Files
smthemex-ComfyUI_InteractAv…/example_workflows/InteractAvatar.json
T
2026-02-05 12:39:00 +08:00

1375 lines
24 KiB
JSON

{
"id": "70258d66-2650-4bb1-b607-75e03c1f7f28",
"revision": 0,
"last_node_id": 33,
"last_link_id": 51,
"nodes": [
{
"id": 4,
"type": "VAEDecode",
"pos": [
21469.293939506748,
-611.0624712987261
],
"size": [
140,
46
],
"flags": {},
"order": 21,
"mode": 2,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 15
},
{
"name": "vae",
"type": "VAE",
"link": 4
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
5
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 6,
"type": "CreateVideo",
"pos": [
21653.483940544334,
-624.0641184307909
],
"size": [
270,
78
],
"flags": {},
"order": 23,
"mode": 2,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 5
},
{
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": null
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
6
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
30
]
},
{
"id": 7,
"type": "SaveVideo",
"pos": [
21524.550939818026,
-375.9493523272225
],
"size": [
270,
106
],
"flags": {},
"order": 25,
"mode": 2,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 6
}
],
"outputs": [],
"properties": {},
"widgets_values": [
"video/ComfyUI",
"auto",
"auto"
]
},
{
"id": 1,
"type": "InteractAvatar_SM_Model",
"pos": [
20655.956740953232,
-826.2880845675337
],
"size": [
278.662109375,
178
],
"flags": {},
"order": 0,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "model",
"type": "MODEL",
"links": [
13
]
}
],
"properties": {
"Node name for S&R": "InteractAvatar_SM_Model"
},
"widgets_values": [
"interact-avatar.safetensors",
"interact-avatar.safetensors",
"none",
"none",
1
]
},
{
"id": 13,
"type": "InteractAvatar_SM_Sampler",
"pos": [
21111.045470959252,
-616.7680274485149
],
"size": [
281.2984375,
318
],
"flags": {},
"order": 19,
"mode": 2,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 13
},
{
"name": "data_dict",
"type": "CONDITIONING",
"link": 18
}
],
"outputs": [
{
"name": "Latent",
"type": "LATENT",
"links": [
15
]
}
],
"properties": {
"Node name for S&R": "InteractAvatar_SM_Sampler"
},
"widgets_values": [
20,
551863485,
"randomize",
5,
5,
5,
0,
25,
1000,
false
]
},
{
"id": 14,
"type": "Note",
"pos": [
21073.49649099832,
-891.9647068066879
],
"size": [
390.28170729224803,
246.35694222626103
],
"flags": {},
"order": 1,
"mode": 2,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"mode=a2mv\ntransformer_path=interact-avatar\ntest_data_path=InterDemo/TIA2MV/demo_tia2mv.json\nback_append_frame=1\nframe_num=101\n\n# for pose dirven with audio\nmode=ap2v\ntransformer_path=interact-avatar\ntest_data_path=InterDemo/TIAP2V/demo_ap2v.json\nback_append_frame=1\nframe_num=133\n\nfor song with action\n# mode=a2mv\n# transformer_path=interact-avatar-long\n# test_data_path=demo_song_action.json\n# back_append_frame=2\n# frame_num=1000"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 8,
"type": "CLIPLoader",
"pos": [
20214.19076831883,
-812.6313406695036
],
"size": [
270,
106
],
"flags": {},
"order": 2,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
16
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"wan",
"default"
]
},
{
"id": 5,
"type": "VAELoader",
"pos": [
20224.42956543533,
-644.7584067826607
],
"size": [
270,
58
],
"flags": {},
"order": 3,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
4,
17
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"Wan2.2_VAE.pth"
]
},
{
"id": 9,
"type": "LoadImage",
"pos": [
19817.499679613604,
-756.4208862352102
],
"size": [
270,
314
],
"flags": {},
"order": 4,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
19
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"001.jpeg",
"image"
]
},
{
"id": 10,
"type": "LoadImage",
"pos": [
19839.92752091642,
-392.48311359683214
],
"size": [
270,
314
],
"flags": {},
"order": 5,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
20
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"001_obj_handbag.png",
"image"
]
},
{
"id": 15,
"type": "InteractAvatar_SM_Predata",
"pos": [
20589.88000915876,
-520.7428687917542
],
"size": [
439.0049413961933,
585.8462358678404
],
"flags": {},
"order": 16,
"mode": 2,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 16
},
{
"name": "vae",
"type": "VAE",
"link": 17
},
{
"name": "images",
"type": "IMAGE",
"link": 19
},
{
"name": "pose_images",
"type": "IMAGE",
"link": 20
},
{
