787 lines
17 KiB
JSON
787 lines
17 KiB
JSON
{
|
|
"id": "e7a4e606-6510-4c4e-b127-9a8b6bf3ea71",
|
|
"revision": 0,
|
|
"last_node_id": 11,
|
|
"last_link_id": 5,
|
|
"nodes": [
|
|
{
|
|
"id": 1,
|
|
"type": "LoadImage",
|
|
"pos": [
|
|
40,
|
|
100
|
|
],
|
|
"size": [
|
|
320,
|
|
300
|
|
],
|
|
"flags": {},
|
|
"order": 0,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"localized_name": "image",
|
|
"name": "image",
|
|
"type": "COMBO",
|
|
"widget": {
|
|
"name": "image"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "choose file to upload",
|
|
"name": "upload",
|
|
"type": "IMAGEUPLOAD",
|
|
"widget": {
|
|
"name": "upload"
|
|
},
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "IMAGE",
|
|
"name": "IMAGE",
|
|
"type": "IMAGE",
|
|
"links": [
|
|
1
|
|
]
|
|
},
|
|
{
|
|
"localized_name": "MASK",
|
|
"name": "MASK",
|
|
"type": "MASK",
|
|
"links": null
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "LoadImage"
|
|
},
|
|
"widgets_values": [
|
|
"h3_reference.png",
|
|
"image"
|
|
],
|
|
"title": "Reference image \u2014 select a local file"
|
|
},
|
|
{
|
|
"type": "LoadVideo",
|
|
"size": [
|
|
320,
|
|
200
|
|
],
|
|
"flags": {},
|
|
"inputs": [],
|
|
"outputs": [
|
|
{
|
|
"name": "VIDEO",
|
|
"type": "VIDEO",
|
|
"links": null
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "LoadVideo"
|
|
},
|
|
"widgets_values": [
|
|
"h3_reference.mp4"
|
|
],
|
|
"id": 2,
|
|
"pos": [
|
|
40,
|
|
470
|
|
],
|
|
"order": 1,
|
|
"mode": 0,
|
|
"title": "Optional reference video"
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "LoadAudio",
|
|
"pos": [
|
|
40,
|
|
1100
|
|
],
|
|
"size": [
|
|
320,
|
|
160
|
|
],
|
|
"flags": {},
|
|
"order": 2,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"localized_name": "audio",
|
|
"name": "audio",
|
|
"type": "COMBO",
|
|
"widget": {
|
|
"name": "audio"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "audioUI",
|
|
"name": "audioUI",
|
|
"type": "AUDIO_UI",
|
|
"widget": {
|
|
"name": "audioUI"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "choose file to upload",
|
|
"name": "upload",
|
|
"type": "AUDIOUPLOAD",
|
|
"widget": {
|
|
"name": "upload"
|
|
},
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "AUDIO",
|
|
"name": "AUDIO",
|
|
"type": "AUDIO",
|
|
"links": null
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "LoadAudio"
|
|
},
|
|
"widgets_values": [
|
|
"h3_reference.wav",
|
|
null,
|
|
""
|
|
],
|
|
"title": "Optional reference audio"
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "VLLMOmniVideoReferences",
|
|
"pos": [
|
|
420,
|
|
100
|
|
],
|
|
"size": [
|
|
300,
|
|
365
|
|
],
|
|
"flags": {},
|
|
"order": 3,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"name": "image_1",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": 1
|
|
},
|
|
{
|
|
"name": "image_2",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "audio_1",
|
|
"type": "AUDIO",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "audio_2",
|
|
"type": "AUDIO",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "video_1",
|
|
"type": "VIDEO",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "video_2",
|
|
"type": "VIDEO",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_3",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_4",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_5",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_6",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_7",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_8",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "image_9",
