diff --git a/example_workflows/wanvideo_I2V_InfiniteTalk_example_01.json b/example_workflows/wanvideo_I2V_InfiniteTalk_example_02.json
similarity index 91%
rename from example_workflows/wanvideo_I2V_InfiniteTalk_example_01.json
rename to example_workflows/wanvideo_I2V_InfiniteTalk_example_02.json
index 1f215b5..2834730 100644
--- a/example_workflows/wanvideo_I2V_InfiniteTalk_example_01.json
+++ b/example_workflows/wanvideo_I2V_InfiniteTalk_example_02.json
@@ -1,8 +1,8 @@
{
"id": "8b7a9a57-2303-4ef5-9fc2-bf41713bd1fc",
"revision": 0,
- "last_node_id": 299,
- "last_link_id": 540,
+ "last_node_id": 304,
+ "last_link_id": 545,
"nodes": [
{
"id": 120,
@@ -121,7 +121,7 @@
"flags": {
"collapsed": true
},
- "order": 24,
+ "order": 28,
"mode": 0,
"inputs": [
{
@@ -161,7 +161,7 @@
"flags": {
"collapsed": true
},
- "order": 34,
+ "order": 36,
"mode": 0,
"inputs": [
{
@@ -236,7 +236,7 @@
"flags": {
"collapsed": true
},
- "order": 25,
+ "order": 29,
"mode": 0,
"inputs": [
{
@@ -276,7 +276,7 @@
"flags": {
"collapsed": true
},
- "order": 28,
+ "order": 31,
"mode": 0,
"inputs": [
{
@@ -316,7 +316,7 @@
"flags": {
"collapsed": true
},
- "order": 29,
+ "order": 32,
"mode": 0,
"inputs": [
{
@@ -342,184 +342,12 @@
"color": "#1b4669",
"bgcolor": "#29699c"
},
- {
- "id": 159,
- "type": "AudioCrop",
- "pos": [
- 676.1865234375,
- -1132.495361328125
- ],
- "size": [
- 270,
- 82
- ],
- "flags": {},
- "order": 26,
- "mode": 4,
- "inputs": [
- {
- "name": "audio",
- "type": "AUDIO",
- "link": 257
- }
- ],
- "outputs": [
- {
- "name": "AUDIO",
- "type": "AUDIO",
- "links": [
- 301,
- 448
- ]
- }
- ],
- "properties": {
- "cnr_id": "audio-separation-nodes-comfyui",
- "ver": "31a4567726e035097cc2d1f767767908a6fda2ea",
- "Node name for S&R": "AudioCrop"
- },
- "widgets_values": [
- "0:02",
- "2:00"
- ]
- },
- {
- "id": 170,
- "type": "AudioSeparation",
- "pos": [
- 1064.037353515625,
- -1347.1170654296875
- ],
- "size": [
- 270,
- 166
- ],
- "flags": {},
- "order": 32,
- "mode": 0,
- "inputs": [
- {
- "name": "audio",
- "type": "AUDIO",
- "link": 301
- }
- ],
- "outputs": [
- {
- "name": "Bass",
- "type": "AUDIO",
- "links": null
- },
- {
- "name": "Drums",
- "type": "AUDIO",
- "links": null
- },
- {
- "name": "Other",
- "type": "AUDIO",
- "links": null
- },
- {
- "name": "Vocals",
- "type": "AUDIO",
- "links": [
- 335
- ]
- }
- ],
- "properties": {
- "cnr_id": "audio-separation-nodes-comfyui",
- "ver": "31a4567726e035097cc2d1f767767908a6fda2ea",
- "Node name for S&R": "AudioSeparation"
- },
- "widgets_values": [
- "linear",
- 10,
- 0.1
- ]
- },
- {
- "id": 137,
- "type": "DownloadAndLoadWav2VecModel",
- "pos": [
- 1400.8470458984375,
- -1411.5140380859375
- ],
- "size": [
- 330.96728515625,
- 106
- ],
- "flags": {},
- "order": 4,
- "mode": 0,
- "inputs": [],
- "outputs": [
- {
- "name": "wav2vec_model",
- "type": "WAV2VECMODEL",
- "links": [
- 334
- ]
- }
- ],
- "properties": {
- "cnr_id": "ComfyUI-WanVideoWrapper",
- "ver": "058286fc0f3b0651a2f6b68309df3f06e8332cc0",
- "Node name for S&R": "DownloadAndLoadWav2VecModel"
- },
- "widgets_values": [
- "TencentGameMate/chinese-wav2vec2-base",
- "fp16",
- "main_device"
- ]
- },
- {
- "id": 253,
- "type": "SetNode",
- "pos": [
- 1002.430908203125,
- -1102.810302734375
- ],
- "size": [
- 210,
- 60
- ],
- "flags": {
- "collapsed": true
- },
- "order": 33,
- "mode": 0,
- "inputs": [
- {
- "name": "AUDIO",
- "type": "AUDIO",
- "link": 448
- }
- ],
- "outputs": [
- {
- "name": "*",
- "type": "*",
- "links": null
- }
- ],
- "title": "Set_input_audio",
- "properties": {
- "previousName": "input_audio"
- },
- "widgets_values": [
- "input_audio"
- ],
- "color": "#323",
- "bgcolor": "#535"
- },
{
"id": 282,
"type": "GetNode",
"pos": [
- 1040.8619384765625,
- -1797.7919921875
+ 1036.8980712890625,
+ -1798.782958984375
],
"size": [
210,
@@ -528,7 +356,7 @@
"flags": {
"collapsed": true
},
- "order": 5,
+ "order": 4,
"mode": 0,
"inputs": [],
"outputs": [
@@ -562,7 +390,7 @@
"flags": {
"collapsed": true
},
- "order": 6,
+ "order": 5,
"mode": 0,
"inputs": [],
"outputs": [
@@ -594,7 +422,7 @@
150
],
"flags": {},
- "order": 7,
+ "order": 6,
"mode": 0,
"inputs": [
{
@@ -633,41 +461,6 @@
"color": "#223",
"bgcolor": "#335"
},
- {
- "id": 125,
- "type": "LoadAudio",
- "pos": [
- 536.47412109375,
- -1357.4945068359375
- ],
- "size": [
- 404.9698791503906,
- 136
- ],
- "flags": {},
- "order": 8,
- "mode": 0,
- "inputs": [],
- "outputs": [
- {
- "name": "AUDIO",
- "type": "AUDIO",
- "links": [
- 257
- ]
- }
- ],
- "properties": {
- "cnr_id": "comfy-core",
- "ver": "0.3.41",
- "Node name for S&R": "LoadAudio"
- },
- "widgets_values": [
- "hush.mp3",
- null,
- null
- ]
- },
{
"id": 134,
"type": "WanVideoBlockSwap",
@@ -680,7 +473,7 @@
202
],
"flags": {},
- "order": 9,
+ "order": 7,
"mode": 0,
"inputs": [],
"outputs": [
@@ -721,7 +514,7 @@
58
],
"flags": {},
- "order": 10,
+ "order": 8,
"mode": 0,
"inputs": [],
"outputs": [
@@ -757,7 +550,7 @@
58
],
"flags": {},
- "order": 11,
+ "order": 9,
"mode": 0,
"inputs": [],
"outputs": [
@@ -793,7 +586,7 @@
262
],
"flags": {},
- "order": 37,
+ "order": 39,
"mode": 0,
"inputs": [
{
@@ -859,7 +652,7 @@
"flags": {
"collapsed": true
},
- "order": 12,
+ "order": 10,
"mode": 0,
"inputs": [],
"outputs": [
@@ -893,7 +686,7 @@