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 24
},
{
"name": "object_images",
"shape": 7,
"type": "IMAGE",
"link": 22
},
{
"name": "object_mask",
"shape": 7,
"type": "MASK",
"link": 23
}
],
"outputs": [
{
"name": "data_dict",
"type": "CONDITIONING",
"links": [
18
]
}
],
"properties": {
"Node name for S&R": "InteractAvatar_SM_Predata"
},
"widgets_values": [
768,
"512",
"The man picks up his handbag.",
"bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards",
"(Left hand holds the handle of the handbag)(Right hand hangs naturally)",
101,
"a2mv",
1,
"",
""
]
},
{
"id": 12,
"type": "LoadAudio",
"pos": [
20213.269818313645,
-369.5568758206247
],
"size": [
270,
136
],
"flags": {},
"order": 6,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
24
]
}
],
"properties": {
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"01-seedtts-01_promptvn.wav",
null,
null
]
},
{
"id": 16,
"type": "LoadImage",
"pos": [
20189.94934337644,
-137.90936898810804
],
"size": [
270,
314
],
"flags": {},
"order": 7,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
22
]
},
{
"name": "MASK",
"type": "MASK",
"links": [
23
]
}
],
"properties": {
"Node name for S&R": "LoadImage",
"image": "clipspace/clipspace-painted-masked-1770205344996.png [input]"
},
"widgets_values": [
"clipspace/clipspace-painted-masked-1770205344996.png [input]",
"image"
]
},
{
"id": 22,
"type": "Note",
"pos": [
23356.144432636724,
-881.6479805868449
],
"size": [
390.28170729224803,
246.35694222626103
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"mode=a2mv\ntransformer_path=interact-avatar\ntest_data_path=InterDemo/TIA2MV/demo_tia2mv.json\nback_append_frame=1\nframe_num=101\n\n# for pose dirven with audio\nmode=ap2v\ntransformer_path=interact-avatar\ntest_data_path=InterDemo/TIAP2V/demo_ap2v.json\nback_append_frame=1\nframe_num=133\n\nfor song with action\n# mode=a2mv\n# transformer_path=interact-avatar-long\n# test_data_path=demo_song_action.json\n# back_append_frame=2\n# frame_num=1000"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 17,
"type": "VAEDecode",
"pos": [
23722.253703389688,
-631.077504367396
],
"size": [
140,
46
],
"flags": {},
"order": 24,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 25
},
{
"name": "vae",
"type": "VAE",
"link": 26
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
27
]
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 30,
"type": "InteractAvatar_SM_Model",
"pos": [
22978.61090737092,
-788.1824536240806
],
"size": [
278.662109375,
154
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "model",
"type": "MODEL",
"links": [
38
]
}
],
"properties": {
"Node name for S&R": "InteractAvatar_SM_Model"
},
"widgets_values": [
"interact-avatar.safetensors",
"none",
"none",
1,
true
]
},
{
"id": 23,
"type": "CLIPLoader",
"pos": [
22571.92322214492,
-801.1227967958882
],
"size": [
270,
106
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
43
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"wan",
"default"
]
},
{
"id": 24,
"type": "VAELoader",
"pos": [
22582.16201926142,
-633.2498629090453
],
"size": [
270,
58
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"links": [
26,
44
]
}
],
"properties": {
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"Wan2.2_VAE.pth"
]
},
{
"id": 31,
"type": "SaveImage",
"pos": [
23358.789761969365,
-99.02376747958866
],
"size": [
270,
270
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 40
}
],
"outputs": [],
"properties": {},
"widgets_values": [
"ComfyUI"
]
},
{
"id": 32,
"type": "InvertMask",
"pos": [
22906.801289048886,
69.22168329705264
],
"size": [
140,
26
],
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "mask",
"type": "MASK",
"link": 41
}
],
"outputs": [
{
"name": "MASK",
"type": "MASK",
"links": [
50
]
}
],
"properties": {
"Node name for S&R": "InvertMask"
},
"widgets_values": []
},
{
"id": 25,
"type": "LoadImage",
"pos": [
22240.782104397193,
-694.856000903146
],
"size": [
270,
314.00000000000006
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
45
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"003.jpeg",
"image"
]
},
{
"id": 26,
"type": "LoadImage",
"pos": [
22246.524498547184,
-338.06913418740334
],
"size": [
270,
314.0000000000001
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
47
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"003_obj_coffee.png",
"image"
]
},
{
"id": 29,
"type": "LoadImage",
"pos": [
22582.48287269269,
-271.44503357861754
],
