ComfyPilotComfyPilot
工作流 / 音频 / YuE2：音乐翻唱
YuE2：音乐翻唱

YuE2：音乐翻唱

YuE2: Music Cover

使用 YuE2 从参考音频创建歌曲的新版本。在改变音乐风格、人声、歌词和编曲的同时，保留原始旋律。

音频 4 个节点 1 个输入 22 次使用 ComfyUI ≥ 0.36.0 ComfyUI 39 KB

下载工作流 JSON 查看官方来源

下载后把文件拖进 ComfyUI 窗口即可打开。

需要的权重

这个工作流引用了 2 个权重文件，其中 2 个能在本站模型库里找到。

sheetsage2_bf16.safetensors 在模型库查看
yue2_3b_int8_convrot.safetensors 在模型库查看

节点构成

SaveAudioAdvanced × 1
59dddde1-2d83-4b6e-9c71-1e5cb2d823d6 × 1
LoadAudio × 1
MarkdownNote × 1

官方标注的模型

YuE2

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
2 "id": "8946c283-b05c-4bea-84dc-f0ea169054c6",
3 "revision": 0,
4 "last_node_id": 46,
5 "last_link_id": 97,
6 "nodes": [
7 {
8 "id": 10,
9 "type": "SaveAudioAdvanced",
10 "pos": [
11 1880,
12 -260
13 ],
14 "size": [
15 850,
16 140
17 ],
18 "flags": [],
19 "order": 3,
20 "mode": 0,
21 "inputs": [
22 {
23 "name": "audio",
24 "type": "AUDIO",
25 "link": 63
26 }
27 ],
28 "outputs": [
29 {
30 "name": "audio",
31 "type": "AUDIO",
32 "links": []
33 }
34 ],
35 "properties": {
36 "Node name for S&R": "SaveAudioAdvanced"
37 },
38 "widgets_values": [
39 "audio/YuE2_cover",
40 "flac"
41 ],
42 "widgets_values_named": {
43 "filename_prefix": "audio/YuE2_cover",
44 "format": "flac"
45 }
46 },
47 {
48 "id": 33,
49 "type": "59dddde1-2d83-4b6e-9c71-1e5cb2d823d6",
50 "pos": [
51 1440,
52 -260
53 ],
54 "size": [
55 390,
56 450
57 ],
58 "flags": [],
59 "order": 2,
60 "mode": 0,
61 "inputs": [
62 {
63 "label": "Style",
64 "name": "value",
65 "type": "STRING",
66 "widget": {
67 "name": "value"
68 },
69 "link": null
70 },
71 {
72 "label": "Lyrics",
73 "name": "value_1",
74 "type": "STRING",
75 "widget": {
76 "name": "value_1"
77 },
78 "link": null
79 },
80 {
81 "name": "audio",
82 "type": "AUDIO",
83 "link": 97
84 }
85 ],
86 "outputs": [
87 {
88 "name": "AUDIO",
89 "type": "AUDIO",
90 "links": [
91 63
92 ]
93 }
94 ],
95 "properties": {
96 "previewExposures": [
97 {
98 "name": "$$canvas-image-preview",
99 "sourceNodeId": "8",
100 "sourcePreviewName": "$$canvas-image-preview"
101 }
102 ]
103 },
104 "widgets_values": [
105 "English, soulful jazz-pop, expressive male vocal, relaxed 88 BPM, Rhodes piano, upright bass, brushed drums, warm saxophone, subtle strings, intimate late-night atmosphere, rich and organic live-band production",
106 "[Verse]\nStreetlights shimmer on the pavement\nMidnight breathing soft and slow\nEvery corner holds a memory\nOf the places we used to know\n\n[Chorus]\nStay with me until the morning\nLet the city fade away\nWe don't need to chase tomorrow\nAll I need is here today\n\n[Verse]\nOld café beneath the neon\nRain is falling on the glass\nEvery song becomes a story\nEvery moment moves too fast\n\n[Chorus]\nStay with me until the morning\nLet the city fade away\nWe don't need to chase tomorrow\nAll I need is here today\n\n[Bridge]\nMaybe time will keep on turning\nMaybe everything will change\nBut tonight the music holds us\nLike a fire inside the rain\n\n[Chorus]\nStay with me until the morning\nLet the city fade away\nWe don't need to chase tomorrow\nAll I need is here today",
107 360,
108 0,
109 "yue2_3b_int8_convrot.safetensors",
110 "sheetsage2_bf16.safetensors"
111 ],
112 "widgets_values_named": {
113 "value": "English, soulful jazz-pop, expressive male vocal, relaxed 88 BPM, Rhodes piano, upright bass, brushed drums, warm saxophone, subtle strings, intimate late-night atmosphere, rich and organic live-band production",
