diff --git a/examples/rvc-model-trainer.json b/examples/rvc-model-trainer.json index 51a0988..bbf340e 100644 --- a/examples/rvc-model-trainer.json +++ b/examples/rvc-model-trainer.json @@ -1,13 +1,13 @@ { - "last_node_id": 17, - "last_link_id": 30, + "last_node_id": 27, + "last_link_id": 57, "nodes": [ { "id": 3, "type": "LoadPitchExtractionParams", "pos": [ - -387, - 130 + -962.0740292968748, + 39.00402600097682 ], "size": { "0": 315, @@ -44,8 +44,8 @@ "id": 5, "type": "LoadHubertModel", "pos": [ - -403, - 402 + -989.0740292968749, + 321.0040260009767 ], "size": { "0": 315, @@ -76,36 +76,36 @@ "id": 6, "type": "RVCNode", "pos": [ - 945.4000799560547, - -349.9999832153321 + -388, + -373 + ], + "size": [ + 418.1999816894531, + 166 ], - "size": { - "0": 418.1999816894531, - "1": 166 - }, "flags": {}, - "order": 6, + "order": 10, "mode": 0, "inputs": [ { "name": "audio", "type": "AUDIO,VHS_AUDIO", - "link": 12 + "link": 56 }, { "name": "model", "type": "RVC_MODEL", - "link": 23 + "link": 50 }, { "name": "hubert_model", "type": "HUBERT_MODEL", - "link": 24 + "link": 51 }, { "name": "pitch_extraction_params", "type": "PITCH_EXTRACTION", - "link": 25 + "link": 52 } ], "outputs": [ @@ -125,15 +125,35 @@ "widgets_values": [ 0, "flac", - true + true, + { + "hidden": false, + "paused": false, + "params": {} + }, + { + "hidden": false, + "paused": false, + "params": {} + }, + { + "hidden": false, + "paused": false, + "params": {} + }, + { + "hidden": false, + "paused": false, + "params": {} + } ] }, { "id": 9, "type": "RVC-Studio.LoadAudio", "pos": [ - 315.40007995605475, - -363.99998321533207 + -1025.233936645508, + -375.3608336547855 ], "size": { "0": 210, @@ -161,15 +181,16 @@ { "name": "audio", "type": "AUDIO", - "links": null, - "shape": 3 + "links": [], + "shape": 3, + "slot_index": 2 } ], "properties": { "Node name for S&R": "RVC-Studio.LoadAudio" }, "widgets_values": [ - "idol-tv.flac", + "You are my sunshine.flac", "None", "image" ] @@ -178,15 +199,15 @@ "id": 10, "type": "UVR5Node", "pos": [ - 573.4000799560546, - -355.9999832153321 + -769, + -364 ], "size": { "0": 315, "1": 150 }, "flags": {}, - "order": 4, + "order": 5, "mode": 0, "inputs": [ { @@ -200,7 +221,8 @@ "name": "primary_stem", "type": "VHS_AUDIO", "links": [ - 12 + 56, + 57 ], "slot_index": 0, "shape": 3 @@ -229,15 +251,15 @@ "id": 11, "type": "MergeAudioNode", "pos": [ - 1431.4000799560547, - -346.9999832153321 + 76.3659833984373, + -363.3608504394535 + ], + "size": [ + 315, + 166 ], - "size": { - "0": 315, - "1": 166 - }, "flags": {}, - "order": 7, + "order": 11, "mode": 0, "inputs": [ { @@ -283,28 +305,155 @@ "widgets_values": [ "None", "median", - true + true, + { + "hidden": false, + "paused": false, + "params": {} + }, + { + "hidden": false, + "paused": false, + "params": {} + }, + { + "hidden": false, + "paused": false, + "params": {} + }, + { + "hidden": false, + "paused": false, + "params": {} + } ] }, { - "id": 15, + "id": 17, + "type": "RVCProcessDatasetNode", + "pos": [ + -594.440406835937, + 51.19102186035135 + ], + "size": { + "0": 337.6000061035156, + "1": 290 + }, + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "hubert_model", + "type": "HUBERT_MODEL", + "link": 28 + }, + { + "name": "pitch_extraction_params", + "type": "PITCH_EXTRACTION", + "link": 29 + }, + { + "name": "audio_processor", + "type": "AUDIO_PROCESSOR", + "link": 53 + } + ], + "outputs": [ + { + "name": "rvc_dataset_pipe", + "type": "RVC_DATASET_PIPE", + "links": [ + 41 + ], + "slot_index": 0, + "shape": 3 + } + ], + "properties": { + "Node name for S&R": "RVCProcessDatasetNode" + }, + "widgets_values": [ + "Sayano-pretrain", + "Sayano.zip", + "40k", + 4, + 3, + 0.5, + 0.99, + 0.01, + "image" + ] + }, + { + "id": 19, + "type": "RVCTrainParamsNode", + "pos": [ + -578.8380483398437, + 386.9360217895509 + ], + "size": { + "0": 315, + "1": 394 + }, + "flags": {}, + "order": 3, + "mode": 0, + "outputs": [ + { + "name": "rvc_training_params", + "type": "RVC_TRAINING_PARAMS", + "links": [ + 42 + ], + "shape": 3 + } + ], + "properties": { + "Node name for S&R": "RVCTrainParamsNode" + }, + "widgets_values": [ + 6, + 1, + 45, + 1, + 2, + 1, + 1, + 1, + 0, + 