"flags": {
"collapsed": true
},
- "order": 13,
+ "order": 11,
"mode": 0,
"inputs": [],
"outputs": [
@@ -925,7 +718,7 @@
58
],
"flags": {},
- "order": 14,
+ "order": 12,
"mode": 0,
"inputs": [],
"outputs": [
@@ -953,8 +746,8 @@
"id": 294,
"type": "SetNode",
"pos": [
- 1751.949462890625,
- -1184.374267578125
+ 1676.046630859375,
+ -1182.43310546875
],
"size": [
210,
@@ -963,7 +756,7 @@
"flags": {
"collapsed": true
},
- "order": 38,
+ "order": 42,
"mode": 0,
"inputs": [
{
@@ -995,15 +788,15 @@
"id": 293,
"type": "PreviewAny",
"pos": [
- 1772.05078125,
- -1110.6668701171875
+ 1696.14794921875,
+ -1108.7257080078125
],
"size": [
210,
88
],
"flags": {},
- "order": 40,
+ "order": 44,
"mode": 0,
"inputs": [
{
@@ -1034,7 +827,7 @@
"flags": {
"collapsed": true
},
- "order": 30,
+ "order": 33,
"mode": 0,
"inputs": [
{
@@ -1064,15 +857,15 @@
"id": 194,
"type": "MultiTalkWav2VecEmbeds",
"pos": [
- 1400.6778564453125,
- -1237.9234619140625
+ 1324.7750244140625,
+ -1235.9822998046875
],
"size": [
291.08203125,
278
],
"flags": {},
- "order": 36,
+ "order": 40,
"mode": 0,
"inputs": [
{
@@ -1083,7 +876,7 @@
{
"name": "audio_1",
"type": "AUDIO",
- "link": 335
+ "link": 544
},
{
"name": "audio_2",
@@ -1159,15 +952,15 @@
"id": 263,
"type": "Note",
"pos": [
- 1719.4892578125,
- -965.56591796875
+ 1643.58642578125,
+ -963.624755859375
],
"size": [
344.82928466796875,
143.7332305908203
],
"flags": {},
- "order": 15,
+ "order": 13,
"mode": 0,
"inputs": [],
"outputs": [],
@@ -1190,7 +983,7 @@
314
],
"flags": {},
- "order": 27,
+ "order": 30,
"mode": 0,
"inputs": [
{
@@ -1284,7 +1077,7 @@
202
],
"flags": {},
- "order": 16,
+ "order": 14,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1315,8 +1108,8 @@
"id": 272,
"type": "GetNode",
"pos": [
- 1174.7862548828125,
- -1059.2822265625
+ 1098.8834228515625,
+ -1057.341064453125
],
"size": [
210,
@@ -1325,7 +1118,7 @@
"flags": {
"collapsed": true
},
- "order": 17,
+ "order": 15,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1357,7 +1150,7 @@
198
],
"flags": {},
- "order": 42,
+ "order": 45,
"mode": 0,
"inputs": [
{
@@ -1406,10 +1199,10 @@
],
"size": [
991.5499877929688,
- 334
+ 1319.550048828125
],
"flags": {},
- "order": 43,
+ "order": 46,
"mode": 0,
"inputs": [
{
@@ -1488,7 +1281,7 @@
"flags": {
"collapsed": true
},
- "order": 18,
+ "order": 16,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1522,7 +1315,7 @@
"flags": {
"collapsed": false
},
- "order": 35,
+ "order": 37,
"mode": 0,
"inputs": [
{
@@ -1582,7 +1375,7 @@
386.354248046875
],
"flags": {},
- "order": 19,
+ "order": 17,
"mode": 0,
"inputs": [
{
@@ -1640,7 +1433,7 @@
266
],
"flags": {},
- "order": 39,
+ "order": 41,
"mode": 0,
"inputs": [
{
@@ -1718,7 +1511,7 @@
"flags": {
"collapsed": true
},
- "order": 20,
+ "order": 18,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1738,6 +1531,457 @@
"color": "#322",
"bgcolor": "#533"
},
+ {
+ "id": 283,
+ "type": "GetNode",
+ "pos": [
+ 1039.0777587890625,
+ -1849.6192626953125
+ ],
+ "size": [
+ 210,
+ 34
+ ],
+ "flags": {
+ "collapsed": true
+ },
+ "order": 19,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "INT",
+ "type": "INT",
+ "links": [
+ 494
+ ]
+ }
+ ],
+ "title": "Get_width",
+ "properties": {},
+ "widgets_values": [
+ "width"
+ ],
+ "color": "#1b4669",
+ "bgcolor": "#29699c"
+ },
+ {
+ "id": 284,
+ "type": "LoadImage",
+ "pos": [
+ 634.8666381835938,
+ -1939.31591796875
+ ],
+ "size": [
+ 274.080078125,
+ 314
+ ],
+ "flags": {},
+ "order": 20,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "IMAGE",
+ "type": "IMAGE",
+ "links": [
+ 496
+ ]
+ },
+ {
+ "name": "MASK",
+ "type": "MASK",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "comfy-core",
+ "ver": "0.3.50",
+ "Node name for S&R": "LoadImage"
+ },
+ "widgets_values": [
+ "woman.png",
+ "image"
+ ]
+ },
+ {
+ "id": 281,
+ "type": "ImageResizeKJv2",
+ "pos": [
+ 1207.9007568359375,
+ -1937.6312255859375
+ ],
+ "size": [
+ 270,
+ 336
+ ],
+ "flags": {},
+ "order": 34,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "image",
+ "type": "IMAGE",
+ "link": 496
+ },
+ {
+ "name": "mask",
+ "shape": 7,
+ "type": "MASK",
+ "link": null
+ },
+ {
+ "name": "width",
+ "type": "INT",
+ "widget": {
+ "name": "width"
+ },
+ "link": 494
+ },
+ {
+ "name": "height",
+ "type": "INT",
+ "widget": {
+ "name": "height"
+ },
+ "link": 495
+ }
+ ],
+ "outputs": [
+ {
+ "name": "IMAGE",
+ "type": "IMAGE",
+ "links": [
+ 538
+ ]
+ },
+ {
+ "name": "width",
+ "type": "INT",
+ "links": []
+ },
+ {
+ "name": "height",
+ "type": "INT",
+ "links": []
+ },
+ {
+ "name": "mask",
+ "type": "MASK",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "comfyui-kjnodes",
+ "ver": "f7eb33abc80a2aded1b46dff0dd14d07856a7d50",
+ "Node name for S&R": "ImageResizeKJv2"
+ },
+ "widgets_values": [
+ 832,
+ 480,
+ "lanczos",
+ "crop",
+ "0, 0, 0",
+ "center",
+ 16,
+ "cpu"
+ ]
+ },
+ {
+ "id": 299,
+ "type": "Note",
+ "pos": [
+ 1424.5263671875,
+ -2250.27001953125
+ ],
+ "size": [
+ 290.9361267089844,
+ 88
+ ],
+ "flags": {},
+ "order": 21,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [],
+ "properties": {},
+ "widgets_values": [
+ "Clip vision is not strictly necessary\n\nAny I2V model should work, MAGREF can be interesting to play with as well."