114 "value_1": "[Verse]\nStreetlights shimmer on the pavement\nMidnight breathing soft and slow\nEvery corner holds a memory\nOf the places we used to know\n\n[Chorus]\nStay with me until the morning\nLet the city fade away\nWe don't need to chase tomorrow\nAll I need is here today\n\n[Verse]\nOld café beneath the neon\nRain is falling on the glass\nEvery song becomes a story\nEvery moment moves too fast\n\n[Chorus]\nStay with me until the morning\nLet the city fade away\nWe don't need to chase tomorrow\nAll I need is here today\n\n[Bridge]\nMaybe time will keep on turning\nMaybe everything will change\nBut tonight the music holds us\nLike a fire inside the rain\n\n[Chorus]\nStay with me until the morning\nLet the city fade away\nWe don't need to chase tomorrow\nAll I need is here today",
115 "max_duration": 360,
116 "seed": 0,
117 "ckpt_name": "yue2_3b_int8_convrot.safetensors",
118 "audio_encoder_name": "sheetsage2_bf16.safetensors"
119 }
120 },
121 {
122 "id": 45,
123 "type": "LoadAudio",
124 "pos": [
125 800,
126 -260
127 ],
128 "size": [
129 590,
130 140
131 ],
132 "flags": [],
133 "order": 0,
134 "mode": 0,
135 "inputs": [],
136 "outputs": [
137 {
138 "name": "AUDIO",
139 "type": "AUDIO",
140 "links": [
141 97
142 ]
143 }
144 ],
145 "properties": {
146 "Node name for S&R": "LoadAudio"
147 },
148 "widgets_values": [
149 "yue2_reference_song.flac",
150 null,
151 null
152 ],
153 "widgets_values_named": {
154 "audio": "yue2_reference_song.flac",
155 "upload": null
156 }
157 },
158 {
159 "id": 46,
160 "type": "MarkdownNote",
161 "pos": [
162 220,
163 -260
164 ],
165 "size": [
166 550,
167 1906.640625
168 ],
169 "flags": [],
170 "order": 1,
171 "mode": 0,
172 "inputs": [],
173 "outputs": [],
174 "properties": [],
175 "widgets_values": [
176 "# YuE2: Music Cover\n\nCreate a new version of an existing song with YuE2.\n\nThis workflow uses **SheetSage2** to transcribe the melody from the reference audio into an editable ABC score, then uses YuE2 to regenerate the song with a new **Style** and **Lyrics**.\n\n## Input Asset\n\n- [yue2_reference_song.flac](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/yue2_reference_song.flac)\n\n## Model Links\n\n- [Hugging Face:Comfy-Org/YuE2](https://huggingface.co/Comfy-Org/YuE2)\n- [ModelScope:Comfy-Org/YuE2](https://modelscope.cn/models/Comfy-Org/YuE2)\n\n**checkpoints**\n\n- [yue2_3b_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/YuE2/resolve/main/checkpoints/yue2_3b_int8_convrot.safetensors) (3.69 GB)\n\n**audio_encoders**\n\n- [sheetsage2_bf16.safetensors](https://huggingface.co/Comfy-Org/YuE2/resolve/main/audio_encoders/sheetsage2_bf16.safetensors) (1.29 GB)\n\n\n## Model Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 checkpoints/\n│ │ └── yue2_3b_int8_convrot.safetensors\n│ └── 📂 audio_encoders/\n│ └── sheetsage2_bf16.safetensors\n```\n\n## How to Use\n\n[Subgraph](https://docs.comfy.org/interface/features/subgraph)\n\n1. Load a reference song in **Audio**.\n2. Describe the new musical direction in **Style**.\n3. Enter the lyrics you want to sing in **Lyrics**.\n4. Run the workflow to generate a new cover version.\n\nThe reference audio provides the melody, while YuE2 creates a new performance and arrangement based on your Style and Lyrics.\n\n## Writing the Style\n\nDescribe the target musical style clearly.\n\nUseful elements include:\n\n- **Genre:** jazz, pop, rock, folk, electronic\n- **Vocals:** warm male vocal, expressive female vocal, soft vocals\n- **Language:** English, Chinese, Japanese, etc.\n- **Tempo:** 90 BPM, slow, upbeat\n- **Instruments:** piano, guitar, bass, drums, strings, synths\n- **Mood:** intimate, energetic, nostalgic, cinematic\n\nExample:\n\n> English, soulful jazz-pop, expressive male vocal, relaxed 88 BPM, Rhodes piano, upright bass, brushed drums, warm saxophone, intimate late-night atmosphere\n\n## Writing Lyrics\n\nUse section tags such as:\n\n [Verse]\n Streetlights shimmer on the pavement\n Midnight breathing soft and slow\n\n [Chorus]\n Stay with me until the morning\n Let the city fade away\n\nYou can use:\n\n`[Verse]` · `[Chorus]` · `[Bridge]` · `[Outro]`\n\nFor better melody matching, keep the new lyrics reasonably close to the original phrasing and syllable count.