LTX-2.3-Foley-Workflow / foley-sliding-window.json
square-zero-labs's picture
Promote sliding window workflow fix
20f1418
Raw
History Blame Contribute Delete
27 kB
{
"last_node_id": 28,
"last_link_id": 47,
"nodes": [
{
"id": 1,
"type": "LoadVideo",
"pos": [
-1600,
-420
],
"size": [
320,
90
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": [
1
]
}
],
"properties": {
"Node name for S&R": "LoadVideo"
},
"widgets_values": [
"input.mp4"
]
},
{
"id": 2,
"type": "GetVideoComponents",
"pos": [
-1220,
-420
],
"size": [
220,
120
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 1
}
],
"outputs": [
{
"name": "images",
"type": "IMAGE",
"links": [
2,
7,
44
]
},
{
"name": "audio",
"type": "AUDIO",
"links": null
},
{
"name": "fps",
"type": "FLOAT",
"links": [
3,
4,
21,
45
]
},
{
"name": "bit_depth",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "GetVideoComponents"
},
"widgets_values": []
},
{
"id": 3,
"type": "CheckpointLoaderSimple",
"pos": [
-1600,
-160
],
"size": [
360,
110
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
10
]
},
{
"name": "CLIP",
"type": "CLIP",
"links": null
},
{
"name": "VAE",
"type": "VAE",
"links": [
19
]
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"ltx-2.3-22b-dev-fp8.safetensors"
]
},
{
"id": 4,
"type": "LTXVAudioVAELoader",
"pos": [
-1600,
0
],
"size": [
360,
80
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "Audio VAE",
"type": "VAE",
"links": [
20,
35
]
}
],
"properties": {
"Node name for S&R": "LTXVAudioVAELoader"
},
"widgets_values": [
"ltx-2.3-22b-dev-fp8.safetensors"
]
},
{
"id": 5,
"type": "LTXAVTextEncoderLoader",
"pos": [
-1600,
150
],
"size": [
360,
120
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
12,
13
]
}
],
"properties": {
"Node name for S&R": "LTXAVTextEncoderLoader"
},
"widgets_values": [
"gemma_3_12B_it_fp8_scaled.safetensors",
"ltx-2.3-22b-dev-fp8.safetensors",
"default"
]
},
{
"id": 6,
"type": "CLIPTextEncode",
"pos": [
-1180,
140
],
"size": [
420,
180
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 12
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
14
]
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"Two men are playing tennis. No speech is present. No music is present."
],
"title": "Positive Prompt"
},
{
"id": 7,
"type": "CLIPTextEncode",
"pos": [
-1180,
370
],
"size": [
420,
160
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 13
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
15
]
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"music, melody, song, singing, vocals, score, soundtrack, beat, rhythm bed, instrumental backing, tinny, thin, harsh, clipped, distorted, low bitrate"
],
"title": "Negative Prompt"
},
{
"id": 8,
"type": "LTXVConditioning",
"pos": [
-700,
300
],
"size": [
220,
90
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "positive",
"type": "CONDITIONING",
"link": 14
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 15
},
{
"name": "frame_rate",
"type": "FLOAT",
"link": 3
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
16
]
},
{
"name": "negative",
"type": "CONDITIONING",
"links": [
17
]
}
],
"properties": {
"Node name for S&R": "LTXVConditioning"
},
"widgets_values": [
25.0
]
},
{
"id": 9,
"type": "LTXFoleyWindowPlan",
"pos": [
-860,
-430
],
"size": [
320,
210
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 2
},
{
"name": "frame_rate",
"type": "FLOAT",
"link": 4
}
],
"outputs": [
{
"name": "window_plan",
"type": "FOLEY_WINDOW_PLAN",
"links": [
8,
43
]
},
{
"name": "window_count",
"type": "INT",
"links": [
6
]
},
{
