Files
SayanoAI-Comfy-RVC/examples/complete-ai-voice-changer.json
T
2024-06-11 22:53:19 -04:00

1434 lines
24 KiB
JSON

{
"last_node_id": 54,
"last_link_id": 168,
"nodes": [
{
"id": 37,
"type": "RVCNode",
"pos": [
1300,
-248
],
"size": [
309.34271240234375,
166
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 135
},
{
"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
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "RVCNode"
},
"widgets_values": [
0,
"flac",
true,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 6,
"type": "LoadPitchExtractionParams",
"pos": [
1297,
-467
],
"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": 33,
"type": "MergeAudioNode",
"pos": [
1702,
-801
],
"size": [
315,
166
],
"flags": {},
"order": 18,
"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": [
63
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"median",
false,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 39,
"type": "PreviewAudio",
"pos": [
2056,
-794
],
"size": [
315,
150
],
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 63
},
{
"name": "filename",
"type": "STRING",
"link": 64,
"widget": {
"name": "filename"
},
"slot_index": 1
}
],
"outputs": [
{
"name": "output_path",
"type": "STRING",
"links": null,
"shape": 3
},
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "PreviewAudio"
},
"widgets_values": [
"test",
"flac",
2,
true,
true,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 44,
"type": "UVR5Node",
"pos": [
-543,
-582
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 163
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
97
],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/UVR-BVE-4B_SN-44100-1.pth",
true,
10,
"flac"
]
},
{
"id": 36,
"type": "MergeAudioNode",
"pos": [
527,
-795
],
"size": [
315,
166
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 167
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 156
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": 108
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
54
],
"shape": 3,
"slot_index": 0
}
],
"title": "🌺Merge Instrumental",
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"median",
true,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 47,
"type": "UVR5Node",
"pos": [
180,
-353
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 106
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
141
],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
108
],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/HP5-vocals+instrumentals.pth",
true,
10,
"flac"
]
},
{
"id": 43,
"type": "MergeAudioNode",
"pos": [
-209,
-583
],
"size": [
315,
166
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 153
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 97
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": null
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
98,
99,
106
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"median",
true,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 11,
"type": "UVR5Node",
"pos": [
-208,
-796
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 162
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
153
],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/UVR-DeEcho-DeReverb.pth",
10,
10,
"flac"
]
},
{
"id": 50,
"type": "MergeAudioNode",
"pos": [
531,
-478
],
"size": [
315,
166
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 166
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 157
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": 141
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
142
],
"shape": 3,
"slot_index": 0
}
],
"title": "🌺Merge Vocals",
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"min",
true,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 46,
"type": "MergeAudioNode",
"pos": [
1296,
-735
],
"size": [
315,
166
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "VHS_AUDIO",
"link": 152
},
{
"name": "audio2",
"type": "VHS_AUDIO",
"link": 151
},
{
"name": "audio3_opt",
"type": "VHS_AUDIO",
"link": null,
"slot_index": 2
},
{
"name": "audio4_opt",
"type": "VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
135
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"median",
true,
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
},
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 17,
"type": "UVR5Node",
"pos": [
950,
-581
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 148
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
152