+ ],
+ "color": "#432",
+ "bgcolor": "#653"
+ },
+ {
+ "id": 253,
+ "type": "SetNode",
+ "pos": [
+ 909.3299560546875,
+ -1326.90576171875
+ ],
+ "size": [
+ 210,
+ 60
+ ],
+ "flags": {
+ "collapsed": true
+ },
+ "order": 35,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "AUDIO",
+ "type": "AUDIO",
+ "link": 542
+ }
+ ],
+ "outputs": [
+ {
+ "name": "AUDIO",
+ "type": "AUDIO",
+ "links": [
+ 545
+ ]
+ }
+ ],
+ "title": "Set_input_audio",
+ "properties": {
+ "previousName": "input_audio"
+ },
+ "widgets_values": [
+ "input_audio"
+ ],
+ "color": "#323",
+ "bgcolor": "#535"
+ },
+ {
+ "id": 125,
+ "type": "LoadAudio",
+ "pos": [
+ 453.9859313964844,
+ -1425.9039306640625
+ ],
+ "size": [
+ 404.9698791503906,
+ 136
+ ],
+ "flags": {},
+ "order": 22,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "AUDIO",
+ "type": "AUDIO",
+ "links": [
+ 542
+ ]
+ }
+ ],
+ "properties": {
+ "cnr_id": "comfy-core",
+ "ver": "0.3.41",
+ "Node name for S&R": "LoadAudio"
+ },
+ "widgets_values": [
+ "hush.mp3",
+ null,
+ null
+ ]
+ },
+ {
+ "id": 137,
+ "type": "DownloadAndLoadWav2VecModel",
+ "pos": [
+ 453.353515625,
+ -1010.69482421875
+ ],
+ "size": [
+ 330.96728515625,
+ 106
+ ],
+ "flags": {},
+ "order": 23,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "wav2vec_model",
+ "type": "WAV2VECMODEL",
+ "links": [
+ 334
+ ]
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-WanVideoWrapper",
+ "ver": "058286fc0f3b0651a2f6b68309df3f06e8332cc0",
+ "Node name for S&R": "DownloadAndLoadWav2VecModel"
+ },
+ "widgets_values": [
+ "TencentGameMate/chinese-wav2vec2-base",
+ "fp16",
+ "main_device"
+ ]
+ },
+ {
+ "id": 300,
+ "type": "Wav2VecModelLoader",
+ "pos": [
+ 438.4236145019531,
+ -846.713623046875
+ ],
+ "size": [
+ 346.9834289550781,
+ 106
+ ],
+ "flags": {},
+ "order": 24,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "wav2vec_model",
+ "type": "WAV2VECMODEL",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-WanVideoWrapper",
+ "ver": "6fce0e2d3bb976b0006bc6d8e37e1f23460938ee",
+ "Node name for S&R": "Wav2VecModelLoader"
+ },
+ "widgets_values": [
+ "wav2vec2-chinese-base_fp16.safetensors",
+ "fp16",
+ "main_device"
+ ]
+ },
+ {
+ "id": 302,
+ "type": "MelBandRoFormerSampler",
+ "pos": [
+ 1110.198486328125,
+ -1350.2908935546875
+ ],
+ "size": [
+ 222.73397827148438,
+ 46
+ ],
+ "flags": {},
+ "order": 38,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "model",
+ "type": "MELROFORMERMODEL",
+ "link": 543
+ },
+ {
+ "name": "audio",
+ "type": "AUDIO",
+ "link": 545
+ }
+ ],
+ "outputs": [
+ {
+ "name": "vocals",
+ "type": "AUDIO",
+ "links": [
+ 544
+ ]
+ },
+ {
+ "name": "instruments",
+ "type": "AUDIO",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-MelBandRoFormer",
+ "ver": "b68d9077815387b64d596f8c39607052b95b6eba",
+ "Node name for S&R": "MelBandRoFormerSampler"
+ }
+ },
+ {
+ "id": 303,
+ "type": "MarkdownNote",
+ "pos": [
+ 875.717529296875,
+ -854.7509155273438
+ ],
+ "size": [
+ 355.3899841308594,
+ 125.51774597167969
+ ],
+ "flags": {},
+ "order": 25,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [],
+ "title": "Wav2vec2 safetensors",
+ "properties": {},
+ "widgets_values": [
+ "Alternative to the download node is to use single .safetensors file from:\n\n[https://huggingface.co/Kijai/wav2vec2_safetensors/tree/main](https://huggingface.co/Kijai/wav2vec2_safetensors/tree/main)\n\nThe model goes to `ComfyUI/models/wav2vec2`"
+ ],
+ "color": "#432",
+ "bgcolor": "#653"
+ },
+ {
+ "id": 304,
+ "type": "MarkdownNote",
+ "pos": [
+ 461.80609130859375,
+ -1254.9613037109375
+ ],
+ "size": [
+ 345.2374267578125,
+ 91.6759033203125
+ ],
+ "flags": {},
+ "order": 26,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [],
+ "title": "Wav2vec2 safetensors",
+ "properties": {},
+ "widgets_values": [
+ "Vocal separator model\n\n[https://huggingface.co/Kijai/MelBandRoFormer_comfy/tree/main](https://huggingface.co/Kijai/MelBandRoFormer_comfy/tree/main)\n\nThe model goes to `ComfyUI/models/diffusion_models`"
+ ],
+ "color": "#432",
+ "bgcolor": "#653"
+ },
+ {
+ "id": 301,
+ "type": "MelBandRoFormerModelLoader",
+ "pos": [
+ 454.7294006347656,
+ -1117.843994140625
+ ],
+ "size": [
+ 400.5706481933594,
+ 58
+ ],
+ "flags": {},
+ "order": 27,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "model",
+ "type": "MELROFORMERMODEL",
+ "links": [
+ 543
+ ]
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-MelBandRoFormer",
+ "ver": "b68d9077815387b64d596f8c39607052b95b6eba",
+ "Node name for S&R": "MelBandRoFormerModelLoader"
+ },
+ "widgets_values": [
+ "MelBandRoFormer\\MelBandRoformer_fp16.safetensors"
+ ]
+ },
{
"id": 128,
"type": "WanVideoSampler",
@@ -1750,7 +1994,7 @@
999
],
"flags": {},
- "order": 41,
+ "order": 43,
"mode": 0,
"inputs": [
{
@@ -1875,7 +2119,7 @@
"Node name for S&R": "WanVideoSampler"
},
"widgets_values": [
- 7,
+ 6,
1.0000000000000002,
11.000000000000002,