\n\n## How the Cover Works\n\nThe workflow does not directly use the reference audio as YuE2 conditioning.\n\nInstead:\n\n Reference Audio\n ↓\n SheetSage2\n ↓\n Melody ABC\n ↓\n YuE2 + Style + Lyrics\n ↓\n New Cover Audio\n\nSheetSage2 converts the source recording into a symbolic melody representation. YuE2 then uses that melody as the musical plan for the new cover.\n\n## Tips\n\n- Keep **Style** focused on the target sound, not the original sound.\n- Use **melody-only** planning for most cover tasks.\n- Changing the Style can create a very different arrangement while preserving the melody.\n- Lyrics can be changed, but similar phrasing and syllable counts usually fit the original melody better.\n- For a simple style-transfer test, keep the original lyrics and only change the Style.\n- For a stronger reinterpretation, change both the Style and Lyrics.\n\n## Learn More\n\n- [YuE2 Cover Guide](https://github.com/multimodal-art-projection/YuE/blob/main/docs/covers.md)\n- [YuE2 Music Skill](https://github.com/multimodal-art-projection/YuE/blob/main/skills/yue2-music/SKILL.md)\n- [Generation & Covers Reference](https://github.com/multimodal-art-projection/YuE/blob/main/skills/yue2-music/references/generation-and-covers.md)\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
177 ],
178 "widgets_values_named": {
179 "text": "# YuE2: Music Cover\n\nCreate a new version of an existing song with YuE2.\n\nThis workflow uses **SheetSage2** to transcribe the melody from the reference audio into an editable ABC score, then uses YuE2 to regenerate the song with a new **Style** and **Lyrics**.\n\n## Input Asset\n\n- [yue2_reference_song.flac](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/yue2_reference_song.flac)\n\n## Model Links\n\n- [Hugging Face:Comfy-Org/YuE2](https://huggingface.co/Comfy-Org/YuE2)\n- [ModelScope:Comfy-Org/YuE2](https://modelscope.cn/models/Comfy-Org/YuE2)\n\n**checkpoints**\n\n- [yue2_3b_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/YuE2/resolve/main/checkpoints/yue2_3b_int8_convrot.safetensors) (3.69 GB)\n\n**audio_encoders**\n\n- [sheetsage2_bf16.safetensors](https://huggingface.co/Comfy-Org/YuE2/resolve/main/audio_encoders/sheetsage2_bf16.safetensors) (1.29 GB)\n\n\n## Model Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 checkpoints/\n│ │ └── yue2_3b_int8_convrot.safetensors\n│ └── 📂 audio_encoders/\n│ └── sheetsage2_bf16.safetensors\n```\n\n## How to Use\n\n[Subgraph](https://docs.comfy.org/interface/features/subgraph)\n\n1. Load a reference song in **Audio**.\n2. Describe the new musical direction in **Style**.\n3. Enter the lyrics you want to sing in **Lyrics**.\n4. Run the workflow to generate a new cover version.\n\nThe reference audio provides the melody, while YuE2 creates a new performance and arrangement based on your Style and Lyrics.\n\n## Writing the Style\n\nDescribe the target musical style clearly.\n\nUseful elements include:\n\n- **Genre:** jazz, pop, rock, folk, electronic\n- **Vocals:** warm male vocal, expressive female vocal, soft vocals\n- **Language:** English, Chinese, Japanese, etc.\n- **Tempo:** 90 BPM, slow, upbeat\n- **Instruments:** piano, guitar, bass, drums, strings, synths\n- **Mood:** intimate, energetic, nostalgic, cinematic\n\nExample:\n\n> English, soulful jazz-pop, expressive male vocal, relaxed 88 BPM, Rhodes piano, upright bass, brushed drums, warm saxophone, intimate late-night atmosphere\n\n## Writing Lyrics\n\nUse section tags such as:\n\n [Verse]\n Streetlights shimmer on the pavement\n Midnight breathing soft and slow\n\n [Chorus]\n Stay with me until the morning\n Let the city fade away\n\nYou can use:\n\n`[Verse]` · `[Chorus]` · `[Bridge]` · `[Outro]`\n\nFor better melody matching, keep the new lyrics reasonably close to the original phrasing and syllable count.