MiniMax H3 reference to video: raw JSON
Use reference media and a written prompt to guide video generation with audio.
23 KB ยท JSON file
{
"id": "e3f2b845-8f2c-4b5a-9caf-eac1029d3e7e",
"revision": 0,
"last_node_id": 140,
"last_link_id": 282,
"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": [
""
],
"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": [
""
],
"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": "0.30.1",
"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"
}
]
},
"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": "0.30.1",
"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"
}
]
},
"widgets_values": [
"minimax_h3_audio_vae_fp32.safetensors"
]
},
{
"id": 122,
"type": "VAEDecode",
"pos": [
480,
5060
],
"size": [
230,
60
],
"flags": {
"collapsed": false
},
"order": 19,
"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": "0.30.1",
"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": "0.30.1",
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"res_multistep"
]
},
{
"id": 124,
"type": "BasicScheduler",
"pos": [
-260,
5310
],
"size": [
370,
130
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 252
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
256
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "BasicScheduler"
},
"widgets_values": [
"simple",
20,
1
]
},
{
"id": 125,
"type": "SamplerCustomAdvanced",
"pos": [
150,
5110
],
"size": [
230,
140
],
"flags": {},
"order": 18,
"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": "0.30.1",
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 126,
"type": "BasicGuider",
"pos": [
-260,
5080
],
"size": [
360,
60
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 257
},
{
"name": "conditioning",
"type": "CONDITIONING",
"link": 270
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
254
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "BasicGuider"
},
"widgets_values": []
},
{
"id": 129,
"type": "RandomNoise",
"pos": [
-260,
4940
],
"size": [
360,
90
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
253
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
575549648673280,
"randomize"
]
},
{
"id": 130,
"type": "CreateVideo",
"pos": [
790,
5090
],
"size": [
270,
110
],
"flags": {},
"order": 21,
"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": "0.30.1",
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
24,
8
]
},
{
"id": 132,
"type": "PrimitiveFloat",
"pos": [
-1480,
5830
],
"size": [
270,
70
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "FLOAT",
"type": "FLOAT",
"links": [
261
]
}
],
"title": "Float (Duration)",
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "PrimitiveFloat"
},
"widgets_values": [
5
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 136,
"type": "MiniMaxH3ReferenceToVideo",
"pos": [
-750,
4940
],
"size": [
410,
530
],
"flags": {},
"order": 16,
"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": 278
},
{
"label": "ref_image_1",
"name": "ref_images.ref_image_1",
"shape": 7,
"type": "IMAGE",
"link": 282
},
{
"label": "ref_image_2",
"name": "ref_images.ref_image_2",
"shape": 7,
"type": "IMAGE",
"link": null
},
{
"label": "ref_video_0",
"name": "ref_videos.ref_video_0",
"shape": 7,
"type": "IMAGE",
"link": null
},
{
"label": "ref_video_audio_0",
"name": "ref_video_audios.ref_video_audio_0",
"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": 279
},
{
"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": "0.30.1",
"Node name for S&R": "MiniMaxH3ReferenceToVideo"
},
"widgets_values": [
"prompt",
1344,
768,
124,
"match"
]
},
{
"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": [
""
],
"color": "#222",
"bgcolor": "#000"
},
{
"id": 127,
"type": "UNETLoader",
"pos": [
-1490,
4940
],
"size": [
640,
90
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
252,
257
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"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": 128,
"type": "CLIPLoader",
"pos": [
-1490,
5090
],
"size": [
640,
120
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
272
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "qwen3vl_32b_minimax_h3_int8_convrot.safetensors",
"url": "https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"qwen3vl_32b_minimax_h3_int8_convrot.safetensors",
"minimax",
"default"
]
},
{
"id": 131,
"type": "ComfyMathExpression",
"pos": [
-1425.213452795095,
5955.151180856628
],
"size": [
225,
74
],
"flags": {
"collapsed": true
},
"order": 14,
"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": "0.30.1",
"Node name for S&R": "ComfyMathExpression"
},
"widgets_values": [
"max(5, round(a * 24)) + (5 - (max(5, round(a * 24)) % 17)) % 17"
]
},
{
"id": 115,
"type": "ResolutionSelector",
"pos": [
-1480,
5610
],
"size": [
270,
170
],
"flags": {},
"order": 10,
"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": "0.30.1",
"Node name for S&R": "ResolutionSelector"
},
"widgets_values": [
"16:9 (Widescreen)",
1,
32
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 92,
"type": "SaveVideo",
"pos": [
1150,
4880
],
"size": [
1293.037835285697,
828.234877035251
],
"flags": {},
"order": 22,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 260
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1"
},
"widgets_values": [
"video/MiniMax_H3",
"auto",
"auto"
]
},
{
"id": 121,
"type": "VAEDecodeAudio",
"pos": [
471.3916367714808,
5176.35356195682
],
"size": [
230,
60
],
"flags": {
"collapsed": false
},
"order": 20,
"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": "0.30.1",
"Node name for S&R": "VAEDecodeAudio"
},
"widgets_values": []
},
{
"id": 138,
"type": "PrimitiveStringMultiline",
"pos": [
-1480,
6000
],
"size": [
370,
390
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": [
279
]
}
],
"title": "Input Text (Prompt)",
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "PrimitiveStringMultiline"
},
"widgets_values": [
"prompt"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 137,
"type": "LoadImage",
"pos": [
-990.981795314844,
5630.616156752944
],
"size": [
382.48764794147155,
593.8220998346542
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
278
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"seed_1.jpg",
"image"
]
},
{
"id": 139,
"type": "LoadImage",
"pos": [
-580,
5630
],
"size": [
290,
330
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
282
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.30.1",
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"mecha_dragon_lightning.png",
"image"
]
}
],
"links": [
[
250,
120,
0,
121,
1,
"VAE"
],
[
251,
119,
0,
122,
1,
"VAE"
],
[
252,
127,
0,
124,
0,
"MODEL"
],
[
253,
129,
0,
125,
0,
"NOISE"
],
[
254,
126,
0,
125,
1,
"GUIDER"
],
[
255,
123,
0,
125,
2,
"SAMPLER"
],
[
256,
124,
0,
125,
3,
"SIGMAS"
],
[
257,
127,
0,
126,
0,
"MODEL"
],
[
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,
12,
"INT"
],
[
276,
115,
0,
136,
10,
"INT"
],
[
277,
115,
1,
136,
11,
"INT"
],
[
278,
137,
0,
136,
3,
"IMAGE"
],
[
279,
138,
0,
136,
9,
"STRING"
],
[
280,
125,
0,
122,
0,
"LATENT"
],
[
281,
125,
0,
121,
0,
"LATENT"
],
[
282,
139,
0,
136,
4,
"IMAGE"
]
],
"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": [
-1520,
5540,
1930,
900
],
"color": "#3f789e",
"flags": {}
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.6305740690573794,
"offset": [
2768.5410569148244,
-4496.788380272165
]
},
"frontendVersion": "1.47.12",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}