2,
@@ -1890,205 +2134,9 @@
-1,
true
]
- },
- {
- "id": 283,
- "type": "GetNode",
- "pos": [
- 1043.0416259765625,
- -1848.6282958984375
- ],
- "size": [
- 210,
- 34
- ],
- "flags": {
- "collapsed": true
- },
- "order": 21,
- "mode": 0,
- "inputs": [],
- "outputs": [
- {
- "name": "INT",
- "type": "INT",
- "links": [
- 494
- ]
- }
- ],
- "title": "Get_width",
- "properties": {},
- "widgets_values": [
- "width"
- ],
- "color": "#1b4669",
- "bgcolor": "#29699c"
- },
- {
- "id": 284,
- "type": "LoadImage",
- "pos": [
- 638.8305053710938,
- -1938.324951171875
- ],
- "size": [
- 274.080078125,
- 314
- ],
- "flags": {},
- "order": 22,
- "mode": 0,
- "inputs": [],
- "outputs": [
- {
- "name": "IMAGE",
- "type": "IMAGE",
- "links": [
- 496
- ]
- },
- {
- "name": "MASK",
- "type": "MASK",
- "links": null
- }
- ],
- "properties": {
- "cnr_id": "comfy-core",
- "ver": "0.3.50",
- "Node name for S&R": "LoadImage"
- },
- "widgets_values": [
- "woman.png",
- "image"
- ]
- },
- {
- "id": 281,
- "type": "ImageResizeKJv2",
- "pos": [
- 1211.8646240234375,
- -1936.6402587890625
- ],
- "size": [
- 270,
- 336
- ],
- "flags": {},
- "order": 31,
- "mode": 0,
- "inputs": [
- {
- "name": "image",
- "type": "IMAGE",
- "link": 496
- },
- {
- "name": "mask",
- "shape": 7,
- "type": "MASK",
- "link": null
- },
- {
- "name": "width",
- "type": "INT",
- "widget": {
- "name": "width"
- },
- "link": 494
- },
- {
- "name": "height",
- "type": "INT",
- "widget": {
- "name": "height"
- },
- "link": 495
- }
- ],
- "outputs": [
- {
- "name": "IMAGE",
- "type": "IMAGE",
- "links": [
- 538
- ]
- },
- {
- "name": "width",
- "type": "INT",
- "links": []
- },
- {
- "name": "height",
- "type": "INT",
- "links": []
- },
- {
- "name": "mask",
- "type": "MASK",
- "links": null
- }
- ],
- "properties": {
- "cnr_id": "comfyui-kjnodes",
- "ver": "f7eb33abc80a2aded1b46dff0dd14d07856a7d50",
- "Node name for S&R": "ImageResizeKJv2"
- },
- "widgets_values": [
- 832,
- 480,
- "lanczos",
- "crop",
- "0, 0, 0",
- "center",
- 16,
- "cpu",
- "| Output: | 1 x 640 x 640 | 4.69MB |
"
- ]
- },
- {
- "id": 299,
- "type": "Note",
- "pos": [
- 1424.5263671875,
- -2250.27001953125
- ],
- "size": [
- 290.9361267089844,
- 88
- ],
- "flags": {},
- "order": 23,
- "mode": 0,
- "inputs": [],
- "outputs": [],
- "properties": {},
- "widgets_values": [
- "Clip vision is not strictly necessary\n\nAny I2V model should work, MAGREF can be interesting to play with as well."
- ],
- "color": "#432",
- "bgcolor": "#653"
}
],
"links": [
- [
- 257,
- 125,
- 0,
- 159,
- 0,
- "AUDIO"
- ],
- [
- 301,
- 159,
- 0,
- 170,
- 0,
- "AUDIO"
- ],
[
334,
137,
@@ -2097,14 +2145,6 @@
0,
"WAV2VECMODEL"
],
- [
- 335,
- 170,
- 3,
- 194,
- 1,
- "AUDIO"
- ],
[
349,
138,
@@ -2201,14 +2241,6 @@
0,
"*"
],
- [
- 448,
- 159,
- 0,
- 253,
- 0,
- "*"
- ],
[
449,
254,
@@ -2360,6 +2392,38 @@
192,
1,
"IMAGE"
+ ],
+ [
+ 542,
+ 125,
+ 0,
+ 253,
+ 0,
+ "AUDIO"
+ ],
+ [
+ 543,
+ 301,
+ 0,
+ 302,
+ 0,
+ "MELROFORMERMODEL"
+ ],
+ [
+ 544,
+ 302,
+ 0,
+ 194,
+ 1,
+ "AUDIO"
+ ],
+ [
+ 545,
+ 253,
+ 0,
+ 302,
+ 1,
+ "AUDIO"
]
],
"groups": [
@@ -2380,10 +2444,10 @@
"id": 4,
"title": "Audio",
"bounding": [
- 462.57562255859375,
- -1529.8046875,
- 1656.1551513671875,
- 753.9797973632812
+ 386.6732482910156,
+ -1527.863525390625,
+ 1782.2769775390625,
+ 833.420166015625
],
"color": "#a1309b",
"font_size": 24,
@@ -2393,8 +2457,8 @@
"id": 5,
"title": "Input image",
"bounding": [
- 466.7610778808594,
- -2043.424560546875,
+ 462.7972412109375,
+ -2044.41552734375,
1652.696533203125,
495.40948486328125
],
@@ -2406,13 +2470,13 @@
"config": {},
"extra": {
"ds": {
- "scale": 0.45949729863576383,
+ "scale": 0.6115909044842021,
"offset": [
- 34.34672984465828,
- 2847.63895576458
+ -305.72724541367705,
+ 2418.5059970103503
]
},
- "frontendVersion": "1.26.3",
+ "frontendVersion": "1.26.6",
"node_versions": {
"ComfyUI-WanVideoWrapper": "0a11c67a0c0062b534178920a0d6dcaa75e7b5fe",
"comfy-core": "0.3.43",
diff --git a/example_workflows/wanvideo_InfiniteTalk_V2V_example_01.json b/example_workflows/wanvideo_InfiniteTalk_V2V_example_02.json
similarity index 92%
rename from example_workflows/wanvideo_InfiniteTalk_V2V_example_01.json
rename to example_workflows/wanvideo_InfiniteTalk_V2V_example_02.json
index dd7babc..48f26f9 100644
--- a/example_workflows/wanvideo_InfiniteTalk_V2V_example_01.json
+++ b/example_workflows/wanvideo_InfiniteTalk_V2V_example_02.json
@@ -1,15 +1,15 @@
{
"id": "8b7a9a57-2303-4ef5-9fc2-bf41713bd1fc",
"revision": 0,
- "last_node_id": 301,
- "last_link_id": 551,
+ "last_node_id": 306,
+ "last_link_id": 555,
"nodes": [
{
"id": 234,
"type": "Note",
"pos": [
- 539.4052734375,
- -832.4791870117188
+ 537.4234619140625,
+ -784.9131469726562
],
"size": [
289.1911926269531,
@@ -90,8 +90,8 @@
"id": 243,
"type": "GetNode",
"pos": [
- 1715.7088623046875,
- -924.8023071289062
+ 1713.7271728515625,
+ -877.2362670898438
],
"size": [
210,
