diff --git a/examples/advanced-ai-voice-changer.json b/examples/advanced-ai-voice-changer.json index 2b9a6bf..657bbe0 100644 --- a/examples/advanced-ai-voice-changer.json +++ b/examples/advanced-ai-voice-changer.json @@ -1,340 +1,7 @@ { - "last_node_id": 43, - "last_link_id": 77, + "last_node_id": 46, + "last_link_id": 84, "nodes": [ - { - "id": 33, - "type": "MergeAudioNode", - "pos": [ - 1154, - -367 - ], - "size": [ - 315, - 166 - ], - "flags": {}, - "order": 12, - "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", - "mean", - true, - { - "hidden": false, - "paused": false, - "params": {} - } - ] - }, - { - "id": 39, - "type": "PreviewAudio", - "pos": [ - 1514, - -358 - ], - "size": [ - 315, - 150 - ], - "flags": {}, - "order": 13, - "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": {} - } - ] - }, - { - "id": 40, - "type": "UVR5Node", - "pos": [ - -172, - -567 - ], - "size": { - "0": 315, - "1": 150 - }, - "flags": {}, - "order": 4, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "VHS_AUDIO", - "link": 65 - } - ], - "outputs": [ - { - "name": "primary_stem", - "type": "VHS_AUDIO", - "links": null, - "shape": 3 - }, - { - "name": "secondary_stem", - "type": "VHS_AUDIO", - "links": [ - 68, - 69 - ], - "shape": 3, - "slot_index": 1 - } - ], - "properties": { - "Node name for S&R": "UVR5Node" - }, - "widgets_values": [ - "UVR/UVR-DeEcho-DeReverb.pth", - true, - 10, - "flac" - ] - }, - { - "id": 41, - "type": "UVR5Node", - "pos": [ - 269, - -736 - ], - "size": { - "0": 315, - "1": 150 - }, - "flags": {}, - "order": 6, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "VHS_AUDIO", - "link": 68 - } - ], - "outputs": [ - { - "name": "primary_stem", - "type": "VHS_AUDIO", - "links": [ - 70 - ], - "shape": 3, - "slot_index": 0 - }, - { - "name": "secondary_stem", - "type": "VHS_AUDIO", - "links": [ - 72 - ], - "shape": 3, - "slot_index": 1 - } - ], - "properties": { - "Node name for S&R": "UVR5Node" - }, - "widgets_values": [ - "UVR/HP5-vocals+instrumentals.pth", - true, - 10, - "flac" - ] - }, - { - "id": 42, - "type": "UVR5Node", - "pos": [ - 613, - -733 - ], - "size": { - "0": 315, - "1": 150 - }, - "flags": {}, - "order": 7, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "VHS_AUDIO", - "link": 69 - } - ], - "outputs": [ - { - "name": "primary_stem", - "type": "VHS_AUDIO", - "links": [ - 71 - ], - "shape": 3, - "slot_index": 0 - }, - { - "name": "secondary_stem", - "type": "VHS_AUDIO", - "links": [ - 73 - ], - "shape": 3, - "slot_index": 1 - } - ], - "properties": { - "Node name for S&R": "UVR5Node" - }, - "widgets_values": [ - "karafan/MDX23C-8KFFT-InstVoc_HQ.ckpt", - true, - 10, - "flac" - ] - }, - { - "id": 35, - "type": "MergeAudioNode", - "pos": [ - 271, - -545 - ], - "size": [ - 315, - 166 - ], - "flags": {}, - "order": 8, - "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 - ], - "shape": 3, - "slot_index": 0 - } - ], - "properties": { - "Node name for S&R": "MergeAudioNode" - }, - "widgets_values": [ - "None", - "min", - true, - { - "hidden": false, - "paused": false, - "params": {} - } - ] - }, { "id": 36, "type": "MergeAudioNode", @@ -342,12 +9,12 @@ 608, -544 ], - "size": [ - 315, - 166 - ], + "size": { + "0": 315, + "1": 166 + }, "flags": {}, - "order": 9, + "order": 10, "mode": 0, "inputs": [ { @@ -388,20 +55,15 @@ "widgets_values": [ "None", "mean", - true, - { - "hidden": false, - "paused": false, - "params": {} - } + true ] }, { "id": 6, "type": "LoadPitchExtractionParams", "pos": [ - 272, - 101 + 266.0001464843749, + 143.99998779296874 ], "size": { "0": 315, @@ -433,155 +95,74 @@ ] }, { - "id": 38, - "type": "LoadAudio", + "id": 35, + "type": "MergeAudioNode", "pos": [ - -171, - -739 + 271, + -545 ], "size": { - "0": 309.8900146484375, - "1": 126 + "0": 315, + "1": 166 }, "flags": {}, - "order": 1, + "order": 9, "mode": 0, - "outputs": [ + "inputs": [ { - "name": "audio_name", - "type": "STRING", - "links": [ - 77 - ], - "shape": 3, - "slot_index": 0 + "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": [ - 65 - ], - "shape": 3, - "slot_index": 1 - } - ], - "properties": { - "Node name for S&R": "LoadAudio" - }, - "widgets_values": [ - "grimlight-ost-1st-trailer---wish-upon-a-star.mp3", - "None", - "image" - ] - }, - { - "id": 31, - "type": "JoinStrings", - "pos": [ - 309, - -145 - ], - "size": { - "0": 315, - "1": 106 - }, - "flags": { - "collapsed": true - }, - "order": 5, - "mode": 0, - "inputs": [ - { - "name": "string1", - "type": "STRING", - "link": 76, - "widget": { - "name": "string1" - } - }, - { - "name": "string2", - "type": "STRING", - "link": 77, - "widget": { - "name": "string2" - } - } - ], - "outputs": [ - { - "name": "STRING", - "type": "STRING", - "links": [ - 64 + 74 ], "shape": 3, "slot_index": 0 } ], "properties": { - "Node name for S&R": "JoinStrings" + "Node name for S&R": "MergeAudioNode" }, "widgets_values": [ - "", - "", - "\\" - ] - }, - { - "id": 4, - "type": "LoadRVCModelNode", - "pos": [ - 637, - -157 - ], - "size": { - "0": 315, - "1": 78 - }, - "flags": {}, - "order": 2, - "mode": 0, - "outputs": [ - { - "name": "model", - "type": "RVC_MODEL", - "links": [ - 57 - ], - "shape": 3 - }, - { - "name": "model_name", - "type": "STRING", - "links": [ - 76 - ], - "shape": 3, - "slot_index": 1 - } - ], - "properties": { - "Node name for S&R": "LoadRVCModelNode" - }, - "widgets_values": [ - "RVC/Sayano.pth" + "None", + "min", + true ] }, { "id": 43, "type": "UVR5Node", "pos": [ - 278, - -99 + 272.0001464843749, + -56.000012207031226 ], "size": { "0": 315, "1": 150 }, "flags": {}, - "order": 10, + "order": 11, "mode": 0, "inputs": [ { @@ -594,48 +175,202 @@ { "name": "primary_stem", "type": "VHS_AUDIO", - "links": [ - 75 - ], + "links": [], "shape": 3, "slot_index": 0 }, { "name": "secondary_stem", "type": "VHS_AUDIO", - "links": null, - "shape": 3 + "links": [ + 78 + ], + "shape": 3, + "slot_index": 1 } ], "properties": { "Node name for S&R": "UVR5Node" }, "widgets_values": [ - "UVR/HP5-vocals+instrumentals.pth", + "UVR/UVR-DeNoise.pth", true, 10, "flac" ] }, { - "id": 37, - "type": "RVCNode", + "id": 45, + "type": "RVC-Studio.LoadAudio", "pos": [ - 639, - 61 + -161, + -737 + ], + "size": { + "0": 295.5188293457031, + "1": 130.45115661621094 + }, + "flags": {}, + "order": 1, + "mode": 0, + "outputs": [ + { + "name": "audio_name", + "type": "STRING", + "links": [ + 79 + ], + "shape": 3, + "slot_index": 0 + }, + { + "name": "vhs_audio", + "type": "VHS_AUDIO", + "links": [ + 80 + ], + "shape": 3, + "slot_index": 1 + } + ], + "properties": { + "Node name for S&R": "RVC-Studio.LoadAudio" + }, + "widgets_values": [ + "FRIENDS.mp3", + "None", + "image" + ] + }, + { + "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 + ], + "shape": 3, + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "MergeAudioNode" + }, + "widgets_values": [ + "None", + "mean", + true + ] + }, + { + "id": 46, + "type": "RVC-Studio.PreviewAudio", + "pos": [ + 1510, + -370 ], "size": [ - 309.34271240234375, - 166 + 315, + 174 ], "flags": {}, - "order": 11, + "order": 14, "mode": 0, "inputs": [ { "name": "audio", "type": "VHS_AUDIO", - "link": 75 + "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 + } + ], + "properties": { + "Node name for S&R": "RVC-Studio.PreviewAudio" + }, + "widgets_values": [ + "test", + "flac", + 1, + true, + 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", @@ -670,20 +405,15 @@ "widgets_values": [ 0, "flac", - true, - { - "hidden": false, - "paused": false, - "params": {} - } + true ] }, { "id": 5, "type": "LoadHubertModel", "pos": [ - 642, - -34 + 628.0001464843749, + 35.99998779296875 ], "size": { "0": 315, @@ -692,7 +422,7 @@ "flags": { "collapsed": false }, - "order": 3, + "order": 2, "mode": 0, "outputs": [ { @@ -708,7 +438,277 @@ "Node name for S&R": "LoadHubertModel" }, "widgets_values": [ - "hubert_base.pt" + "content-vec-best.safetensors" + ] + }, + { + "id": 4, + "type": "LoadRVCModelNode", + "pos": [ + 628.0001464843749, + -110.00001220703123 + ], + "size": { + "0": 315, + "1": 102 + }, + "flags": {}, + "order": 3, + "mode": 0, + "outputs": [ + { + "name": "model", + "type": "RVC_MODEL", + "links": [ + 57 + ], + "shape": 3 + }, + { + "name": "model_name", + "type": "STRING", + "links": [ + 76 + ], + "shape": 3, + "slot_index": 1 + } + ], + "properties": { + "Node name for S&R": "LoadRVCModelNode" + }, + "widgets_values": [ + "RVC/Sayano.pth", + "None" + ] + }, + { + "id": 44, + "type": "Note", + "pos": [ + 441, + -280 + ], + "size": { + "0": 428.5817565917969, + "1": 61.225948333740234 + }, + "flags": {}, + "order": 4, + "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": 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 + ], + "shape": 3, + "slot_index": 0 + }, + { + "name": "secondary_stem", + "type": "VHS_AUDIO", + "links": [ + 72 + ], + "shape": 3, + "slot_index": 1 + } + ], + "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 + ], + "shape": 3, + "slot_index": 0 + }, + { + "name": "secondary_stem", + "type": "VHS_AUDIO", + "links": [ + 73 + ], + "shape": 3, + "slot_index": 1 + } + ], + "properties": { + "Node name for S&R": "UVR5Node" + }, + "widgets_values": [ + "karafan/MDX23C-8KFFT-InstVoc_HQ.ckpt", + true, + 10, + "flac" + ] + }, + { + "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 + ], + "shape": 3, + "slot_index": 0 + }, + { + "name": "secondary_stem", + "type": "VHS_AUDIO", + "links": [], + "shape": 3, + "slot_index": 1 + } + ], + "properties": { + "Node name for S&R": "UVR5Node" + }, + "widgets_values": [ + "UVR/UVR-DeEcho-DeReverb.pth", + true, + 10, + "flac" + ] + }, + { + "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 + ], + "shape": 3, + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "JoinStrings" + }, + "widgets_values": [ + "", + "", + "\\" ] } ], @@ -753,46 +753,6 @@ 1, "VHS_AUDIO" ], - [ - 63, - 33, - 0, - 39, - 0, - "VHS_AUDIO" - ], - [ - 64, - 31, - 