"name": "manifest",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "LTXFoleyWindowPlan"
},
"widgets_values": [
25.0,
89,
1.0,
16
]
},
{
"id": 10,
"type": "LoraLoaderModelOnly",
"pos": [
-1180,
-160
],
"size": [
360,
90
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 10
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
11
]
}
],
"properties": {
"Node name for S&R": "LoraLoaderModelOnly"
},
"widgets_values": [
"ltx-2.3-foley-400-steps.safetensors",
1.0
]
},
{
"id": 11,
"type": "LTXFoleyForLoopOpen",
"pos": [
-500,
-430
],
"size": [
300,
170
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "remaining",
"type": "INT",
"link": 6
},
{
"name": "audio_accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"link": null,
"shape": 7
}
],
"outputs": [
{
"name": "flow_control",
"type": "FLOW_CONTROL",
"links": [
40
]
},
{
"name": "remaining",
"type": "INT",
"links": [
9
]
},
{
"name": "audio_accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"links": [
39
]
}
],
"properties": {
"Node name for S&R": "LTXFoleyForLoopOpen"
},
"widgets_values": []
},
{
"id": 12,
"type": "LTXFoleyWindowSelect",
"pos": [
-140,
-430
],
"size": [
320,
140
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 7
},
{
"name": "window_plan",
"type": "FOLEY_WINDOW_PLAN",
"link": 8
},
{
"name": "remaining",
"type": "INT",
"link": 9
}
],
"outputs": [
{
"name": "window_images",
"type": "IMAGE",
"links": [
18
]
},
{
"name": "window_info",
"type": "FOLEY_WINDOW",
"links": [
37
]
}
],
"properties": {
"Node name for S&R": "LTXFoleyWindowSelect"
},
"widgets_values": []
},
{
"id": 13,
"type": "LTXFoleyVideoToAudioLatent",
"pos": [
-140,
-220
],
"size": [
360,
340
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 18
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 16
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 17
},
{
"name": "video_vae",
"type": "VAE",
"link": 19
},
{
"name": "audio_vae",
"type": "VAE",
"link": 20
},
{
"name": "frame_rate",
"type": "FLOAT",
"link": 21
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
25
]
},
{
"name": "negative",
"type": "CONDITIONING",
"links": [
26
]
},
{
"name": "av_latent",
"type": "LATENT",
"links": [
22,
31,
32
]
},
{
"name": "preview_images",
"type": "IMAGE",
"links": null
},
{
"name": "frame_rate",
"type": "FLOAT",
"links": null
},
{
"name": "frames",
"type": "INT",
"links": null
}
],
"properties": {
"Node name for S&R": "LTXFoleyVideoToAudioLatent"
},
"widgets_values": [
25.0,
576,
576,
89
]
},
{
"id": 14,
"type": "ModelSamplingLTXV",
"pos": [
260,
-170
],
"size": [
260,
120
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 11
},
{
"name": "latent",
"type": "LATENT",
"link": 22
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
23
]
}
],
"properties": {
"Node name for S&R": "ModelSamplingLTXV"
},
"widgets_values": [
2.05,
0.95
]
},
{
"id": 15,
"type": "LTXVApplySTG",
"pos": [
560,
-160
],
"size": [
240,
80
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 23
}
],
"outputs": [
{
"name": "model",
"type": "MODEL",
"links": [
24
]
}
],
"properties": {
"Node name for S&R": "LTXVApplySTG"
},
"widgets_values": [
"14, 19"
]
},
{
"id": 16,
"type": "STGGuiderNode",
"pos": [
840,
-180
],
"size": [
240,
150
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 24
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 25
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 26
}
],
"outputs": [
{
"name": "GUIDER",
"type": "GUIDER",
"links": [
28
]
}
],
"properties": {
"Node name for S&R": "STGGuiderNode"
},
"widgets_values": [
4.0,
1.0,
0.7
]
},
{
"id": 17,
"type": "RandomNoise",
"pos": [
560,
-430