@@ -178,7 +178,7 @@
"flags": {
"collapsed": true
},
- "order": 24,
+ "order": 28,
"mode": 0,
"inputs": [
{
@@ -218,7 +218,7 @@
"flags": {
"collapsed": true
},
- "order": 32,
+ "order": 36,
"mode": 0,
"inputs": [
{
@@ -293,7 +293,7 @@
"flags": {
"collapsed": true
},
- "order": 25,
+ "order": 29,
"mode": 0,
"inputs": [
{
@@ -333,7 +333,7 @@
"flags": {
"collapsed": true
},
- "order": 27,
+ "order": 31,
"mode": 0,
"inputs": [
{
@@ -373,7 +373,7 @@
"flags": {
"collapsed": true
},
- "order": 28,
+ "order": 32,
"mode": 0,
"inputs": [
{
@@ -399,137 +399,6 @@
"color": "#1b4669",
"bgcolor": "#29699c"
},
- {
- "id": 170,
- "type": "AudioSeparation",
- "pos": [
- 1099.1485595703125,
- -1843.935302734375
- ],
- "size": [
- 270,
- 166
- ],
- "flags": {},
- "order": 34,
- "mode": 0,
- "inputs": [
- {
- "name": "audio",
- "type": "AUDIO",
- "link": 301
- }
- ],
- "outputs": [
- {
- "name": "Bass",
- "type": "AUDIO",
- "links": null
- },
- {
- "name": "Drums",
- "type": "AUDIO",
- "links": null
- },
- {
- "name": "Other",
- "type": "AUDIO",
- "links": null
- },
- {
- "name": "Vocals",
- "type": "AUDIO",
- "links": [
- 335
- ]
- }
- ],
- "properties": {
- "cnr_id": "audio-separation-nodes-comfyui",
- "ver": "31a4567726e035097cc2d1f767767908a6fda2ea",
- "Node name for S&R": "AudioSeparation"
- },
- "widgets_values": [
- "linear",
- 10,
- 0.1
- ]
- },
- {
- "id": 137,
- "type": "DownloadAndLoadWav2VecModel",
- "pos": [
- 1435.958251953125,
- -1908.332275390625
- ],
- "size": [
- 330.96728515625,
- 106
- ],
- "flags": {},
- "order": 6,
- "mode": 0,
- "inputs": [],
- "outputs": [
- {
- "name": "wav2vec_model",
- "type": "WAV2VECMODEL",
- "links": [
- 334
- ]
- }
- ],
- "properties": {
- "cnr_id": "ComfyUI-WanVideoWrapper",
- "ver": "058286fc0f3b0651a2f6b68309df3f06e8332cc0",
- "Node name for S&R": "DownloadAndLoadWav2VecModel"
- },
- "widgets_values": [
- "TencentGameMate/chinese-wav2vec2-base",
- "fp16",
- "main_device"
- ]
- },
- {
- "id": 253,
- "type": "SetNode",
- "pos": [
- 1037.5419921875,
- -1599.6285400390625
- ],
- "size": [
- 210,
- 60
- ],
- "flags": {
- "collapsed": true
- },
- "order": 35,
- "mode": 0,
- "inputs": [
- {
- "name": "AUDIO",
- "type": "AUDIO",
- "link": 448
- }
- ],
- "outputs": [
- {
- "name": "*",
- "type": "*",
- "links": null
- }
- ],
- "title": "Set_input_audio",
- "properties": {
- "previousName": "input_audio"
- },
- "widgets_values": [
- "input_audio"
- ],
- "color": "#323",
- "bgcolor": "#535"
- },
{
"id": 261,
"type": "GetNode",
@@ -544,7 +413,7 @@
"flags": {
"collapsed": true
},
- "order": 7,
+ "order": 6,
"mode": 0,
"inputs": [],
"outputs": [
@@ -576,7 +445,7 @@
150
],
"flags": {},
- "order": 8,
+ "order": 7,
"mode": 0,
"inputs": [
{
@@ -627,7 +496,7 @@
202
],
"flags": {},
- "order": 9,
+ "order": 8,
"mode": 0,
"inputs": [],
"outputs": [
@@ -668,7 +537,7 @@
58
],
"flags": {},
- "order": 10,
+ "order": 9,
"mode": 0,
"inputs": [],
"outputs": [
@@ -704,7 +573,7 @@
58
],
"flags": {},
- "order": 11,
+ "order": 10,
"mode": 0,
"inputs": [],
"outputs": [
@@ -740,7 +609,7 @@
386.354248046875
],
"flags": {},
- "order": 12,
+ "order": 11,
"mode": 0,
"inputs": [
{
@@ -800,7 +669,7 @@
"flags": {
"collapsed": true
},
- "order": 13,
+ "order": 12,
"mode": 0,
"inputs": [],
"outputs": [
@@ -824,8 +693,8 @@
"id": 249,
"type": "GetNode",
"pos": [
- 897.5274047851562,
- -921.2979125976562
+ 895.5455932617188,
+ -873.7318725585938
],
"size": [
210,
@@ -834,7 +703,7 @@
"flags": {
"collapsed": true
},
- "order": 14,
+ "order": 13,
"mode": 0,
"inputs": [],
"outputs": [
@@ -859,8 +728,8 @@
"id": 250,
"type": "GetNode",
"pos": [
- 895.64990234375,
- -977.6257934570312
+ 893.6680908203125,
+ -930.0597534179688
],
"size": [
210,
@@ -869,7 +738,7 @@
"flags": {
"collapsed": true
},
- "order": 15,
+ "order": 14,
"mode": 0,
"inputs": [],
"outputs": [
@@ -902,7 +771,7 @@
266
],
"flags": {},
- "order": 43,
+ "order": 46,
"mode": 0,
"inputs": [
{
@@ -980,7 +849,7 @@
"flags": {
"collapsed": true
},
- "order": 16,
+ "order": 15,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1012,7 +881,7 @@
262
],
"flags": {},
- "order": 41,
+ "order": 44,
"mode": 0,
"inputs": [
{
@@ -1078,7 +947,7 @@
"flags": {
"collapsed": true
},
- "order": 17,
+ "order": 16,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1112,7 +981,7 @@
"flags": {
"collapsed": true
},
- "order": 18,
+ "order": 17,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1144,7 +1013,7 @@
58
],
"flags": {},
- "order": 19,
+ "order": 18,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1168,77 +1037,6 @@
"color": "#1b4669",
"bgcolor": "#29699c"
},
- {
- "id": 294,
- "type": "SetNode",
- "pos": [
- 1787.0606689453125,
- -1681.1925048828125
- ],
- "size": [
- 210,
- 60
- ],
- "flags": {
- "collapsed": true
- },
- "order": 40,
- "mode": 0,
- "inputs": [
- {
- "name": "INT",
- "type": "INT",
- "link": 519
- }
- ],
- "outputs": [
- {
- "name": "INT",
- "type": "INT",
