Files
SayanoAI-Comfy-RVC/examples/rvc-model-trainer.json
T
2024-08-25 21:20:23 -04:00

533 lines
9.1 KiB
JSON

{
"last_node_id": 17,
"last_link_id": 30,
"nodes": [
{
"id": 3,
"type": "LoadPitchExtractionParams",
"pos": [
-387,
130
],
"size": {
"0": 315,
"1": 202
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "pitch_extraction_params",
"type": "PITCH_EXTRACTION",
"links": [
29
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadPitchExtractionParams"
},
"widgets_values": [
"rmvpe+",
false,
0.75,
0,
0.25,
0.25,
160
]
},
{
"id": 5,
"type": "LoadHubertModel",
"pos": [
-403,
402
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "hubert_model",
"type": "HUBERT_MODEL",
"links": [
28
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadHubertModel"
},
"widgets_values": [
"content-vec-best.safetensors"
]
},
{
"id": 6,
"type": "RVCNode",
"pos": [
945.4000799560547,
-349.9999832153321
],
"size": {
"0": 418.1999816894531,
"1": 166
},
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO,VHS_AUDIO",
"link": 12
},
{
"name": "model",
"type": "RVC_MODEL",
"link": 23
},
{
"name": "hubert_model",
"type": "HUBERT_MODEL",
"link": 24
},
{
"name": "pitch_extraction_params",
"type": "PITCH_EXTRACTION",
"link": 25
}
],
"outputs": [
{
"name": "VHS_AUDIO",
"type": "VHS_AUDIO",
"links": [
13
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "RVCNode"
},
"widgets_values": [
0,
"flac",
true
]
},
{
"id": 9,
"type": "RVC-Studio.LoadAudio",
"pos": [
315.40007995605475,
-363.99998321533207
],
"size": {
"0": 210,
"1": 146
},
"flags": {},
"order": 2,
"mode": 0,
"outputs": [
{
"name": "audio_name",
"type": "STRING",
"links": null,
"shape": 3
},
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": [
11
],
"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": 10,
"type": "UVR5Node",
"pos": [
573.4000799560546,
-355.9999832153321
],
"size": {
"0": 315,
"1": 150
},
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO,VHS_AUDIO",
"link": 11
}
],
"outputs": [
{
"name": "primary_stem",
"type": "VHS_AUDIO",
"links": [
12
],
"slot_index": 0,
"shape": 3
},
{
"name": "secondary_stem",
"type": "VHS_AUDIO",
"links": [
14
],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "UVR5Node"
},
"widgets_values": [
"UVR/HP5-vocals+instrumentals.pth",
true,
10,
"flac"
]
},
{
"id": 11,
"type": "MergeAudioNode",
"pos": [
1431.4000799560547,
-346.9999832153321
],
"size": {
"0": 315,
"1": 166
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "audio1",
"type": "AUDIO,VHS_AUDIO",
"link": 13
},
{
"name": "audio2",
"type": "AUDIO,VHS_AUDIO",
"link": 14
},
{
"name": "audio3_opt",
"type": "AUDIO,VHS_AUDIO",
"link": null
},
{
"name": "audio4_opt",
"type": "AUDIO,VHS_AUDIO",
"link": null
}
],
"outputs": [
{
"name": "vhs_audio",
"type": "VHS_AUDIO",
"links": null,
"slot_index": 0,
"shape": 3
},
{
"name": "audio",
"type": "AUDIO",
"links": [],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "MergeAudioNode"
},
"widgets_values": [
"None",
"median",
true
]
},
{
"id": 15,
"type": "RVCTrainModelNode",
"pos": [
374,
118
],
"size": {
"0": 506.4000244140625,
"1": 382
},
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "rvc_dataset_pipe",
"type": "RVC_DATASET_PIPE",
"link": 30
}
],
"outputs": [
{
"name": "model",
"type": "RVC_MODEL",
"links": [
23
],
"slot_index": 0,
"shape": 3
},
{
"name": "model_name",
"type": "STRING",
"links": null,
"shape": 3
},
{
"name": "hubert_model",
"type": "HUBERT_MODEL",
"links": [
24
],
"slot_index": 2,
"shape": 3
},
{
"name": "pitch_extraction_params",
"type": "PITCH_EXTRACTION",
"links": [
25
],
"slot_index": 3,
"shape": 3
}
],
"properties": {
"Node name for S&R": "RVCTrainModelNode"
},
"widgets_values": [
"0",
5,
100,
10,
"pretrained_v2/G_DMR-V1-32k-f0.pth",
"pretrained_v2/D_DMR-V1-32k-f0.pth",
true,
false,
false,
true,
true,
true
]
},
{
"id": 17,
"type": "RVCProcessDatasetNode",
"pos": [
-8,
176
],
"size": {
"0": 337.6000061035156,
"1": 270
},
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "hubert_model",
"type": "HUBERT_MODEL",
"link": 28
},
{
"name": "pitch_extraction_params",
"type": "PITCH_EXTRACTION",
"link": 29
}
],
"outputs": [
{
"name": "rvc_dataset_pipe",
"type": "RVC_DATASET_PIPE",
"links": [
30
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "RVCProcessDatasetNode"
},
"widgets_values": [
"Comfy-Mae",
"Mae.zip",
"32k",
12,
3,
0.5,
0.9500000000000001,
0.01,
"image"
]
}
],
"links": [
[
11,
9,
1,
10,
0,
"AUDIO,VHS_AUDIO"
],
[
12,
10,
0,
6,
0,
"AUDIO,VHS_AUDIO"
],
[
13,
6,
0,
11,
0,
"AUDIO,VHS_AUDIO"
],
[
14,
10,
1,
11,
1,
"AUDIO,VHS_AUDIO"
],
[
23,
15,
0,
6,
1,
"RVC_MODEL"
],
[
24,
15,
2,
6,
2,
"HUBERT_MODEL"
],
[
25,
15,
3,
6,
3,
"PITCH_EXTRACTION"
],
[
28,
5,
0,
17,
0,
"HUBERT_MODEL"
],
[
29,
3,
0,
17,
1,
"PITCH_EXTRACTION"
],
[
30,
17,
0,
15,
0,
"RVC_DATASET_PIPE"
]
],
"groups": [
{
"title": "Model Trainer",
"bounding": [
-413,
45,
1303,
466
],
"color": "#b06634",
"font_size": 24
},
{
"title": "Basic Voice Changer",
"bounding": [
305,
-438,
1451,
267
],
"color": "#3f789e",
"font_size": 24
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.6830134553650705,
"offset": [
544.5635228085466,
563.3345057885277
]
}
},
"version": 0.4
}