],
"size": [
240,
90
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "NOISE",
"type": "NOISE",
"links": [
27
]
}
],
"properties": {
"Node name for S&R": "RandomNoise"
},
"widgets_values": [
42,
"fixed"
]
},
{
"id": 18,
"type": "KSamplerSelect",
"pos": [
560,
-300
],
"size": [
240,
80
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAMPLER",
"type": "SAMPLER",
"links": [
29
]
}
],
"properties": {
"Node name for S&R": "KSamplerSelect"
},
"widgets_values": [
"euler_ancestral_cfg_pp"
]
},
{
"id": 19,
"type": "LTXVScheduler",
"pos": [
840,
20
],
"size": [
240,
160
],
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "latent",
"type": "LATENT",
"link": 32
}
],
"outputs": [
{
"name": "SIGMAS",
"type": "SIGMAS",
"links": [
30
]
}
],
"properties": {
"Node name for S&R": "LTXVScheduler"
},
"widgets_values": [
30,
2.05,
0.95,
true,
0.1
]
},
{
"id": 20,
"type": "SamplerCustomAdvanced",
"pos": [
1140,
-220
],
"size": [
230,
130
],
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "noise",
"type": "NOISE",
"link": 27
},
{
"name": "guider",
"type": "GUIDER",
"link": 28
},
{
"name": "sampler",
"type": "SAMPLER",
"link": 29
},
{
"name": "sigmas",
"type": "SIGMAS",
"link": 30
},
{
"name": "latent_image",
"type": "LATENT",
"link": 31
}
],
"outputs": [
{
"name": "output",
"type": "LATENT",
"links": [
33
]
},
{
"name": "denoised_output",
"type": "LATENT",
"links": null
}
],
"properties": {
"Node name for S&R": "SamplerCustomAdvanced"
},
"widgets_values": []
},
{
"id": 21,
"type": "LTXVSeparateAVLatent",
"pos": [
1420,
-220
],
"size": [
220,
80
],
"flags": {},
"order": 20,
"mode": 0,
"inputs": [
{
"name": "av_latent",
"type": "LATENT",
"link": 33
}
],
"outputs": [
{
"name": "video_latent",
"type": "LATENT",
"links": null
},
{
"name": "audio_latent",
"type": "LATENT",
"links": [
34
]
}
],
"properties": {
"Node name for S&R": "LTXVSeparateAVLatent"
},
"widgets_values": []
},
{
"id": 22,
"type": "LTXFoleyAudioVAEDecode",
"pos": [
1680,
-220
],
"size": [
240,
90
],
"flags": {},
"order": 21,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 34
},
{
"name": "audio_vae",
"type": "VAE",
"link": 35
}
],
"outputs": [
{
"name": "Audio",
"type": "AUDIO",
"links": [
36
]
}
],
"properties": {
"Node name for S&R": "LTXFoleyAudioVAEDecode"
},
"widgets_values": []
},
{
"id": 23,
"type": "LTXFoleyWindowAudioSave",
"pos": [
1980,
-260
],
"size": [
300,
150
],
"flags": {},
"order": 22,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 36
},
{
"name": "window_info",
"type": "FOLEY_WINDOW",
"link": 37
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": null
},
{
"name": "window_record",
"type": "FOLEY_WINDOW_RECORD",
"links": [
38
]
}
],
"properties": {
"Node name for S&R": "LTXFoleyWindowAudioSave"
},
"widgets_values": [
true,
"ltx_foley_window"
]
},
{
"id": 24,
"type": "LTXFoleyAudioAccumulator",
"pos": [
2320,
-300
],
"size": [
260,
120
],
"flags": {},
"order": 23,
"mode": 0,
"inputs": [
{
"name": "window_record",
"type": "FOLEY_WINDOW_RECORD",
"link": 38
},
{
"name": "accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"link": 39
}
],
"outputs": [
{
"name": "accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"links": [
41
]
}
],
"properties": {
"Node name for S&R": "LTXFoleyAudioAccumulator"
},
"widgets_values": []
},
{
"id": 25,
"type": "LTXFoleyForLoopClose",
"pos": [
2660,
-430
],
"size": [
260,
120
],
"flags": {},
"order": 24,
"mode": 0,
"inputs": [
{
"name": "flow_control",
"type": "FLOW_CONTROL",
"link": 40
},
{
"name": "audio_accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"link": 41,