- "links": [
- 520
- ]
- }
- ],
- "title": "Set_actual_audio_frames",
- "properties": {
- "previousName": "actual_audio_frames"
- },
- "widgets_values": [
- "actual_audio_frames"
- ],
- "color": "#1b4669",
- "bgcolor": "#29699c"
- },
- {
- "id": 293,
- "type": "PreviewAny",
- "pos": [
- 1807.1619873046875,
- -1607.485107421875
- ],
- "size": [
- 210,
- 88
- ],
- "flags": {},
- "order": 42,
- "mode": 0,
- "inputs": [
- {
- "name": "source",
- "type": "*",
- "link": 520
- }
- ],
- "outputs": [],
- "properties": {
- "cnr_id": "comfy-core",
- "ver": "0.3.50",
- "Node name for S&R": "PreviewAny"
- },
- "widgets_values": []
- },
{
"id": 271,
"type": "SetNode",
@@ -1253,7 +1051,7 @@
"flags": {
"collapsed": true
},
- "order": 30,
+ "order": 34,
"mode": 0,
"inputs": [
{
@@ -1279,29 +1077,6 @@
"color": "#1b4669",
"bgcolor": "#29699c"
},
- {
- "id": 263,
- "type": "Note",
- "pos": [
- 1754.6004638671875,
- -1462.3841552734375
- ],
- "size": [
- 344.82928466796875,
- 143.7332305908203
- ],
- "flags": {},
- "order": 20,
- "mode": 0,
- "inputs": [],
- "outputs": [],
- "properties": {},
- "widgets_values": [
- "increase audio_scale for stronger effect\n\naudio_cfg is only used when sampler is using cfg as well\n\nnum_frames is the maximum frame count to generate, if the value is higher than your audio length would be, the audio length is used "
- ],
- "color": "#432",
- "bgcolor": "#653"
- },
{
"id": 122,
"type": "WanVideoModelLoader",
@@ -1314,7 +1089,7 @@
314
],
"flags": {},
- "order": 26,
+ "order": 30,
"mode": 0,
"inputs": [
{
@@ -1408,7 +1183,7 @@
202
],
"flags": {},
- "order": 21,
+ "order": 19,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1439,15 +1214,15 @@
"id": 229,
"type": "WanVideoEncode",
"pos": [
- 1707.7315673828125,
- -876.6842041015625
+ 1705.7498779296875,
+ -829.1181640625
],
"size": [
270,
242
],
"flags": {},
- "order": 36,
+ "order": 39,
"mode": 0,
"inputs": [
{
@@ -1495,15 +1270,15 @@
"id": 228,
"type": "VHS_LoadVideo",
"pos": [
- 892.2421264648438,
- -853.955810546875
+ 890.2603149414062,
+ -806.3897705078125
],
"size": [
247.455078125,
451.9747314453125
],
"flags": {},
- "order": 29,
+ "order": 33,
"mode": 0,
"inputs": [
{
@@ -1591,144 +1366,6 @@
}
}
},
- {
- "id": 291,
- "type": "GetImageSizeAndCount",
- "pos": [
- 2225.578125,
- -1042.865478515625
- ],
- "size": [
- 190.86483764648438,
- 86
- ],
- "flags": {
- "collapsed": true
- },
- "order": 39,
- "mode": 0,
- "inputs": [
- {
- "name": "image",
- "type": "IMAGE",
- "link": 540
- }
- ],
- "outputs": [
- {
- "name": "image",
- "type": "IMAGE",
- "links": [
- 542,
- 543
- ]
- },
- {
- "label": "640 width",
- "name": "width",
- "type": "INT",
- "links": [
- 516
- ]
- },
- {
- "label": "640 height",
- "name": "height",
- "type": "INT",
- "links": [
- 517
- ]
- },
- {
- "label": "1 count",
- "name": "count",
- "type": "INT",
- "links": null
- }
- ],
- "properties": {
- "cnr_id": "comfyui-kjnodes",
- "ver": "6dfd2c2420260dbb321a3412b9f1dff439a0f2e3",
- "Node name for S&R": "GetImageSizeAndCount"
- },
- "widgets_values": []
- },
- {
- "id": 125,
- "type": "LoadAudio",
- "pos": [
- 571.5848999023438,
- -1854.312744140625
- ],
- "size": [
- 404.9698791503906,
- 136
- ],
- "flags": {},
- "order": 22,
- "mode": 0,
- "inputs": [],
- "outputs": [
- {
- "name": "AUDIO",
- "type": "AUDIO",
- "links": [
- 257
- ]
- }
- ],
- "properties": {
- "cnr_id": "comfy-core",
- "ver": "0.3.41",
- "Node name for S&R": "LoadAudio"
- },
- "widgets_values": [
- "one-does-not-simply-walk-into-mordor-its-black-gates-are-guarded-by-more-than-just-orcs.mp3",
- null,
- null
- ]
- },
- {
- "id": 159,
- "type": "AudioCrop",
- "pos": [
- 711.2973022460938,
- -1629.3135986328125
- ],
- "size": [
- 270,
- 82
- ],
- "flags": {},
- "order": 31,
- "mode": 0,
- "inputs": [
- {
- "name": "audio",
- "type": "AUDIO",
- "link": 257
- }
- ],
- "outputs": [
- {
- "name": "AUDIO",
- "type": "AUDIO",
- "links": [
- 301,
- 448
- ]
- }
- ],
- "properties": {
- "cnr_id": "audio-separation-nodes-comfyui",
- "ver": "31a4567726e035097cc2d1f767767908a6fda2ea",
- "Node name for S&R": "AudioCrop"
- },
- "widgets_values": [
- "0:02",
- "2:00"
- ]
- },
{
"id": 272,
"type": "GetNode",
@@ -1743,7 +1380,7 @@
"flags": {
"collapsed": true
},
- "order": 23,
+ "order": 20,
"mode": 0,
"inputs": [],
"outputs": [
@@ -1775,7 +1412,7 @@
198
],
"flags": {},
- "order": 45,
+ "order": 48,
"mode": 0,
"inputs": [
{
@@ -1819,15 +1456,15 @@
"id": 230,
"type": "ImageResizeKJv2",
"pos": [
- 1336.364990234375,
- -852.6764526367188
+ 1334.38330078125,
+ -805.1104125976562
],
"size": [
270,
336
],
"flags": {},
- "order": 33,
+ "order": 37,
"mode": 0,
"inputs": [
{
@@ -1897,23 +1534,22 @@
"0, 0, 0",
"center",
16,
- "cpu",
- "| Output: | 97 x 640 x 640 | 454.69MB |
"
+ "cpu"
]
},
{
"id": 231,
"type": "GetImageRangeFromBatch",
"pos": [
- 1340.5838623046875,
- -1083.07763671875
+ 1338.6021728515625,
+ -1035.5115966796875