0, - 39, - 1, - "STRING" - ], - [ - 65, - 38, - 1, - 40, - 0, - "VHS_AUDIO" - ], - [ - 68, - 40, - 1, - 41, - 0, - "VHS_AUDIO" - ], - [ - 69, - 40, - 1, - 42, - 0, - "VHS_AUDIO" - ], [ 70, 41, @@ -833,14 +793,6 @@ 0, "VHS_AUDIO" ], - [ - 75, - 43, - 0, - 37, - 0, - "VHS_AUDIO" - ], [ 76, 4, @@ -850,12 +802,60 @@ "STRING" ], [ - 77, - 38, + 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": [ @@ -884,8 +884,8 @@ { "title": "Postprocess", "bounding": [ - 262, - -236, + 256, + -193, 712, 529 ], @@ -907,10 +907,10 @@ "config": {}, "extra": { "ds": { - "scale": 0.6830134553650705, + "scale": 0.6209213230591555, "offset": [ - 417.8530750478458, - 895.7208507202507 + 475.93439305141254, + 926.6020865616118 ] } }, diff --git a/examples/complete-ai-voice-changer.json b/examples/complete-ai-voice-changer.json index 0a4007c..3c33e27 100644 --- a/examples/complete-ai-voice-changer.json +++ b/examples/complete-ai-voice-changer.json @@ -1,245 +1,7 @@ { - "last_node_id": 54, - "last_link_id": 168, + "last_node_id": 57, + "last_link_id": 173, "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", @@ -258,7 +20,7 @@ { "name": "audio", "type": "VHS_AUDIO", - "link": 163 + "link": 170 } ], "outputs": [ @@ -306,7 +68,7 @@ 166 ], "flags": {}, - "order": 12, + "order": 13, "mode": 0, "inputs": [ { @@ -349,11 +111,6 @@ "None", "median", true, - { - "hidden": false, - "paused": false, - "params": {} - }, { "hidden": false, "paused": false, @@ -373,7 +130,7 @@ "1": 170 }, "flags": {}, - "order": 10, + "order": 11, "mode": 0, "inputs": [ { @@ -430,7 +187,7 @@ 166 ], "flags": {}, - "order": 7, + "order": 8, "mode": 0, "inputs": [ { @@ -474,16 +231,6 @@ "None", "median", true, - { - "hidden": false, - "paused": false, - "params": {} - }, - { - "hidden": false, - "paused": false, - "params": {} - }, { "hidden": false, "paused": false, @@ -509,7 +256,7 @@ { "name": "audio", "type": "VHS_AUDIO", - "link": 162 + "link": 169 } ], "outputs": [ @@ -558,7 +305,7 @@ 166 ], "flags": {}, - "order": 11, + "order": 12, "mode": 0, "inputs": [ { @@ -601,88 +348,6 @@ "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, @@ -702,7 +367,7 @@ "1": 170 }, "flags": {}, - "order": 14, + "order": 15, "mode": 0, "inputs": [ { @@ -757,7 +422,7 @@ "1": 170 }, "flags": {}, - "order": 15, + "order": 16, "mode": 0, "inputs": [ { @@ -812,7 +477,7 @@ "1": 170 }, "flags": {}, - "order": 13, + "order": 14, "mode": 0, "inputs": [ { @@ -856,80 +521,6 @@ "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", @@ -942,7 +533,7 @@ "1": 170 }, "flags": {}, - "order": 9, + "order": 10, "mode": 0, "inputs": [ { @@ -999,7 +590,7 @@ "1": 170 }, "flags": {}, - "order": 8, + "order": 9, "mode": 0, "inputs": [ { @@ -1045,25 +636,25 @@ ] }, { - "id": 53, - "type": "LoadAudio", + "id": 55, + "type": "RVC-Studio.LoadAudio", "pos": [ - -501, - -799 + -520, + -786 ], "size": [ - 210, - 126 + 252.92194524229842, + 135.8853593804132 ], "flags": {}, - "order": 3, + "order": 0, "mode": 0, "outputs": [ { "name": "audio_name", "type": "STRING", "links": [ - 168 + 171 ], "shape": 3, "slot_index": 0 @@ -1072,20 +663,76 @@ "name": "vhs_audio", "type": "VHS_AUDIO", "links": [ - 162, - 163 + 169, + 170 ], "shape": 3, "slot_index": 1 } ], "properties": { - "Node name for S&R": "LoadAudio" + "Node name for