Files
SayanoAI-Comfy-RVC/examples/advanced-ai-voice-changer.json
T
2024-08-24 00:08:47 -04:00

948 lines
16 KiB
JSON

{
"last_node_id": 46,
"last_link_id": 84,
"nodes": [
{
"id": 4,
"type": "LoadRVCModelNode",
"pos": [
628.0001464843749,
-110.00001220703123
],
"size": {
"0": 315,
"1": 102
},
"flags": {},
"order": 4,
"mode": 0,
"outputs": [
{
"name": "model",
"type": "RVC_MODEL",
"links": [
57
],
"shape": 3
},
{
"name": "model_name",
"type": "STRING",
"links": [
76
],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadRVCModelNode"
},
"widgets_values": [
"RVC/Sayano.pth",
"RVC/.index/Sayano_v2_40k.index"
]
},
{
"id": 5,
"type": "LoadHubertModel",
"pos": [
628.0001464843749,
35.99998779296875
],
"size": {
"0": 315,
"1": 58
},
"flags": {
"collapsed": false
},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "hubert_model",
"type": "HUBERT_MODEL",
"links": [
58
],
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadHubertModel"
},
"widgets_values": [
"content-vec-best.safetensors"
]
},
{
"id": 6,
"type": "LoadPitchExtractionParams",
"pos": [
266.0001464843749,
143.99998779296874
],
"size": {
"0": 315,
"1": 178
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "pitch_extraction_params",
"type": "PITCH_EXTRACTION",
"links": [
59
],
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadPitchExtractionParams"
},
"widgets_values": [
"rmvpe+",
false,
0.75,
0,
0.25,
0.25
]
},
{
"id": 31,
"type": "JoinStrings",
"pos": [
363,
-106
],
"size": {
"0": 315,
"1": 106
},
"flags": {
"collapsed": true
},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "string1",
"type": "STRING",
"link": 76,
"widget": {
"name": "string1"
}
},
{
"name": "string2",
"type": "STRING",
"link": 79,
"widget": {
"name": "string2"
}
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": [
84
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "JoinStrings"
},
"widgets_values": [
"",
"",
"\\"
]
},
{
"id": 33,
"type": "MergeAudioNode",
"pos": [
1154,
-367
],
"size": {
"0": 315,
"1": 166
},
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 54
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 60
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": null
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
81
],
"slot_index": 0,
"shape": 3
},
{
"name": "audio",
"type": "AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"mean",
true
]
},
{
"id": 35,
"type": "MergeAudioNode",
"pos": [
271,
-545
],
"size": {
"0": 315,
"1": 166
},
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 70
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 71
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": null
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
74
],
"slot_index": 0,
"shape": 3
},
{
"name": "audio",
"type": "AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"min",
true
]
},
{
"id": 36,
"type": "MergeAudioNode",
"pos": [
608,
-544
],
"size": {
"0": 315,
"1": 166
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 72
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 73
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": null
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
54
],
"slot_index": 0,
"shape": 3
},
{
"name": "audio",
"type": "AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"mean",
true
]
},
{
"id": 37,
"type": "RVCNode",
"pos": [
632.0001464843749,
138.99998779296877
],
"size": {
"0": 309.34271240234375,
"1": 166
},
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 78
},
{
"name": "model",
"type": "RVC_MODEL",
"link": 57
},
{
"name": "hubert_model",
"type": "HUBERT_MODEL",
"link": 58
},
{
"name": "pitch_extraction_params",
"type": "PITCH_EXTRACTION",
"link": 59
}
],
"outputs": [
{
"name": "VHS_AUDIO",
"type": "VHS_AUDIO",
"links": [
60
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "RVCNode"
},
"widgets_values": [
0,
"flac",
true
]
},
{
"id": 40,
"type": "UVR5Node",
"pos": [
-172,
-567
],
"size": {
"0": 315,
"1": 150
},
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 80
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