|
|
"type": "IMAGE",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "audio_3",
|
|
"type": "AUDIO",
|
|
"shape": 7,
|
|
"link": null
|
|
},
|
|
{
|
|
"name": "video_3",
|
|
"type": "VIDEO",
|
|
"shape": 7,
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "references",
|
|
"name": "references",
|
|
"type": "VIDEO_REFERENCES",
|
|
"links": [
|
|
2
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VLLMOmniVideoReferences"
|
|
},
|
|
"widgets_values": [],
|
|
"title": "References \u2014 up to 12 total"
|
|
},
|
|
{
|
|
"id": 5,
|
|
"type": "VLLMOmniDiffusionSampling",
|
|
"pos": [
|
|
420,
|
|
530
|
|
],
|
|
"size": [
|
|
310,
|
|
275
|
|
],
|
|
"flags": {},
|
|
"order": 4,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"localized_name": "n",
|
|
"name": "n",
|
|
"type": "INT",
|
|
"widget": {
|
|
"name": "n"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "num_inference_steps",
|
|
"name": "num_inference_steps",
|
|
"type": "INT",
|
|
"widget": {
|
|
"name": "num_inference_steps"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "guidance_scale",
|
|
"name": "guidance_scale",
|
|
"type": "FLOAT",
|
|
"widget": {
|
|
"name": "guidance_scale"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "true_cfg_scale",
|
|
"name": "true_cfg_scale",
|
|
"type": "FLOAT",
|
|
"widget": {
|
|
"name": "true_cfg_scale"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "vae_use_slicing",
|
|
"name": "vae_use_slicing",
|
|
"type": "BOOLEAN",
|
|
"widget": {
|
|
"name": "vae_use_slicing"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "vae_use_tiling",
|
|
"name": "vae_use_tiling",
|
|
"type": "BOOLEAN",
|
|
"widget": {
|
|
"name": "vae_use_tiling"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "seed",
|
|
"name": "seed",
|
|
"type": "INT",
|
|
"widget": {
|
|
"name": "seed"
|
|
},
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "diffusion sampling params",
|
|
"name": "diffusion sampling params",
|
|
"type": "SAMPLING_PARAMS",
|
|
"links": [
|
|
3
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VLLMOmniDiffusionSampling"
|
|
},
|
|
"widgets_values": [
|
|
1,
|
|
50,
|
|
1.0,
|
|
1.0,
|
|
false,
|
|
false,
|
|
42,
|
|
"fixed"
|
|
],
|
|
"title": "Sampling \u2014 base 50 / Turbo 5"
|
|
},
|
|
{
|
|
"id": 6,
|
|
"type": "VLLMOmniMiniMaxH3Params",
|
|
"pos": [
|
|
790,
|
|
750
|
|
],
|
|
"size": [
|
|
310,
|
|
105
|
|
],
|
|
"flags": {},
|
|
"order": 5,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"localized_name": "audio_flow_shift",
|
|
"name": "audio_flow_shift",
|
|
"type": "FLOAT",
|
|
"widget": {
|
|
"name": "audio_flow_shift"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "flow_shift",
|
|
"name": "flow_shift",
|
|
"type": "FLOAT",
|
|
"widget": {
|
|
"name": "flow_shift"
|
|
},
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "MiniMax-H3 video params",
|
|
"name": "MiniMax-H3 video params",
|
|
"type": "VIDEO_PARAMS",
|
|
"links": [
|
|
4
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VLLMOmniMiniMaxH3Params"
|
|
},
|
|
"widgets_values": [
|
|
3.0,
|
|
12.0
|
|
],
|
|
"title": "H3 video/audio flow shifts"
|
|
},
|
|
{
|
|
"type": "VLLMOmniRemoteLoRA",
|
|
"size": [
|
|
310,
|
|
180
|
|
],
|
|
"flags": {},
|
|
"inputs": [],
|
|
"outputs": [
|
|
{
|
|
"name": "lora",
|
|
"type": "REMOTE_LORA",
|
|
"links": null
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VLLMOmniRemoteLoRA"
|
|
},
|
|
"widgets_values": [
