Files
ComfyUI/blueprints/Music Cover (YuE2).json
T

1232 lines
30 KiB
JSON

{
"revision": 0,
"last_node_id": "58",
"last_link_id": 0,
"nodes": [
{
"id": 58,
"type": "75e2923b-fcd3-4bc5-9588-451fa1c1475b",
"pos": [
920,
-270
],
"size": [
390,
450
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"label": "Style",
"name": "value",
"type": "STRING",
"widget": {
"name": "value"
},
"link": null
},
{
"label": "Lyrics",
"name": "value_1",
"type": "STRING",
"widget": {
"name": "value_1"
},
"link": null
},
{
"name": "max_duration",
"type": "FLOAT",
"widget": {
"name": "max_duration"
},
"link": null
},
{
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": null
},
{
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": null
},
{
"name": "audio",
"type": "AUDIO",
"link": null
},
{
"name": "audio_encoder_name",
"type": "COMBO",
"widget": {
"name": "audio_encoder_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": []
}
],
"properties": {
"previewExposures": [
{
"name": "$$canvas-image-preview",
"sourceNodeId": "51",
"sourcePreviewName": "$$canvas-image-preview"
}
]
},
"widgets_values": [
"",
"",
360,
0,
"yue2_3b_int8_convrot.safetensors",
"sheetsage2_bf16.safetensors"
],
"widgets_values_named": {
"value": "",
"value_1": "",
"max_duration": 360,
"seed": 0,
"ckpt_name": "yue2_3b_int8_convrot.safetensors",
"audio_encoder_name": "sheetsage2_bf16.safetensors"
},
"title": "Music Cover (YuE2)"
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "75e2923b-fcd3-4bc5-9588-451fa1c1475b",
"version": 1,
"state": {
"lastGroupId": 7,
"lastNodeId": 58,
"lastLinkId": 97,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Music Cover (YuE2)",
"inputNode": {
"id": -10,
"bounding": [
-840,
-550,
168.966796875,
188
]
},
"outputNode": {
"id": -20,
"bounding": [
2930,
-690,
128,
68
]
},
"inputs": [
{
"id": "6c1f1dc8-09bc-416e-93e6-185bdbb48f42",
"name": "value",
"type": "STRING",
"linkIds": [
95
],
"label": "Style",
"pos": [
-695.033203125,
-526
]
},
{
"id": "54203a99-fe32-452b-8bc6-fa9add883a70",
"name": "value_1",
"type": "STRING",
"linkIds": [
96
],
"label": "Lyrics",
"pos": [
-695.033203125,
-506
]
},
{
"id": "d0fcad51-9ad7-4a92-ab62-efffeb4c47a1",
"name": "max_duration",
"type": "FLOAT",
"linkIds": [
79
],
"pos": [
-695.033203125,
-486
]
},
{
"id": "42d2b2cb-be16-40f7-a6d2-95a45aefcfca",
"name": "seed",
"type": "INT",
"linkIds": [
80
],
"pos": [
-695.033203125,
-466
]
},
{
"id": "99304313-156e-4357-aab8-34fa0944f94a",
"name": "ckpt_name",
"type": "COMBO",
"linkIds": [
81
],
"pos": [
-695.033203125,
-446
]
},
{
"id": "340bc841-85e9-488c-9ba4-94906af1c45c",
"name": "audio",
"type": "AUDIO",
"linkIds": [
90
],
"pos": [
-695.033203125,
-426
]
},
{
"id": "c9f667dd-dd37-4b13-95f8-636ad9ca91d5",
"name": "audio_encoder_name",
"type": "COMBO",
"linkIds": [
91
],
"pos": [
-695.033203125,
-406
]
}
],
"outputs": [
{
"id": "0732a71d-66d1-4d9b-aae6-02256c00fab7",
"name": "AUDIO",
"type": "AUDIO",
"linkIds": [
31
],
"localized_name": "AUDIO",
"pos": [
2954,
-666
]
}
],
"widgets": [],
"nodes": [
{
"id": 47,
"type": "CheckpointLoaderSimple",
"pos": [
-230,
-1090
],
"size": [
420,
130
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "ckpt_name",
"name": "ckpt_name",
"type": "COMBO",
"widget": {
"name": "ckpt_name"
},
"link": 81
}
],
"outputs": [
{
"localized_name": "MODEL",
"name": "MODEL",
"type": "MODEL",
"links": [
18
]
},
{
"localized_name": "CLIP",
"name": "CLIP",
"type": "CLIP",
"links": [
43
]
},
{
"localized_name": "VAE",
"name": "VAE",
"type": "VAE",
"links": [
21
]
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple",
"models": [
{
"name": "yue2_3b_int8_convrot.safetensors",
