "video", + "type": "VIDEO", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.32.0", + "ue_properties": { + "widget_ue_connectable": { + "filename_prefix": true, + "format": true, + "codec": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "video/minimax-h3-turbo", + "auto", + "auto" + ], + "widgets_values_named": { + "filename_prefix": "video/minimax-h3-turbo", + "format": "auto", + "codec": "auto" + } + }, + { + "id": 79, + "type": "CCTechDualVAELoader", + "pos": [ + 903.4671261731579, + -403.0970193781772 + ], + "size": [ + 336.640625, + 133.90625 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "video_vae", + "type": "VAE", + "links": [ + 168, + 174 + ] + }, + { + "name": "audio_vae", + "type": "VAE", + "links": [ + 169 + ] + } + ], + "properties": { + "cnr_id": "comfyui-gguf-loader", + "ver": "1.0.1", + "Node name for S&R": "CCTechDualVAELoader", + "ue_properties": { + "widget_ue_connectable": { + "video_vae_name": true, + "audio_vae_name": true + }, + "version": "7.8", + "input_ue_unconnectable": {} + } + }, + "widgets_values": [ + "minimax_h3_video_vae_fp16.safetensors", + "minimax_h3_audio_vae_fp32.safetensors" + ], + "widgets_values_named": { + "video_vae_name": "minimax_h3_video_vae_fp16.safetensors", + "audio_vae_name": "minimax_h3_audio_vae_fp32.safetensors" + } + }, + { + "id": 81, + "type": "TextEncodeQwenImageEdit", + "pos": [ + 201.81431682088083, + -154.57993803459848 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 176 + }, + { + "name": "vae", + "shape": 7, + "type": "VAE", + "link": 174 + }, + { + "name": "image", + "shape": 7, + "type": "IMAGE", + "link": 175 + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 172 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.0", + "Node name for S&R": "TextEncodeQwenImageEdit", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + }, + "widgets_values": [ + "make her fly, full body shot, playful music" + ], + "widgets_values_named": { + "prompt": "make her fly, full body shot, playful music" + } + }, + { + "id": 82, + "type": "LoadImage", + "pos": [ + -176.33359297733517, + -142.4081055935555 + ], + "size": [ + 282.734375, + 321.890625 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 175 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.33.0", + "Node name for S&R": "LoadImage", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + }, + "widgets_values": [ + "ComfyUI_00003.png", + "image" + ], + "widgets_values_named": { + "image": "ComfyUI_00003.png", + "upload": "image" + } + }, + { + "id": 83, + "type": "CCTechClipProjLoader", + "pos": [ + 175.81623049712607, + -414.1243868581415 + ], + "size": [ + 328.046875, + 141.828125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "CLIP", + "type": "CLIP", + "links": [ + 176, + 177 + ] + } + ], + "properties": { + "cnr_id": "comfyui-gguf-loader", + "ver": "1.4.1", + "Node name for S&R": "CCTechClipProjLoader", + "ue_properties": { + "widget_ue_connectable": {}, + "input_ue_unconnectable": {}, + "version": "7.8" + } + }, + "widgets_values": [ + "qwen3vl_8b_fp8_scaled.safetensors", + "auto", + "mmh3-8b-ClipProj-v3-mlp.safetensors" + ], + "widgets_values_named": { + "clip_name": "qwen3vl_8b_fp8_scaled.safetensors", + "type": "auto", + "projection": "mmh3-8b-ClipProj-v3-mlp.safetensors" + } + } + ], + "links": [ + [ + 159, + 75, + 0, + 8, + 0, + "LATENT" + ], + [ + 160, + 75, + 0, + 51, + 0, + "LATENT" + ], + [ + 162, + 7, + 0, + 75, + 2, + "CONDITIONING" + ], + [ + 163, + 68, + 0, + 75, + 3, + "LATENT" + ], + [ + 164, + 73, + 0, + 75, + 0, + "MODEL" + ], + [ + 165, + 77, + 0, + 78, + 0, + "VIDEO" + ], + [ + 166, + 8, + 0, + 77, + 0, + "IMAGE" + ], + [ + 167, + 51, + 0, + 77, + 1, + "AUDIO" + ], + [ + 168, + 79, + 0, + 8, + 1, + "VAE" + ], + [ + 169, + 79, + 1, + 51, + 1, + "VAE" + ], + [ + 172, + 81, + 0, + 75, + 1, + "CONDITIONING" + ], + [ + 174, + 79, + 0, + 81, + 1, + "VAE" + ], + [ + 175, + 82, + 0, + 81, + 2, + "IMAGE" + ], + [ + 176, + 83, + 0, + 81, + 0, + "CLIP" + ], + [ + 177, + 83, + 0, + 7, + 0, + "CLIP" + ] + ], + "groups": [ + { + "id": 1, + "title": "Loaders", + "bounding": [ + 149.03320227519978, + -493.94593430779815, + 1135.3429700039073, + 261.03757516536433 + ], + "color": "#3f789e", + "flags": {} + }, + { + "id": 2, + "title": "Save", + "bounding": [ + 1514.9356881131998, + -187.925655472603, + 305.0422276256443, + 382.45627049311906 + ], + "color": "#3f789e", + "flags": {} + }, + { + "id": 3, + "title": "Sampler", + "bounding": [ + 643.0777407644214, + -217.35632425131726, + 356.4138250250036, + 609.4262900469166 + ], + "color": "#3f789e", + "flags": {} + }, + { + "id": 4, + "title": "Prompt", + "bounding": [ + 153.555533943543, + -210.57284231939354, + 485.14093636076666, + 562.0432969383874 + ], + "color": "#3f789e", + "flags": {} + }, + { + "id": 5, + "title": "Decode", + "bounding": [ + 1020.8404987703558, + -211.1811507399694, + 254.8753026052974, + 265.3999523582605 + ], + "color": "#3f789e", + "flags": {} + }, + { + "id": 6, + "title": "Input", + "bounding": [ + -228.87681748467992, + -207.75739980458934, + 366.809965433087, + 416.27975947492394 + ], + "color": "#3f789e", + "flags": {} + } + ], + "config": {}, + "extra": { + "ds": { + "scale": 0.7268514088707215, + "offset": [ + 356.6794319123364, + 651.8451223107105 + ] + }, + "ue_links": [], + "links_added_by_ue": [], + "frontendVersion": "1.49.6" + }, + "version": 0.4 +} \ No newline at end of file