],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/5_HP-Karaoke-UVR.pth",
10,
10,
"flac"
]
},
{
"id": 40,
"type": "UVR5Node",
"pos": [
955,
-370
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 149
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
151
],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/6_HP-Karaoke-UVR.pth",
true,
10,
"flac"
]
},
{
"id": 45,
"type": "UVR5Node",
"pos": [
955,
-794
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 142
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
148,
149
],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/UVR-DeEcho-DeReverb.pth",
true,
10,
"flac"
]
},
{
"id": 4,
"type": "LoadRVCModelNode",
"pos": [
956,
-118
],
"size": {
"0": 315,
"1": 102
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "model",
"type": "RVC_MODEL",
"links": [
57
],
"shape": 3
},
{
"name": "model_name",
"type": "STRING",
"links": [
66
],
"shape": 3,
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoadRVCModelNode"
},
"widgets_values": [
"RVC/Sayano.pth",
"RVC/.index/added_IVF1063_Flat_nprobe_1_Sayano_v2.index"
]
},
{
"id": 5,
"type": "LoadHubertModel",
"pos": [
1011,
-156
],
"size": {
"0": 315,
"1": 58
},
"flags": {
"collapsed": true
},
"order": 2,
"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": 14,
"type": "UVR5Node",
"pos": [
179,
-579
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 99
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
156
],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
157
],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/model_bs_roformer_ep_317_sdr_12.9755.ckpt",
10,
10,
"flac"
]
},
{
"id": 7,
"type": "UVR5Node",
"pos": [
173,
-800
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "VHS_AUDIO",
"link": 98
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
166
],
"shape": 3,
"slot_index": 0
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
167
],
"shape": 3,
"slot_index": 1
},
{
"name": "audio_passthrough",
"type": "VHS_AUDIO",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"karafan/MDX23C-8KFFT-InstVoc_HQ.ckpt",
10,
10,
"flac"
]
},
{
"id": 53,
"type": "LoadAudio",
"pos": [
-501,
-799
],
"size": [
210,
126
],
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "audio_name",
"type": "STRING",
"links": [
168
],
"shape": 3,
"slot_index": 0
},
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
162,
163
],
"shape": 3,
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"Monologue of Three.mp3",
"None",
"image",
{
"hidden": false,
"paused": false,
"params": {}
}
]
},
{
"id": 31,
"type": "JoinStrings",
"pos": [
1379,
-786
],
"size": {
"0": 315,
"1": 106
},
"flags": {
"collapsed": true
},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "string1",
"type": "STRING",
"link": 66,
"widget": {
"name": "string1"
}
},
{
"name": "string2",
"type": "STRING",
"link": 168,
"widget": {
"name": "string2"
}
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": [
64
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "JoinStrings"
},
"widgets_values": [
"",
"",
"\\"
]
}
],
"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"
],
[
63,
33,
0,
39,
0,
"VHS_AUDIO"
],
[
64,
31,
0,
39,
1,
"STRING"
],
[
66,
4,
1,
31,
0,
"STRING"
],
[
97,
44,
1,
43,
1,
"VHS_AUDIO"
],
[
98,
43,
0,
7,
0,
"VHS_AUDIO"
],
[
99,
43,
0,
14,
0,
"VHS_AUDIO"
],
[
106,
43,
0,
47,
0,
"VHS_AUDIO"
],
[
108,
47,
1,
36,
2,
"VHS_AUDIO"
],
[
135,
46,
0,
37,
0,
"VHS_AUDIO"
],
[
141,
47,
0,
50,
2,
"VHS_AUDIO"
],
[
142,
50,
0,
45,
0,
"VHS_AUDIO"
],
[
148,
45,
0,
17,
0,
"VHS_AUDIO"
],
[
149,
45,
0,
40,
0,
"VHS_AUDIO"
],
[
151,
40,
1,
46,
1,
"VHS_AUDIO"
],
[
152,
17,
1,
46,
0,
"VHS_AUDIO"
],
[
153,
11,
0,
43,
0,
"VHS_AUDIO"
],
[
156,
14,
0,
36,
1,
"VHS_AUDIO"
],
[
157,
14,
1,
50,
1,
"VHS_AUDIO"
],
[
162,
53,
1,
11,
0,
"VHS_AUDIO"
],
[
163,
53,
1,
44,
0,
"VHS_AUDIO"
],
[
166,
7,
0,
50,
0,
"VHS_AUDIO"
],
[
167,
7,
1,
36,
0,
"VHS_AUDIO"
],
[
168,
53,
0,
31,
1,
"STRING"
]
],
"groups": [
{
"title": "Preprocess",
"bounding": [
-557,
-873,
674,
471
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Ensemble Vocal Separation",
"bounding": [
163,
-874,
694,
701
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Postprocess",
"bounding": [
940,
-867,
694,
860
],
"color": "#3f789e",
"font_size": 24
},
{
"title": "Output Audio",
"bounding": [
1690,
-872,
698,
255
],
"color": "#3f789e",
"font_size": 24
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.9090909090909091,
"offset": [
-959.9219208282357,
981.1146284125558
]
}
},
"version": 0.4
}