"url": "https://huggingface.co/Comfy-Org/YuE2/resolve/main/checkpoints/yue2_3b_int8_convrot.safetensors",
"directory": "checkpoints"
}
]
},
"widgets_values": [
"yue2_3b_int8_convrot.safetensors"
],
"widgets_values_named": {
"ckpt_name": "yue2_3b_int8_convrot.safetensors"
}
},
{
"id": 48,
"type": "YuE2GenerateMusic",
"pos": [
650,
-890
],
"size": [
400,
410
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "clip",
"name": "clip",
"type": "CLIP",
"link": 43
},
{
"localized_name": "style",
"name": "style",
"type": "STRING",
"widget": {
"name": "style"
},
"link": 95
},
{
"localized_name": "lyrics",
"name": "lyrics",
"type": "STRING",
"widget": {
"name": "lyrics"
},
"link": 96
},
{
"localized_name": "abc",
"name": "abc",
"type": "STRING",
"widget": {
"name": "abc"
},
"link": 94
},
{
"localized_name": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": 68
},
{
"localized_name": "mode",
"name": "mode",
"type": "COMBO",
"widget": {
"name": "mode"
},
"link": null
},
{
"localized_name": "max_duration",
"name": "max_duration",
"type": "FLOAT",
"widget": {
"name": "max_duration"
},
"link": 79
},
{
"localized_name": "temperature",
"name": "temperature",
"type": "FLOAT",
"widget": {
"name": "temperature"
},
"link": null
},
{
"localized_name": "top_p",
"name": "top_p",
"type": "FLOAT",
"widget": {
"name": "top_p"
},
"link": null
},
{
"localized_name": "top_k",
"name": "top_k",
"type": "INT",
"widget": {
"name": "top_k"
},
"link": null
},
{
"localized_name": "repetition_penalty",
"name": "repetition_penalty",
"type": "FLOAT",
"widget": {
"name": "repetition_penalty"
},
"link": null
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
49,
50
]
},
{
"localized_name": "seconds",
"name": "seconds",
"type": "FLOAT",
"links": [
48,
51
]
}
],
"properties": {
"Node name for S&R": "YuE2GenerateMusic"
},
"widgets_values": [
"",
"",
"",
530976807293994,
"randomize",
"melody",
360,
1,
0.95,
100,
1.2
],
"widgets_values_named": {
"style": "",
"lyrics": "",
"abc": "",
"seed": 530976807293994,
"control_after_generate": "randomize",
"mode": "melody",
"max_duration": 360,
"temperature": 1,
"top_p": 0.95,
"top_k": 100,
"repetition_penalty": 1.2
}
},
{
"id": 49,
"type": "ConditioningZeroOut",
"pos": [
1150,
-870
],
"size": [
230,
60
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "conditioning",
"name": "conditioning",
"type": "CONDITIONING",
"link": 50
}
],
"outputs": [
{
"localized_name": "CONDITIONING",
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
26
]
}
],
"properties": {
"Node name for S&R": "ConditioningZeroOut"
}
},
{
"id": 50,
"type": "PreviewAny",
"pos": [
1150,
-750
],
"size": [
270,
170
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "source",
"name": "source",
"type": "*",
"link": 51
}
],
"outputs": [
{
"localized_name": "STRING",
"name": "STRING",
"type": "STRING",
"links": null
}
],
"properties": {
"Node name for S&R": "PreviewAny"
},
"widgets_values": [],
"widgets_values_named": {}
},
{
"id": 51,
"type": "KSampler",
"pos": [
1680,
-940
],
"size": [
330,
290
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"localized_name": "model",
"name": "model",
"type": "MODEL",
"link": 18
},
{
"localized_name": "positive",
"name": "positive",
"type": "CONDITIONING",
"link": 49
},
{
"localized_name": "negative",
"name": "negative",
"type": "CONDITIONING",
"link": 26
},
{
"localized_name": "latent_image",
"name": "latent_image",
"type": "LATENT",
"link": 8
},
{
"localized_name": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": 69
},
{
"localized_name": "steps",
"name": "steps",
"type": "INT",
"widget": {
"name": "steps"
},
"link": null
},
{
"localized_name": "cfg",
"name": "cfg",
"type": "FLOAT",
"widget": {
"name": "cfg"
},