],
"size": [
340.3267517089844,
102
],
"flags": {},
- "order": 37,
+ "order": 40,
"mode": 0,
"inputs": [
{
@@ -1965,7 +1601,7 @@
86
],
"flags": {},
- "order": 46,
+ "order": 49,
"mode": 0,
"inputs": [
{
@@ -2007,7 +1643,8 @@
"cnr_id": "comfyui-kjnodes",
"ver": "6dfd2c2420260dbb321a3412b9f1dff439a0f2e3",
"Node name for S&R": "GetImageSizeAndCount"
- }
+ },
+ "widgets_values": []
},
{
"id": 301,
@@ -2023,7 +1660,7 @@
"flags": {
"collapsed": true
},
- "order": 47,
+ "order": 50,
"mode": 0,
"inputs": [
{
@@ -2080,10 +1717,10 @@
],
"size": [
725.5770263671875,
- 700.7885131835938
+ 334
],
"flags": {},
- "order": 49,
+ "order": 52,
"mode": 0,
"inputs": [
{
@@ -2162,7 +1799,7 @@
"flags": {
"collapsed": true
},
- "order": 48,
+ "order": 51,
"mode": 0,
"inputs": [
{
@@ -2209,7 +1846,7 @@
999
],
"flags": {},
- "order": 44,
+ "order": 47,
"mode": 0,
"inputs": [
{
@@ -2350,19 +1987,210 @@
true
]
},
+ {
+ "id": 125,
+ "type": "LoadAudio",
+ "pos": [
+ 534.9194946289062,
+ -1932.5986328125
+ ],
+ "size": [
+ 404.9698791503906,
+ 136
+ ],
+ "flags": {},
+ "order": 21,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "AUDIO",
+ "type": "AUDIO",
+ "links": [
+ 553
+ ]
+ }
+ ],
+ "properties": {
+ "cnr_id": "comfy-core",
+ "ver": "0.3.41",
+ "Node name for S&R": "LoadAudio"
+ },
+ "widgets_values": [
+ "one-does-not-simply-walk-into-mordor-its-black-gates-are-guarded-by-more-than-just-orcs.mp3",
+ null,
+ null
+ ]
+ },
+ {
+ "id": 291,
+ "type": "GetImageSizeAndCount",
+ "pos": [
+ 2227.56005859375,
+ -1010.1637573242188
+ ],
+ "size": [
+ 190.86483764648438,
+ 86
+ ],
+ "flags": {
+ "collapsed": true
+ },
+ "order": 42,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "image",
+ "type": "IMAGE",
+ "link": 540
+ }
+ ],
+ "outputs": [
+ {
+ "name": "image",
+ "type": "IMAGE",
+ "links": [
+ 542,
+ 543
+ ]
+ },
+ {
+ "label": "640 width",
+ "name": "width",
+ "type": "INT",
+ "links": [
+ 516
+ ]
+ },
+ {
+ "label": "640 height",
+ "name": "height",
+ "type": "INT",
+ "links": [
+ 517
+ ]
+ },
+ {
+ "label": "1 count",
+ "name": "count",
+ "type": "INT",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "comfyui-kjnodes",
+ "ver": "6dfd2c2420260dbb321a3412b9f1dff439a0f2e3",
+ "Node name for S&R": "GetImageSizeAndCount"
+ },
+ "widgets_values": []
+ },
+ {
+ "id": 263,
+ "type": "Note",
+ "pos": [
+ 1787.3021240234375,
+ -1411.845458984375
+ ],
+ "size": [
+ 344.82928466796875,
+ 143.7332305908203
+ ],
+ "flags": {},
+ "order": 22,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [],
+ "properties": {},
+ "widgets_values": [
+ "increase audio_scale for stronger effect\n\naudio_cfg is only used when sampler is using cfg as well\n\nnum_frames is the maximum frame count to generate, if the value is higher than your audio length would be, the audio length is used "
+ ],
+ "color": "#432",
+ "bgcolor": "#653"
+ },
+ {
+ "id": 293,
+ "type": "PreviewAny",
+ "pos": [
+ 1857.700927734375,
+ -1558.92822265625
+ ],
+ "size": [
+ 210,
+ 88
+ ],
+ "flags": {},
+ "order": 45,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "source",
+ "type": "*",
+ "link": 520
+ }
+ ],
+ "outputs": [],
+ "properties": {
+ "cnr_id": "comfy-core",
+ "ver": "0.3.50",
+ "Node name for S&R": "PreviewAny"
+ },
+ "widgets_values": []
+ },
+ {
+ "id": 294,
+ "type": "SetNode",
+ "pos": [
+ 1855.4366455078125,
+ -1617.7711181640625
+ ],
+ "size": [
+ 210,
+ 60
+ ],
+ "flags": {
+ "collapsed": true
+ },
+ "order": 43,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "INT",
+ "type": "INT",
+ "link": 519
+ }
+ ],
+ "outputs": [
+ {
+ "name": "INT",
+ "type": "INT",
+ "links": [
+ 520
+ ]
+ }
+ ],
+ "title": "Set_actual_audio_frames",
+ "properties": {
+ "previousName": "actual_audio_frames"
+ },
+ "widgets_values": [
+ "actual_audio_frames"
+ ],
+ "color": "#1b4669",
+ "bgcolor": "#29699c"
+ },
{
"id": 194,
"type": "MultiTalkWav2VecEmbeds",
"pos": [
- 1435.7890625,
- -1734.74169921875
+ 1495.2457275390625,
+ -1720.8681640625
],
"size": [
291.08203125,
278
],
"flags": {},
- "order": 38,
+ "order": 41,
"mode": 0,
"inputs": [
{
@@ -2373,7 +2201,7 @@
{
"name": "audio_1",
"type": "AUDIO",
- "link": 335
+ "link": 555
},
{
"name": "audio_2",
@@ -2444,25 +2272,247 @@
],
"color": "#323",
"bgcolor": "#535"
+ },
+ {
+ "id": 253,
+ "type": "SetNode",
+ "pos": [
+ 1038.5330810546875,
+ -1823.584716796875
+ ],
+ "size": [
+ 210,
+ 60
+ ],
+ "flags": {
+ "collapsed": true
+ },
+ "order": 35,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "AUDIO",
+ "type": "AUDIO",
+ "link": 553
+ }
+ ],
+ "outputs": [
+ {
+ "name": "AUDIO",
+ "type": "AUDIO",
+ "links": [
+ 554
+ ]
+ }
+ ],
+ "title": "Set_input_audio",
+ "properties": {
+ "previousName": "input_audio"
+ },
+ "widgets_values": [
+ "input_audio"
+ ],
+ "color": "#323",
+ "bgcolor": "#535"
+ },
+ {
+ "id": 304,
+ "type": "MelBandRoFormerSampler",
+ "pos": [
+ 1057.7366943359375,
+ -1683.228759765625