82,
83
],
"slot_index": 0,
"shape": 3
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/UVR-DeEcho-DeReverb.pth",
true,
10,
"flac"
]
},
{
"id": 41,
"type": "UVR5Node",
"pos": [
271,
-734
],
"size": {
"0": 315,
"1": 150
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 82
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
70
],
"slot_index": 0,
"shape": 3
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
72
],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/HP5-vocals+instrumentals.pth",
true,
10,
"flac"
]
},
{
"id": 42,
"type": "UVR5Node",
"pos": [
614,
-738
],
"size": {
"0": 315,
"1": 150
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 83
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
71
],
"slot_index": 0,
"shape": 3
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
73
],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"karafan/MDX23C-8KFFT-InstVoc_HQ.ckpt",
true,
10,
"flac"
]
},
{
"id": 43,
"type": "UVR5Node",
"pos": [
272.0001464843749,
-56.000012207031226
],
"size": {
"0": 315,
"1": 150
},
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 74
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [],
"slot_index": 0,
"shape": 3
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
78
],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/UVR-DeNoise.pth",
true,
10,
"flac"
]
},
{
"id": 44,
"type": "Note",
"pos": [
441,
-280
],
"size": {
"0": 428.5817565917969,
"1": 61.225948333740234
},
"flags": {},
"order": 2,
"mode": 0,
"properties": {
"text": ""
},
"widgets_values": [
"More advanced workflow that uses ensemble UVR techniques to split the vocals and apply post processing to the vocals."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 45,
"type": "RVC-Studio.LoadAudio",
"pos": [
-161,
-744
],
"size": {
"0": 295.5188293457031,
"1": 146
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "audio_name",
"type": "STRING",
"links": [
79
],
"slot_index": 0,
"shape": 3
},
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
80
],
"slot_index": 1,
"shape": 3
},
{
"name": "audio",
"type": "AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "RVC-Studio.LoadAudio"
},
"widgets_values": [
"idol-tv.flac",
"None",
"image"
]
},
{
"id": 46,
"type": "RVC-Studio.PreviewAudio",
"pos": [
1510,
-370
],
"size": {
"0": 315,
"1": 174
},
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 81
},
{
"name": "filename",
"type": "STRING",
"link": 84,
"widget": {
"name": "filename"
}
}
],
"outputs": [
{
"name": "output_path",
"type": "STRING",
"links": null,
"shape": 3
},
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
},
{
"name": "audio",
"type": "AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "RVC-Studio.PreviewAudio"
},
"widgets_values": [
"test",
"flac",
2,
true,
true
]
}
],
"links": [
[
54,
36,
0,
33,
0,
"VHS_AUDIO"
],
[
57,
4,
0,
37,
1,
"RVC_MODEL"
],
[
58,
5,
0,
37,
2,
"HUBERT_MODEL"
],
[
59,
6,
0,
37,
3,
"PITCH_EXTRACTION"
],
[
60,
37,
0,
33,
1,
"VHS_AUDIO"
],
[
70,
41,
0,
35,
0,
"VHS_AUDIO"
],
[
71,
42,
0,
35,
1,
"VHS_AUDIO"
],
[
72,
41,
1,
36,
0,
"VHS_AUDIO"
],
[
73,
42,
1,
36,
1,
"VHS_AUDIO"
],
[
74,
35,
0,
43,
0,
"VHS_AUDIO"
],
[
76,
4,
1,
31,
0,
"STRING"
],
[
78,
43,
1,
37,
0,
"VHS_AUDIO"
],
[
79,
45,
0,
31,
1,
"STRING"
],
[
80,
45,
1,
40,
0,
"VHS_AUDIO"
],
[
81,
33,
0,
46,
0,
"VHS_AUDIO"
],
[
82,
40,
0,
41,
0,
"VHS_AUDIO"
],
[
83,
40,
0,
42,
0,
"VHS_AUDIO"
],
[
84,
31,
0,
46,
1,
"STRING"
]
],
"groups": [
{
"title": "Preprocess",
"bounding": [
-182,
-813,
335,
406
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Ensemble Vocal Separation",
"bounding": [
259,
-810,
677,
472
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Postprocess",
"bounding": [
256,
-193,
712,
529
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Output Audio",
"bounding": [
1144,
-441,
698,
255
],
"color": "#3f789e",
"font_size": 24
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.7513148009015777,
"offset": [
-710.5738747513219,
614.3999323135652
]
}
},
"version": 0.4
}