"link": null
},
{
"localized_name": "sampler_name",
"name": "sampler_name",
"type": "COMBO",
"widget": {
"name": "sampler_name"
},
"link": null
},
{
"localized_name": "scheduler",
"name": "scheduler",
"type": "COMBO",
"widget": {
"name": "scheduler"
},
"link": null
},
{
"localized_name": "denoise",
"name": "denoise",
"type": "FLOAT",
"widget": {
"name": "denoise"
},
"link": null
}
],
"outputs": [
{
"localized_name": "LATENT",
"name": "LATENT",
"type": "LATENT",
"links": [
9
]
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
42,
"fixed",
32,
1,
"dpm_2",
"sgm_uniform",
1
],
"widgets_values_named": {
"seed": 42,
"control_after_generate": "fixed",
"steps": 32,
"cfg": 1,
"sampler_name": "dpm_2",
"scheduler": "sgm_uniform",
"denoise": 1
}
},
{
"id": 52,
"type": "EmptyYuE2LatentAudio",
"pos": [
1890,
-470
],
"size": [
230,
120
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"localized_name": "seconds",
"name": "seconds",
"type": "FLOAT",
"widget": {
"name": "seconds"
},
"link": 48
},
{
"localized_name": "batch_size",
"name": "batch_size",
"type": "INT",
"widget": {
"name": "batch_size"
},
"link": null
}
],
"outputs": [
{
"localized_name": "LATENT",
"name": "LATENT",
"type": "LATENT",
"links": [
8
]
}
],
"properties": {
"Node name for S&R": "EmptyYuE2LatentAudio"
},
"widgets_values": [
120,
1
],
"widgets_values_named": {
"seconds": 120,
"batch_size": 1
},
"color": "#323",
"bgcolor": "#535"
},
{
"id": 53,
"type": "VAEDecodeAudio",
"pos": [
2060,
-860
],
"size": [
230,
80
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"localized_name": "samples",
"name": "samples",
"type": "LATENT",
"link": 9
},
{
"localized_name": "vae",
"name": "vae",
"type": "VAE",
"link": 21
}
],
"outputs": [
{
"localized_name": "AUDIO",
"name": "AUDIO",
"type": "AUDIO",
"links": [
31
]
}
],
"properties": {
"Node name for S&R": "VAEDecodeAudio"
}
},
{
"id": 54,
"type": "SeedNode",
"pos": [
730,
-410
],
"size": [
270,
90
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"localized_name": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": 80
}
],
"outputs": [
{
"localized_name": "seed",
"name": "seed",
"type": "INT",
"links": [
68,
69
]
}
],
"properties": {
"Node name for S&R": "SeedNode"
},
"widgets_values": [
0,
"randomize"
],
"widgets_values_named": {
"seed": 0,
"fixed": "randomize"
}
},
{
"id": 55,
"type": "SheetSage2AudioToABC",
"pos": [
-150,
-650
],
"size": [
230,
110
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"localized_name": "audio_encoder",
"name": "audio_encoder",
"type": "AUDIO_ENCODER",
"link": 84
},
{
"localized_name": "audio",
"name": "audio",
"type": "AUDIO",
"link": 90
},
{
"localized_name": "mode",
"name": "mode",
"type": "COMBO",
"widget": {
"name": "mode"
},
"link": null
}
],
"outputs": [
{
"localized_name": "abc",
"name": "abc",
"shape": 6,
"type": "STRING",
"links": [
93
]
}
],
"properties": {
"Node name for S&R": "SheetSage2AudioToABC"
},
"widgets_values": [
"melody"
],
"widgets_values_named": {
"mode": "melody"
}
},
{
"id": 56,
"type": "AudioEncoderLoader",
"pos": [
-240,
-920
],
"size": [
420,
90
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"localized_name": "audio_encoder_name",
"name": "audio_encoder_name",
"type": "COMBO",
"widget": {
"name": "audio_encoder_name"
},
"link": 91
}
],
"outputs": [
{
"localized_name": "AUDIO_ENCODER",
"name": "AUDIO_ENCODER",
"type": "AUDIO_ENCODER",
"links": [
84
]
}
],
"properties": {
"Node name for S&R": "AudioEncoderLoader",
"models": [
{
"name": "sheetsage2_bf16.safetensors",
"url": "https://huggingface.co/Comfy-Org/YuE2/resolve/main/audio_encoders/sheetsage2_bf16.safetensors",
"directory": "audio_encoders"
}
]
},
"widgets_values": [