|
|
"",
|
|
"h3-ref2va-turbo",
|
|
1.0,
|
|
0
|
|
],
|
|
"id": 7,
|
|
"pos": [
|
|
420,
|
|
940
|
|
],
|
|
"order": 6,
|
|
"mode": 0,
|
|
"title": "Optional Turbo LoRA \u2014 connect to enable"
|
|
},
|
|
{
|
|
"id": 8,
|
|
"type": "VLLMOmniGenerateVideo",
|
|
"pos": [
|
|
800,
|
|
100
|
|
],
|
|
"size": [
|
|
470,
|
|
560
|
|
],
|
|
"flags": {},
|
|
"order": 7,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"localized_name": "frame",
|
|
"name": "frame",
|
|
"shape": 7,
|
|
"type": "IMAGE",
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "references",
|
|
"name": "references",
|
|
"shape": 7,
|
|
"type": "VIDEO_REFERENCES",
|
|
"link": 2
|
|
},
|
|
{
|
|
"localized_name": "sampling_params",
|
|
"name": "sampling_params",
|
|
"shape": 7,
|
|
"type": "SAMPLING_PARAMS",
|
|
"link": 3
|
|
},
|
|
{
|
|
"localized_name": "lora",
|
|
"name": "lora",
|
|
"shape": 7,
|
|
"type": "REMOTE_LORA",
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "model_params",
|
|
"name": "model_params",
|
|
"shape": 7,
|
|
"type": "VIDEO_PARAMS",
|
|
"link": 4
|
|
},
|
|
{
|
|
"localized_name": "url",
|
|
"name": "url",
|
|
"type": "STRING",
|
|
"widget": {
|
|
"name": "url"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "model",
|
|
"name": "model",
|
|
"type": "STRING",
|
|
"widget": {
|
|
"name": "model"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "prompt",
|
|
"name": "prompt",
|
|
"type": "STRING",
|
|
"widget": {
|
|
"name": "prompt"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "negative_prompt",
|
|
"name": "negative_prompt",
|
|
"type": "STRING",
|
|
"widget": {
|
|
"name": "negative_prompt"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "width",
|
|
"name": "width",
|
|
"type": "INT",
|
|
"widget": {
|
|
"name": "width"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "height",
|
|
"name": "height",
|
|
"type": "INT",
|
|
"widget": {
|
|
"name": "height"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "fps",
|
|
"name": "fps",
|
|
"type": "INT",
|
|
"widget": {
|
|
"name": "fps"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "duration",
|
|
"name": "duration",
|
|
"type": "FLOAT",
|
|
"widget": {
|
|
"name": "duration"
|
|
},
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "video",
|
|
"name": "video",
|
|
"type": "VIDEO",
|
|
"links": [
|
|
5
|
|
]
|
|
}
|
|
],
|
|
"properties": {
|
|
"Node name for S&R": "VLLMOmniGenerateVideo"
|
|
},
|
|
"widgets_values": [
|
|
"http://localhost:8000/v1",
|
|
"MiniMaxAI/MiniMax-H3",
|
|
"Use the subject and visual style from <Picture 1>. Create a cinematic shot with a gentle camera move and natural ambient sound.",
|
|
"",
|
|
1344,
|
|
768,
|
|
24,
|
|
5.167
|
|
],
|
|
"title": "MiniMax-H3 Reference to Video"
|
|
},
|
|
{
|
|
"id": 9,
|
|
"type": "SaveVideo",
|
|
"pos": [
|
|
1360,
|
|
100
|
|
],
|
|
"size": [
|
|
410,
|
|
420
|
|
],
|
|
"flags": {},
|
|
"order": 8,
|
|
"mode": 0,
|
|
"inputs": [
|
|
{
|
|
"localized_name": "video",
|
|
"name": "video",
|
|
"type": "VIDEO",
|
|
"link": 5
|
|
},
|
|
{
|
|
"localized_name": "filename_prefix",
|
|
"name": "filename_prefix",
|
|
"type": "STRING",
|
|
"widget": {
|
|
"name": "filename_prefix"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "format",
|
|
"name": "format",
|
|
"type": "COMBO",
|
|
"widget": {
|
|
"name": "format"
|
|
},
|
|
"link": null
|
|
},
|
|
{
|
|
"localized_name": "codec",
|
|
"name": "codec",
|
|
"type": "COMFY_DYNAMICCOMBO_V3",
|
|
"widget": {
|
|
"name": "codec"
|
|
},
|
|