"shape": 7
}
],
"outputs": [
{
"name": "audio_accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"links": [
42
]
}
],
"properties": {
"Node name for S&R": "LTXFoleyForLoopClose"
},
"widgets_values": []
},
{
"id": 26,
"type": "LTXFoleyAudioStitch",
"pos": [
3020,
-380
],
"size": [
300,
110
],
"flags": {},
"order": 25,
"mode": 0,
"inputs": [
{
"name": "accumulation",
"type": "FOLEY_AUDIO_ACCUM",
"link": 42
},
{
"name": "window_plan",
"type": "FOLEY_WINDOW_PLAN",
"link": 43
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
46
]
},
{
"name": "manifest",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "LTXFoleyAudioStitch"
},
"widgets_values": []
},
{
"id": 27,
"type": "CreateVideo",
"pos": [
3380,
-420
],
"size": [
260,
140
],
"flags": {},
"order": 26,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 44
},
{
"name": "fps",
"type": "FLOAT",
"link": 45
},
{
"name": "audio",
"type": "AUDIO",
"link": 46
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": [
47
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
25.0,
8
]
},
{
"id": 28,
"type": "SaveVideo",
"pos": [
3700,
-420
],
"size": [
260,
110
],
"flags": {},
"order": 27,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 47
}
],
"outputs": [
{
"name": "video",
"type": "VIDEO",
"links": null
}
],
"properties": {
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"ltx_foley_loop",
"auto",
"auto"
]
}
],
"links": [
[
1,
1,
0,
2,
0,
"VIDEO"
],
[
2,
2,
0,
9,
0,
"IMAGE"
],
[
3,
2,
2,
8,
2,
"FLOAT"
],
[
4,
2,
2,
9,
1,
"FLOAT"
],
[
6,
9,
1,
11,
0,
"INT"
],
[
7,
2,
0,
12,
0,
"IMAGE"
],
[
8,
9,
0,
12,
1,
"FOLEY_WINDOW_PLAN"
],
[
9,
11,
1,
12,
2,
"INT"
],
[
10,
3,
0,
10,
0,
"MODEL"
],
[
11,
10,
0,
14,
0,
"MODEL"
],
[
12,
5,
0,
6,
0,
"CLIP"
],
[
13,
5,
0,
7,
0,
"CLIP"
],
[
14,
6,
0,
8,
0,
"CONDITIONING"
],
[
15,
7,
0,
8,
1,
"CONDITIONING"
],
[
16,
8,
0,
13,
1,
"CONDITIONING"
],
[
17,
8,
1,
13,
2,
"CONDITIONING"
],
[
18,
12,
0,
13,
0,
"IMAGE"
],
[
19,
3,
2,
13,
3,
"VAE"
],
[
20,
4,
0,
13,
4,
"VAE"
],
[
21,
2,
2,
13,
5,
"FLOAT"
],
[
22,
13,
2,
14,
1,
"LATENT"
],
[
23,
14,
0,
15,
0,
"MODEL"
],
[
24,
15,
0,
16,
0,
"MODEL"
],
[
25,
13,
0,
16,
1,
"CONDITIONING"
],
[
26,
13,
1,
16,
2,
"CONDITIONING"
],
[
27,
17,
0,
20,
0,
"NOISE"
],
[
28,
16,
0,
20,
1,
"GUIDER"
],
[
29,
18,
0,
20,
2,
"SAMPLER"
],
[
30,
19,
0,
20,
3,
"SIGMAS"
],
[
31,
13,
2,
20,
4,
"LATENT"
],
[
32,
13,
2,
19,
0,
"LATENT"
],
[
33,
20,
0,
21,
0,
"LATENT"
],
[
34,
21,
1,
22,
0,
"LATENT"
],
[
35,
4,
0,
22,
1,
"VAE"
],
[
36,
22,
0,
23,
0,
"AUDIO"
],
[
37,
12,
1,
23,
1,
"FOLEY_WINDOW"
],
[
38,
23,
1,
24,
0,
"FOLEY_WINDOW_RECORD"
],
[
39,
11,
2,
24,
1,
"FOLEY_AUDIO_ACCUM"
],
[
40,
11,
0,
25,
0,
"FLOW_CONTROL"
],
[
41,
24,
0,
25,
1,
"FOLEY_AUDIO_ACCUM"
],
[
42,
25,
0,
26,
0,
"FOLEY_AUDIO_ACCUM"
],
[
43,
9,
0,
26,
1,
"FOLEY_WINDOW_PLAN"
],
[
44,
2,
0,
27,
0,
"IMAGE"
],
[
45,
2,
2,
27,
1,
"FLOAT"
],
[
46,
26,
0,
27,
2,
"AUDIO"
],
[
47,
27,
0,
28,
0,
"VIDEO"
]
],
"groups": [],
"config": {},
"extra": {},
"models": [
{
"name": "ltx-2.3-22b-dev-fp8.safetensors",
"url": "https://huggingface.co/Lightricks/LTX-2.3-fp8/resolve/main/ltx-2.3-22b-dev-fp8.safetensors",
"directory": "checkpoints"
},
{
"name": "gemma_3_12B_it_fp8_scaled.safetensors",
"url": "https://huggingface.co/Comfy-Org/ltx-2/resolve/main/split_files/text_encoders/gemma_3_12B_it_fp8_scaled.safetensors",
"directory": "text_encoders"
},
{
"name": "ltx-2.3-foley-400-steps.safetensors",
"url": "https://huggingface.co/FuzzPuppy/LTX-2.3-Foley-LoRA/resolve/main/ltx-2.3-foley-400-steps.safetensors",
"directory": "loras"
}
],
"version": 0.4
}