"sheetsage2_bf16.safetensors"
],
"widgets_values_named": {
"audio_encoder_name": "sheetsage2_bf16.safetensors"
}
},
{
"id": 57,
"type": "PreviewAny",
"pos": [
-250,
-500
],
"size": [
470,
300
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"localized_name": "source",
"name": "source",
"type": "*",
"link": 93
}
],
"outputs": [
{
"localized_name": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
94
]
}
],
"properties": {
"Node name for S&R": "PreviewAny"
},
"widgets_values": [],
"widgets_values_named": {}
}
],
"groups": [
{
"id": 3,
"title": "Model",
"bounding": [
-330,
-1180,
620,
430
],
"color": "#3f789e",
"flags": {}
},
{
"id": 2,
"title": "ABC",
"bounding": [
-330,
-730,
620,
560
],
"color": "#3f789e",
"flags": {}
},
{
"id": 6,
"title": "Conditioning",
"bounding": [
390,
-1080,
1160,
790
],
"color": "#3f789e",
"flags": {}
},
{
"id": 4,
"title": "Duration",
"bounding": [
1640,
-570,
720,
280
],
"color": "#3f789e",
"flags": {}
},
{
"id": 5,
"title": "Sampling & Decode",
"bounding": [
1640,
-1080,
720,
480
],
"color": "#3f789e",
"flags": {}
}
],
"links": [
{
"id": 43,
"origin_id": 47,
"origin_slot": 1,
"target_id": 48,
"target_slot": 0,
"type": "CLIP"
},
{
"id": 50,
"origin_id": 48,
"origin_slot": 0,
"target_id": 49,
"target_slot": 0,
"type": "CONDITIONING"
},
{
"id": 51,
"origin_id": 48,
"origin_slot": 1,
"target_id": 50,
"target_slot": 0,
"type": "FLOAT"
},
{
"id": 18,
"origin_id": 47,
"origin_slot": 0,
"target_id": 51,
"target_slot": 0,
"type": "MODEL"
},
{
"id": 49,
"origin_id": 48,
"origin_slot": 0,
"target_id": 51,
"target_slot": 1,
"type": "CONDITIONING"
},
{
"id": 26,
"origin_id": 49,
"origin_slot": 0,
"target_id": 51,
"target_slot": 2,
"type": "CONDITIONING"
},
{
"id": 8,
"origin_id": 52,
"origin_slot": 0,
"target_id": 51,
"target_slot": 3,
"type": "LATENT"
},
{
"id": 48,
"origin_id": 48,
"origin_slot": 1,
"target_id": 52,
"target_slot": 0,
"type": "FLOAT"
},
{
"id": 9,
"origin_id": 51,
"origin_slot": 0,
"target_id": 53,
"target_slot": 0,
"type": "LATENT"
},
{
"id": 21,
"origin_id": 47,
"origin_slot": 2,
"target_id": 53,
"target_slot": 1,
"type": "VAE"
},
{
"id": 31,
"origin_id": 53,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "AUDIO"
},
{
"id": 68,
"origin_id": 54,
"origin_slot": 0,
"target_id": 48,
"target_slot": 4,
"type": "INT"
},
{
"id": 69,
"origin_id": 54,
"origin_slot": 0,
"target_id": 51,
"target_slot": 4,
"type": "INT"
},
{
"id": 79,
"origin_id": -10,
"origin_slot": 2,
"target_id": 48,
"target_slot": 6,
"type": "FLOAT"
},
{
"id": 80,
"origin_id": -10,
"origin_slot": 3,
"target_id": 54,
"target_slot": 0,
"type": "INT"
},
{
"id": 81,
"origin_id": -10,
"origin_slot": 4,
"target_id": 47,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 84,
"origin_id": 56,
"origin_slot": 0,
"target_id": 55,
"target_slot": 0,
"type": "AUDIO_ENCODER"
},
{
"id": 90,
"origin_id": -10,
"origin_slot": 5,
"target_id": 55,
"target_slot": 1,
"type": "AUDIO"
},
{
"id": 91,
"origin_id": -10,
"origin_slot": 6,
"target_id": 56,
"target_slot": 0,
"type": "COMBO"
},
{
"id": 93,
"origin_id": 55,
"origin_slot": 0,
"target_id": 57,
"target_slot": 0,
"type": "STRING"
},
{
"id": 94,
"origin_id": 57,
"origin_slot": 0,
"target_id": 48,
"target_slot": 3,
"type": "STRING"
},
{
"id": 95,
"origin_id": -10,
"origin_slot": 0,
"target_id": 48,
"target_slot": 1,
"type": "STRING"
},
{
"id": 96,
"origin_id": -10,
"origin_slot": 1,
"target_id": 48,
"target_slot": 2,
"type": "STRING"
}
],
"extra": {},
"category": "Audio/Music generation",
"description": "Creates a new version of a song from reference audio using YuE2, preserving melody while changing style, vocals, lyrics, and arrangement."
}
]
},
"extra": {}
}