"size": [
270,
314.0000000000001
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
40,
49
]
},
{
"name": "MASK",
"type": "MASK",
"links": [
41
]
}
],
"properties": {
"Node name for S&R": "LoadImage",
"image": "clipspace/clipspace-painted-masked-1770263662180.png [input]"
},
"widgets_values": [
"clipspace/clipspace-painted-masked-1770263662180.png [input]",
"image"
]
},
{
"id": 33,
"type": "InteractAvatar_SM_Predata",
"pos": [
22907.492315667885,
-559.0905265728924
],
"size": [
417.9086048651043,
534.3207101901768
],
"flags": {},
"order": 20,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 43
},
{
"name": "vae",
"type": "VAE",
"link": 44
},
{
"name": "images",
"type": "IMAGE",
"link": 45
},
{
"name": "pose_images",
"type": "IMAGE",
"link": 47
},
{
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 46
},
{
"name": "object_images",
"shape": 7,
"type": "IMAGE",
"link": 49
},
{
"name": "object_mask",
"shape": 7,
"type": "MASK",
"link": 50
}
],
"outputs": [
{
"name": "data_dict",
"type": "CONDITIONING",
"links": [
51
]
}
],
"properties": {
"Node name for S&R": "InteractAvatar_SM_Predata"
},
"widgets_values": [
512,
"The woman took the coffee from the table and drank it.",
"bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards",
"(Moved her right hand away from the coffee cup)(Picked up the coffee cup with her left hand)(Brought the cup close to her mouth)(Took a sip)",
101,
"a2mv",
1,
"",
"",
""
]
},
{
"id": 28,
"type": "LoadAudio",
"pos": [
22564.72897739852,
-467.13215138503244
],
"size": [
270,
136
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
39,
46
]
}
],
"properties": {
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"02-seedtts-02_promptvn.wav",
null,
null
]
},
{
"id": 21,
"type": "InteractAvatar_SM_Sampler",
"pos": [
23343.637071139194,
-502.7631653504566
],
"size": [
281.2984375,
318
],
"flags": {},
"order": 22,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 38
},
{
"name": "data_dict",
"type": "CONDITIONING",
"link": 51
}
],
"outputs": [
{
"name": "Latent",
"type": "LATENT",
"links": [
25
]
}
],
"properties": {
"Node name for S&R": "InteractAvatar_SM_Sampler"
},
"widgets_values": [
20,
1714210267,
"randomize",
5,
5,
7.5,
800,
25,
true,
false
]
},
{
"id": 18,
"type": "CreateVideo",
"pos": [
23633.536530795816,
-481.4985380777255
],
"size": [
270,
78
],
"flags": {},
"order": 26,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 27
},
{
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 39
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
28
]
}
],
"properties": {
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
25
]
},
{
"id": 19,
"type": "SaveVideo",
"pos": [
23885.79947024992,
-672.7530469258098
],
"size": [
478,
815
],
"flags": {},
"order": 27,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 28
}
],
"outputs": [],
"properties": {},
"widgets_values": [
"video/ComfyUI",
"auto",
"auto"
]
}
],
"links": [
[
4,
5,
0,
4,
1,
"VAE"
],
[
5,
4,
0,
6,
0,
"IMAGE"
],
[
6,
6,
0,
7,
0,
"VIDEO"
],
[
13,
1,
0,
13,
0,
"MODEL"
],
[
15,
13,
0,
4,
0,
"LATENT"
],
[
16,
8,
0,
15,
0,
"CLIP"
],
[
17,
5,
0,
15,
1,
"VAE"
],
[
18,
15,
0,
13,
1,
"CONDITIONING"
],
[
19,
9,
0,
15,
2,
"IMAGE"
],
[
20,
10,
0,
15,
3,
"IMAGE"
],
[
22,
16,
0,
15,
5,
"IMAGE"
],
[
23,
16,
1,
15,
6,
"MASK"
],
[
24,
12,
0,
15,
4,
"AUDIO"
],
[
25,
21,
0,
17,
0,
"LATENT"
],
[
26,
24,
0,
17,
1,
"VAE"
],
[
27,
17,
0,
18,
0,
"IMAGE"
],
[
28,
18,
0,
19,
0,
"VIDEO"
],
[
38,
30,
0,
21,
0,
"MODEL"
],
[
39,
28,
0,
18,
1,
"AUDIO"
],
[
40,
29,
0,
31,
0,
"IMAGE"
],
[
41,
29,
1,
32,
0,
"MASK"
],
[
43,
23,
0,
33,
0,
"CLIP"
],
[
44,
24,
0,
33,
1,
"VAE"
],
[
45,
25,
0,
33,
2,
"IMAGE"
],
[
46,
28,
0,
33,
4,
"AUDIO"
],
[
47,
26,
0,
33,
3,
"IMAGE"
],
[
49,
29,
0,
33,
5,
"IMAGE"
],
[
50,
32,
0,
33,
6,
"MASK"
],
[
51,
33,
0,
21,
1,
"CONDITIONING"
]
],
"groups": [
{
"id": 1,
"title": "Group",
"bounding": [
19720.47631993595,
-966.4716476151324,
2291.6857937761633,
1151.0443112641383
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 2,
"title": "Group",
"bounding": [
22078.208773762042,
-954.963103741517,
2291.6857937761633,
1151.0443112641383
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
}
],
"config": {},
"extra": {
"workflowRendererVersion": "LG",
"ds": {
"scale": 0.6934334949442076,
"offset": [
-21975.66153358101,
1046.1905376736581
]
},
"frontendVersion": "1.37.11",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}