S&R": "RVC-Studio.LoadAudio" }, "widgets_values": [ - "Monologue of Three.mp3", + "Midnight Memories.mp3", "None", - "image", + "image" + ] + }, + { + "id": 33, + "type": "MergeAudioNode", + "pos": [ + 1702, + -801 + ], + "size": [ + 315, + 166 + ], + "flags": {}, + "order": 19, + "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": [ + 172 + ], + "shape": 3, + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "MergeAudioNode" + }, + "widgets_values": [ + "None", + "median", + false, { "hidden": false, "paused": false, @@ -1093,12 +740,165 @@ } ] }, + { + "id": 56, + "type": "RVC-Studio.PreviewAudio", + "pos": [ + 2054, + -796 + ], + "size": [ + 315, + 150 + ], + "flags": {}, + "order": 20, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "VHS_AUDIO", + "link": 172 + }, + { + "name": "filename", + "type": "STRING", + "link": 173, + "widget": { + "name": "filename" + } + } + ], + "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": "RVC-Studio.PreviewAudio" + }, + "widgets_values": [ + "test", + "flac", + 1, + true, + true, + { + "hidden": false, + "paused": false, + "params": {} + } + ] + }, + { + "id": 37, + "type": "RVCNode", + "pos": [ + 1299, + -191 + ], + "size": [ + 309.34271240234375, + 166 + ], + "flags": {}, + "order": 18, + "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": {} + } + ] + }, + { + "id": 5, + "type": "LoadHubertModel", + "pos": [ + 1293, + -288 + ], + "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": 31, "type": "JoinStrings", "pos": [ - 1379, - -786 + 1383, + -791 ], "size": { "0": 315, @@ -1107,7 +907,7 @@ "flags": { "collapsed": true }, - "order": 4, + "order": 7, "mode": 0, "inputs": [ { @@ -1121,7 +921,7 @@ { "name": "string2", "type": "STRING", - "link": 168, + "link": 171, "widget": { "name": "string2" } @@ -1132,7 +932,7 @@ "name": "STRING", "type": "STRING", "links": [ - 64 + 173 ], "shape": 3, "slot_index": 0 @@ -1146,6 +946,168 @@ "", "\\" ] + }, + { + "id": 46, + "type": "MergeAudioNode", + "pos": [ + 1294, + -753 + ], + "size": [ + 315, + 166 + ], + "flags": {}, + "order": 17, + "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": {} + } + ] + }, + { + "id": 6, + "type": "LoadPitchExtractionParams", + "pos": [ + 1297, + -499 + ], + "size": { + "0": 315, + "1": 178 + }, + "flags": {}, + "order": 2, + "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": 4, + "type": "LoadRVCModelNode", + "pos": [ + 961, + -135 + ], + "size": { + "0": 315, + "1": 102 + }, + "flags": {}, + "order": 3, + "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": 57, + "type": "Note", + "pos": [ + -489, + -945 + ], + "size": { + "0": 210, + "1": 58 + }, + "flags": {}, + "order": 4, + "mode": 0, + "properties": { + "text": "" + }, + "widgets_values": [ + "Enjoy the complete AI song cover generator!" + ], + "color": "#432", + "bgcolor": "#653" } ], "links": [ @@ -1189,22 +1151,6 @@ 1, "VHS_AUDIO" ], - [ - 63, - 33, - 0, - 39, - 0, - "VHS_AUDIO" - ], - [ - 64, - 31, - 0, - 39, - 1, - "STRING" - ], [ 66, 4, @@ -1333,22 +1279,6 @@ 1, "VHS_AUDIO" ], - [ - 162, - 53, - 1, - 11, - 0, - "VHS_AUDIO" - ], - [ - 163, - 53, - 1, - 44, - 0, - "VHS_AUDIO" - ], [ 166, 7, @@ -1366,12 +1296,44 @@ "VHS_AUDIO" ], [ - 168, - 53, + 169, + 55, + 1, + 11, + 0, + "VHS_AUDIO" + ], + [ + 170, + 55, + 1, + 44, + 