"link": null
|
|
}
|
|
],
|
|
"outputs": [
|
|
{
|
|
"localized_name": "video",
|
|
"name": "video",
|
|
"type": "VIDEO",
|
|
"links": null
|
|
}
|
|
],
|
|
"properties": {},
|
|
"widgets_values": [
|
|
"video/MiniMax-H3-Ref2VA",
|
|
"mp4",
|
|
"h264"
|
|
],
|
|
"title": "Save generated video with audio"
|
|
},
|
|
{
|
|
"id": 10,
|
|
"type": "MarkdownNote",
|
|
"pos": [
|
|
1360,
|
|
590
|
|
],
|
|
"size": [
|
|
440,
|
|
595
|
|
],
|
|
"flags": {},
|
|
"order": 9,
|
|
"mode": 0,
|
|
"inputs": [],
|
|
"outputs": [],
|
|
"title": "Reference inputs and output settings",
|
|
"properties": {},
|
|
"widgets_values": [
|
|
"## Reference to Video\nSelect an image, set the server URL and served model name, then run.\n\nConnect the optional video/audio loaders to Video References, or duplicate loaders for more inputs: up to 9 images, 3 videos, 3 audio clips, 12 total. At least one image or video is required.\n\nSlots are numbered separately per media type. Empty slots are skipped. Update prompt tags such as <Picture 1>, <Video 1>, <Audio 1> to match the connected references. Videos keep their own soundtrack in the reference upload.\n\n**Output:** 24 FPS; 124 frames (~5.17 s). Valid frame counts are 107, 124, 141, 158, 175, 192, 209, 226, 243, 260, 277, 294, 311, 328, 345.\n\n**Width x height:** 1344x768 (16:9), 1024x768 (4:3), 768x768 (1:1), 768x1024 (3:4), 768x1344 (9:16).\n\nEach reference video/audio clip must be 2\u201315 s. Total reference-video duration <=15 s; total standalone-audio duration <=15 s.\n\nRequires the expanded Video References node and the audio-preserving video output fix. See the extension README for setup and validation status."
|
|
],
|
|
"color": "#432",
|
|
"bgcolor": "#000"
|
|
},
|
|
{
|
|
"id": 11,
|
|
"type": "MarkdownNote",
|
|
"pos": [
|
|
790,
|
|
940
|
|
],
|
|
"size": [
|
|
480,
|
|
455
|
|
],
|
|
"flags": {},
|
|
"order": 10,
|
|
"mode": 0,
|
|
"inputs": [],
|
|
"outputs": [],
|
|
"title": "Optional Turbo \u2014 same workflow",
|
|
"properties": {},
|
|
"widgets_values": [
|
|
"## Turbo Ref2VA\nBase mode: leave LoRA disconnected; use 50 steps, video flow shift 12, audio flow shift 3.\n\nFor the 4-step v0.1 Ref2VA Turbo adapter:\n1. Start a Ref2VA-only server with the Diffusers adapter loaded (see README).\n2. Set LoRA local_path to its path on the server, then connect LoRA to Generate Video.\n3. Set Sampling num_inference_steps to **5**; keep shifts at **12 / 3**, scale **1**.\n\nvLLM-Omni counts sigma points: 5 points give 4 denoiser evaluations. Use minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors, not the _comfyui_ export.\n\nDisconnect LoRA and restore 50 steps to return to base mode. FastH3 is a separate T2VA deployment, not this option.\n\nAdapted from the official ComfyUI MiniMax-H3 R2V workflow: https://github.com/Comfy-Org/workflow_templates/blob/main/templates/video_minimax_h3_r2v.json"
|
|
],
|
|
"color": "#432",
|
|
"bgcolor": "#000"
|
|
}
|
|
],
|
|
"links": [
|
|
[
|
|
1,
|
|
1,
|
|
0,
|
|
4,
|
|
0,
|
|
"IMAGE"
|
|
],
|
|
[
|
|
2,
|
|
4,
|
|
0,
|
|
8,
|
|
1,
|
|
"VIDEO_REFERENCES"
|
|
],
|
|
[
|
|
3,
|
|
5,
|
|
0,
|
|
8,
|
|
2,
|
|
"SAMPLING_PARAMS"
|
|
],
|
|
[
|
|
4,
|
|
6,
|
|
0,
|
|
8,
|
|
4,
|
|
"VIDEO_PARAMS"
|
|
],
|
|
[
|
|
5,
|
|
8,
|
|
0,
|
|
9,
|
|
0,
|
|
"VIDEO"
|
|
]
|
|
],
|
|
"groups": [],
|
|
"config": {},
|
|
"extra": {
|
|
"workflowRendererVersion": "LG",
|
|
"ds": {
|
|
"scale": 0.85,
|
|
"offset": [
|
|
100,
|
|
100
|
|
]
|
|
}
|
|
},
|
|
"version": 0.4
|
|
}
|