45, + true, + true, + false, + true, + 0.0001 + ] + }, + { + "id": 21, "type": "RVCTrainModelNode", "pos": [ - 374, - 118 + -215.44040683593724, + 46.191021860351334 ], "size": { "0": 506.4000244140625, - "1": 382 + "1": 430 }, "flags": {}, - "order": 5, + "order": 9, "mode": 0, "inputs": [ { "name": "rvc_dataset_pipe", "type": "RVC_DATASET_PIPE", - "link": 30 + "link": 41 + }, + { + "name": "rvc_training_params", + "type": "RVC_TRAINING_PARAMS", + "link": 42 } ], "outputs": [ @@ -312,7 +461,7 @@ "name": "model", "type": "RVC_MODEL", "links": [ - 23 + 50 ], "slot_index": 0, "shape": 3 @@ -327,7 +476,7 @@ "name": "hubert_model", "type": "HUBERT_MODEL", "links": [ - 24 + 51 ], "slot_index": 2, "shape": 3 @@ -336,7 +485,7 @@ "name": "pitch_extraction_params", "type": "PITCH_EXTRACTION", "links": [ - 25 + 52 ], "slot_index": 3, "shape": 3 @@ -347,70 +496,133 @@ }, "widgets_values": [ "0", - 5, - 100, + 200, 10, - "pretrained_v2/G_DMR-V1-32k-f0.pth", - "pretrained_v2/D_DMR-V1-32k-f0.pth", + "pretrained_v2/f0G40k.pth", + "pretrained_v2/f0D40k.pth", + true, true, - false, false, true, true, - true + true, + 30, + 1, + 1 ] }, { - "id": 17, - "type": "RVCProcessDatasetNode", + "id": 25, + "type": "ProcessAudioNode", "pos": [ - -8, - 176 + -961.8380483398437, + 427.9360217895509 ], "size": { - "0": 337.6000061035156, - "1": 270 + "0": 315, + "1": 290 }, "flags": {}, - "order": 3, + "order": 6, "mode": 0, "inputs": [ { - "name": "hubert_model", - "type": "HUBERT_MODEL", - "link": 28 - }, - { - "name": "pitch_extraction_params", - "type": "PITCH_EXTRACTION", - "link": 29 + "name": "audio", + "type": "AUDIO,VHS_AUDIO", + "link": 57 } ], "outputs": [ { - "name": "rvc_dataset_pipe", - "type": "RVC_DATASET_PIPE", + "name": "audio_processor", + "type": "AUDIO_PROCESSOR", "links": [ - 30 + 53 + ], + "shape": 3 + }, + { + "name": "vhs_audio", + "type": "VHS_AUDIO", + "links": null, + "shape": 3, + "slot_index": 1 + }, + { + "name": "audio", + "type": "AUDIO", + "links": [ + 55 ], "shape": 3, - "slot_index": 0 + "slot_index": 2 } ], "properties": { - "Node name for S&R": "RVCProcessDatasetNode" + "Node name for S&R": "ProcessAudioNode" }, "widgets_values": [ - "Comfy-Mae", - "Mae.zip", - "32k", - 12, - 3, - 0.5, - 0.9500000000000001, - 0.01, - "image" + true, + true, + true, + 4000, + 2, + "median", + 5, + -50, + -1 ] + }, + { + "id": 26, + "type": "PreviewAudio", + "pos": [ + -133.79990234374995, + 545.6000030517579 + ], + "size": { + "0": 315, + "1": 76.0000228881836 + }, + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 55 + } + ], + "properties": { + "Node name for S&R": "PreviewAudio" + }, + "widgets_values": [ + null + ] + }, + { + "id": 27, + "type": "Note", + "pos": [ + -989, + -85 + ], + "size": { + "0": 210, + "1": 58 + }, + "flags": {}, + "order": 4, + "mode": 0, + "properties": { + "text": "" + }, + "widgets_values": [ + "audio processor is experimental and can be skipped" + ], + "color": "#432", + "bgcolor": "#653" } ], "links": [ @@ -422,14 +634,6 @@ 0, "AUDIO,VHS_AUDIO" ], - [ - 12, - 10, - 0, - 6, - 0, - "AUDIO,VHS_AUDIO" - ], [ 13, 6, @@ -446,30 +650,6 @@ 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, @@ -487,22 +667,86 @@ "PITCH_EXTRACTION" ], [ - 30, + 41, 17, 0, - 15, + 21, 0, "RVC_DATASET_PIPE" + ], + [ + 42, + 19, + 0, + 21, + 1, + "RVC_TRAINING_PARAMS" + ], + [ + 50, + 21, + 0, + 6, + 1, + "RVC_MODEL" + ], + [ + 51, + 21, + 2, + 6, + 2, + "HUBERT_MODEL" + ], + [ + 52, + 21, + 3, + 6, + 3, + "PITCH_EXTRACTION" + ], + [ + 53, + 25, + 0, + 17, + 2, + "AUDIO_PROCESSOR" + ], + [ + 55, + 25, + 2, + 26, + 0, + "AUDIO" + ], + [ + 56, + 10, + 0, + 6, + 0, + "AUDIO,VHS_AUDIO" + ], + [ + 57, + 10, + 0, + 25, + 0, + "AUDIO,VHS_AUDIO" ] ], "groups": [ { "title": "Model Trainer", "bounding": [ - -413, - 45, - 1303, - 466 + -999, + -35, + 1300, + 826 ], "color": "#b06634", "font_size": 24 @@ -510,8 +754,8 @@ { "title": "Basic Voice Changer", "bounding": [ - 305, - -438, + -1036, + -450, 1451, 267 ], @@ -522,10 +766,10 @@ "config": {}, "extra": { "ds": { - "scale": 0.6830134553650705, + "scale": 1.2100000000000002, "offset": [ - 544.5635228085466, - 563.3345057885277 + 935.0775202588511, + 160.03046112675403 ] } },