+ ],
+ "size": [
+ 222.73397827148438,
+ 46
+ ],
+ "flags": {},
+ "order": 38,
+ "mode": 0,
+ "inputs": [
+ {
+ "name": "model",
+ "type": "MELROFORMERMODEL",
+ "link": 552
+ },
+ {
+ "name": "audio",
+ "type": "AUDIO",
+ "link": 554
+ }
+ ],
+ "outputs": [
+ {
+ "name": "vocals",
+ "type": "AUDIO",
+ "links": [
+ 555
+ ]
+ },
+ {
+ "name": "instruments",
+ "type": "AUDIO",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-MelBandRoFormer",
+ "ver": "b68d9077815387b64d596f8c39607052b95b6eba",
+ "Node name for S&R": "MelBandRoFormerSampler"
+ },
+ "widgets_values": []
+ },
+ {
+ "id": 302,
+ "type": "MarkdownNote",
+ "pos": [
+ 554.0237426757812,
+ -1739.51611328125
+ ],
+ "size": [
+ 345.2374267578125,
+ 91.6759033203125
+ ],
+ "flags": {},
+ "order": 23,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [],
+ "title": "Wav2vec2 safetensors",
+ "properties": {},
+ "widgets_values": [
+ "Vocal separator model\n\n[https://huggingface.co/Kijai/MelBandRoFormer_comfy/tree/main](https://huggingface.co/Kijai/MelBandRoFormer_comfy/tree/main)\n\nThe model goes to `ComfyUI/models/diffusion_models`"
+ ],
+ "color": "#432",
+ "bgcolor": "#653"
+ },
+ {
+ "id": 303,
+ "type": "MelBandRoFormerModelLoader",
+ "pos": [
+ 551.90185546875,
+ -1588.5252685546875
+ ],
+ "size": [
+ 400.5706481933594,
+ 58
+ ],
+ "flags": {},
+ "order": 24,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "model",
+ "type": "MELROFORMERMODEL",
+ "links": [
+ 552
+ ]
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-MelBandRoFormer",
+ "ver": "b68d9077815387b64d596f8c39607052b95b6eba",
+ "Node name for S&R": "MelBandRoFormerModelLoader"
+ },
+ "widgets_values": [
+ "MelBandRoFormer\\MelBandRoformer_fp16.safetensors"
+ ]
+ },
+ {
+ "id": 306,
+ "type": "Wav2VecModelLoader",
+ "pos": [
+ 559.9737548828125,
+ -1339.565673828125
+ ],
+ "size": [
+ 346.9834289550781,
+ 106
+ ],
+ "flags": {},
+ "order": 25,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "wav2vec_model",
+ "type": "WAV2VECMODEL",
+ "links": null
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-WanVideoWrapper",
+ "ver": "6fce0e2d3bb976b0006bc6d8e37e1f23460938ee",
+ "Node name for S&R": "Wav2VecModelLoader"
+ },
+ "widgets_values": [
+ "wav2vec2-chinese-base_fp16.safetensors",
+ "fp16",
+ "main_device"
+ ]
+ },
+ {
+ "id": 137,
+ "type": "DownloadAndLoadWav2VecModel",
+ "pos": [
+ 565.8975830078125,
+ -1490.1480712890625
+ ],
+ "size": [
+ 330.96728515625,
+ 106
+ ],
+ "flags": {},
+ "order": 26,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [
+ {
+ "name": "wav2vec_model",
+ "type": "WAV2VECMODEL",
+ "links": [
+ 334
+ ]
+ }
+ ],
+ "properties": {
+ "cnr_id": "ComfyUI-WanVideoWrapper",
+ "ver": "058286fc0f3b0651a2f6b68309df3f06e8332cc0",
+ "Node name for S&R": "DownloadAndLoadWav2VecModel"
+ },
+ "widgets_values": [
+ "TencentGameMate/chinese-wav2vec2-base",
+ "fp16",
+ "main_device"
+ ]
+ },
+ {
+ "id": 305,
+ "type": "MarkdownNote",
+ "pos": [
+ 932.0626831054688,
+ -1364.079345703125
+ ],
+ "size": [
+ 355.3899841308594,
+ 125.51774597167969
+ ],
+ "flags": {},
+ "order": 27,
+ "mode": 0,
+ "inputs": [],
+ "outputs": [],
+ "title": "Wav2vec2 safetensors",
+ "properties": {},
+ "widgets_values": [
+ "Alternative to the download node is to use single .safetensors file from:\n\n[https://huggingface.co/Kijai/wav2vec2_safetensors/tree/main](https://huggingface.co/Kijai/wav2vec2_safetensors/tree/main)\n\nThe model goes to `ComfyUI/models/wav2vec2`"
+ ],
+ "color": "#432",
+ "bgcolor": "#653"
}
],
"links": [
- [
- 257,
- 125,
- 0,
- 159,
- 0,
- "AUDIO"
- ],
- [
- 301,
- 159,
- 0,
- 170,
- 0,
- "AUDIO"
- ],
[
334,
137,
@@ -2471,14 +2521,6 @@
0,
"WAV2VECMODEL"
],
- [
- 335,
- 170,
- 3,
- 194,
- 1,
- "AUDIO"
- ],
[
349,
138,
@@ -2623,14 +2665,6 @@
2,
"INT"
],
- [
- 448,
- 159,
- 0,
- 253,
- 0,
- "*"
- ],
[
449,
254,
@@ -2822,6 +2856,38 @@
301,
2,
"INT"
+ ],
+ [
+ 552,
+ 303,
+ 0,
+ 304,
+ 0,
+ "MELROFORMERMODEL"
+ ],
+ [
+ 553,
+ 125,
+ 0,
+ 253,
+ 0,
+ "AUDIO"
+ ],
+ [
+ 554,
+ 253,
+ 0,
+ 304,
+ 1,
+ "AUDIO"
+ ],
+ [
+ 555,
+ 304,
+ 0,
+ 194,
+ 1,
+ "AUDIO"
]
],
"groups": [
@@ -2842,8 +2908,8 @@
"id": 3,
"title": "Video2video",
"bounding": [
- 498.3595886230469,
- -1241.007080078125,
+ 496.3777770996094,
+ -1193.4410400390625,
1720.7049560546875,
926.4686889648438
],
@@ -2857,8 +2923,8 @@
"bounding": [
497.6866149902344,
-2026.6229248046875,
- 1656.1551513671875,
- 753.9797973632812
+ 1675.974365234375,
+ 813.437255859375
],
"color": "#a1309b",
"font_size": 24,
@@ -2868,13 +2934,13 @@
"config": {},
"extra": {
"ds": {
- "scale": 0.41772481694160374,
+ "scale": 0.6727499949326226,
"offset": [
- -263.000991979628,
- 2820.474862310073
+ 560.353326969467,
+ 2231.2792071769563
]
},
- "frontendVersion": "1.26.3",
+ "frontendVersion": "1.26.6",
"node_versions": {
"ComfyUI-WanVideoWrapper": "0a11c67a0c0062b534178920a0d6dcaa75e7b5fe",
"comfy-core": "0.3.43",