0, + "VHS_AUDIO" + ], + [ + 171, + 55, 0, 31, 1, "STRING" + ], + [ + 172, + 33, + 0, + 56, + 0, + "VHS_AUDIO" + ], + [ + 173, + 31, + 0, + 56, + 1, + "STRING" ] ], "groups": [ @@ -1423,10 +1385,10 @@ "config": {}, "extra": { "ds": { - "scale": 0.9090909090909091, + "scale": 0.5131581182307068, "offset": [ - -959.9219208282357, - 981.1146284125558 + 779.5032540079666, + 1177.1065437973318 ] } }, diff --git a/examples/simple-ai-voice-changer.json b/examples/simple-ai-voice-changer.json index 2fc4cf6..46edc02 100644 --- a/examples/simple-ai-voice-changer.json +++ b/examples/simple-ai-voice-changer.json @@ -1,6 +1,6 @@ { - "last_node_id": 9, - "last_link_id": 15, + "last_node_id": 20, + "last_link_id": 25, "nodes": [ { "id": 6, @@ -38,37 +38,6 @@ 0.25 ] }, - { - "id": 5, - "type": "LoadHubertModel", - "pos": [ - 627, - 12 - ], - "size": { - "0": 315, - "1": 58 - }, - "flags": {}, - "order": 1, - "mode": 0, - "outputs": [ - { - "name": "hubert_model", - "type": "HUBERT_MODEL", - "links": [ - 4 - ], - "shape": 3 - } - ], - "properties": { - "Node name for S&R": "LoadHubertModel" - }, - "widgets_values": [ - "hubert_base.pt" - ] - }, { "id": 4, "type": "LoadRVCModelNode", @@ -78,10 +47,10 @@ ], "size": { "0": 315, - "1": 78 + "1": 102 }, "flags": {}, - "order": 2, + "order": 1, "mode": 0, "outputs": [ { @@ -103,66 +72,8 @@ "Node name for S&R": "LoadRVCModelNode" }, "widgets_values": [ - "RVC/Sayano.pth" - ] - }, - { - "id": 3, - "type": "PreviewAudio", - "pos": [ - 1347, - 132 - ], - "size": [ - 315, - 150 - ], - "flags": {}, - "order": 7, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "VHS_AUDIO", - "link": 10 - }, - { - "name": "filename", - "type": "STRING", - "link": 11, - "widget": { - "name": "filename" - } - } - ], - "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", - 1, - true, - true, - { - "hidden": false, - "paused": false, - "params": {} - } + "RVC/Sayano.pth", + "None" ] }, { @@ -172,12 +83,12 @@ 621, 122 ], - "size": [ - 313.7279357910156, - 166 - ], + "size": { + "0": 313.7279357910156, + "1": 166 + }, "flags": {}, - "order": 5, + "order": 6, "mode": 0, "inputs": [ { @@ -222,33 +133,170 @@ "widgets_values": [ 0, "flac", - true, + true + ] + }, + { + "id": 5, + "type": "LoadHubertModel", + "pos": [ + 627, + 12 + ], + "size": { + "0": 315, + "1": 58 + }, + "flags": {}, + "order": 2, + "mode": 0, + "outputs": [ { - "hidden": false, - "paused": false, - "params": {} + "name": "hubert_model", + "type": "HUBERT_MODEL", + "links": [ + 4 + ], + "shape": 3 } + ], + "properties": { + "Node name for S&R": "LoadHubertModel" + }, + "widgets_values": [ + "content-vec-best.safetensors" + ] + }, + { + "id": 8, + "type": "MergeAudioNode", + "pos": [ + 981, + 128 + ], + "size": { + "0": 315, + "1": 166 + }, + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "audio1", + "type": "VHS_AUDIO", + "link": 15 + }, + { + "name": "audio2", + "type": "VHS_AUDIO", + "link": 13 + }, + { + "name": "audio3_opt", + "type": "VHS_AUDIO", + "link": null + }, + { + "name": "audio4_opt", + "type": "VHS_AUDIO", + "link": null + } + ], + "outputs": [ + { + "name": "vhs_audio", + "type": "VHS_AUDIO", + "links": [ + 23 + ], + "shape": 3, + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "MergeAudioNode" + }, + "widgets_values": [ + "None", + "mean", + true + ] + }, + { + "id": 19, + "type": "RVC-Studio.PreviewAudio", + "pos": [ + 1413, + 112 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "VHS_AUDIO", + "link": 23 + }, + { + "name": "filename", + "type": "STRING", + "link": 25, + "widget": { + "name": "filename" + } + } + ], + "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": "RVC-Studio.PreviewAudio" + }, + "widgets_values": [ + "test", + "flac", + 1, + true, + true ] }, { "id": 9, "type": "UVR5Node", "pos": [ - 243, - 157 + 260, + 172 ], "size": { "0": 315, "1": 150 }, "flags": {}, - "order": 4, + "order": 5, "mode": 0, "inputs": [ { "name": "audio", "type": "VHS_AUDIO", - "link": 12 + "link": 24, + "slot_index": 0 } ], "outputs": [ @@ -282,86 +330,48 @@ ] }, { - "id": 8, - "type": "MergeAudioNode", + "id": 16, + "type": "Note", "pos": [ - 981, - 128 - ], - "size": [ - 315, - 166 - ], - "flags": {}, - "order": 6, - "mode": 0, - "inputs": [ - { - "name": "audio1", - "type": "VHS_AUDIO", - "link": 15 - }, - { - "name": "audio2", - "type": "VHS_AUDIO", - "link": 13 - }, - { - "name": "audio3_opt", - "type": "VHS_AUDIO", - "link": null - }, - { - "name": "audio4_opt", - "type": "VHS_AUDIO", - "link": null - } - ], - "outputs": [ - { - "name": "vhs_audio", - "type": "VHS_AUDIO", - "links": [ - 10 - ], - "shape": 3, - "slot_index": 0 - } - ], - "properties": { - "Node name for S&R": "MergeAudioNode" - }, - "widgets_values": [ - "None", - "mean", - true, - { - "hidden": false, - "paused": false, - "params": {} - } - ] - }, - { - "id": 2, - "type": "LoadAudio", - "pos": [ - -106, - 162 + -265, + 1 ], "size": { - "0": 315, - "1": 126 + "0": 445.6835632324219, + "1": 100.08426666259766 }, "flags": {}, "order": 3, "mode": 0, + "properties": { + "text": "" + }, + "widgets_values": [ + "Basic workflow for generating AI covers.\n\nThe nodes here use the legacy VHS_AUDIO format. You can use the converter from VHS (https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite) if you want to use the built-in audio format." + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 20, + "type": "RVC-Studio.LoadAudio", + "pos": [ + -31, + 171 + ], + "size": { + "0": 210, + "1": 126 + }, + "flags": {}, + "order": 4, + "mode": 0, "outputs": [ { "name": "audio_name", "type": "STRING", "links": [ - 11 + 25 ], "shape": 3, "slot_index": 0 @@ -370,22 +380,18 @@ "name": "vhs_audio", "type": "VHS_AUDIO", "links": [ - 12 + 24 ], "shape": 3 } ], "properties": { - "Node name for S&R": "LoadAudio" + "Node name for S&R": "RVC-Studio.LoadAudio" }, "widgets_values": [ - "grimlight-ost-1st-trailer---wish-upon-a-star.mp3", + "FRIENDS.mp3", "None", - { - "hidden": false, - "paused": false, - "params": {} - } + "image" ] } ], @@ -414,30 +420,6 @@ 3, "PITCH_EXTRACTION" ], - [ - 10, - 8, - 0, - 3, - 0, - "VHS_AUDIO" - ], - [ - 11, - 2, - 0, - 3, - 1, - "STRING" - ], - [ - 12, - 2, - 1, - 9, - 0, - "VHS_AUDIO" - ], [ 13, 9, @@ -461,16 +443,40 @@ 8, 0, "VHS_AUDIO" + ], + [ + 23, + 8, + 0, + 19, + 0, + "VHS_AUDIO" + ], + [ + 24, + 20, + 1, + 9, + 0, + "VHS_AUDIO" + ], + [ + 25, + 20, + 0, + 19, + 1, + "STRING" ] ], "groups": [], "config": {}, "extra": { "ds": { - "scale": 0.6830134553650706, + "scale": 0.683013455365071, "offset": [ - 531.5168724939232, - 463.2073890439136 + 423.91524190043117, + 577.965666728948 ] } },