\n\n## How the Cover Works\n\nThe workflow does not directly use the reference audio as YuE2 conditioning.\n\nInstead:\n\n Reference Audio\n ↓\n SheetSage2\n ↓\n Melody ABC\n ↓\n YuE2 + Style + Lyrics\n ↓\n New Cover Audio\n\nSheetSage2 converts the source recording into a symbolic melody representation. YuE2 then uses that melody as the musical plan for the new cover.\n\n## Tips\n\n- Keep **Style** focused on the target sound, not the original sound.\n- Use **melody-only** planning for most cover tasks.\n- Changing the Style can create a very different arrangement while preserving the melody.\n- Lyrics can be changed, but similar phrasing and syllable counts usually fit the original melody better.\n- For a simple style-transfer test, keep the original lyrics and only change the Style.\n- For a stronger reinterpretation, change both the Style and Lyrics.\n\n## Learn More\n\n- [YuE2 Cover Guide](https://github.com/multimodal-art-projection/YuE/blob/main/docs/covers.md)\n- [YuE2 Music Skill](https://github.com/multimodal-art-projection/YuE/blob/main/skills/yue2-music/SKILL.md)\n- [Generation & Covers Reference](https://github.com/multimodal-art-projection/YuE/blob/main/skills/yue2-music/references/generation-and-covers.md)\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
180 },
181 "color": "#222",
182 "bgcolor": "#000"
183 }
184 ],
185 "links": [
186 [
187 63,
188 33,
189 0,
190 10,
191 0,
192 "AUDIO"
193 ],
194 [
195 97,
196 45,
197 0,
198 33,
199 2,
200 "AUDIO"
201 ]
202 ],
203 "groups": [],
204 "definitions": {
205 "subgraphs": [
206 {
207 "id": "59dddde1-2d83-4b6e-9c71-1e5cb2d823d6",
208 "version": 1,
209 "state": {
210 "lastGroupId": 7,
211 "lastNodeId": 46,
212 "lastLinkId": 97,
213 "lastRerouteId": 0
214 },
215 "revision": 0,
216 "config": [],
217 "name": "Music Cover (YuE2)",
218 "inputNode": {
219 "id": -10,
220 "bounding": [
221 -840,
222 -550,
223 168.966796875,
224 188
225 ]
226 },
227 "outputNode": {
228 "id": -20,
229 "bounding": [
230 2930,
231 -690,
232 128,
233 68
234 ]
235 },
236 "inputs": [
237 {
238 "id": "6c1f1dc8-09bc-416e-93e6-185bdbb48f42",
239 "name": "value",
240 "type": "STRING",
241 "linkIds": [
242 95
243 ],
244 "label": "Style",
245 "pos": [
246 -695.033203125,
247 -526
248 ]
249 },
250 {
251 "id": "54203a99-fe32-452b-8bc6-fa9add883a70",
252 "name": "value_1",
253 "type": "STRING",
254 "linkIds": [
255 96
256 ],
257 "label": "Lyrics",
258 "pos": [
259 -695.033203125,
260 -506
261 ]
262 },
263 {
264 "id": "d0fcad51-9ad7-4a92-ab62-efffeb4c47a1",
265 "name": "max_duration",
266 "type": "FLOAT",
267 "linkIds": [
268 79
269 ],
270 "pos": [
271 -695.033203125,
272 -486
273 ]
274 },
275 {
276 "id": "42d2b2cb-be16-40f7-a6d2-95a45aefcfca",
277 "name": "seed",
278 "type": "INT",
279 "linkIds": [
280 80
281 ],
282 "pos": [
283 -695.033203125,
284 -466
285 ]
286 },
287 {
288 "id": "99304313-156e-4357-aab8-34fa0944f94a",
289 "name": "ckpt_name",
290 "type": "COMBO",
291 "linkIds": [
292 81
293 ],
294 "pos": [
295 -695.033203125,
296 -446
297 ]
298 },
299 {
300 "id": "340bc841-85e9-488c-9ba4-94906af1c45c",
301 "name": "audio",
302 "type": "AUDIO",
303 "linkIds": [
304 90
305 ],
306 "pos": [
307 -695.033203125,
308 -426
309 ]
310 },
311 {
312 "id": "c9f667dd-dd37-4b13-95f8-636ad9ca91d5",
313 "name": "audio_encoder_name",
314 "type": "COMBO",
315 "linkIds": [
316 91
317 ],
318 "pos": [
319 -695.033203125,
320 -406
321 ]
322 }
323 ],
324 "outputs": [
325 {
326 "id": "0732a71d-66d1-4d9b-aae6-02256c00fab7",
327 "name": "AUDIO",
328 "type": "AUDIO",
329 "linkIds": [
330 31
331 ],
332 "localized_name": "AUDIO",
333 "pos": [
334 2954,
335 -666
336 ]
337 }
338 ],
339 "widgets": [],
340 "nodes": [
341 {
342 "id": 15,
343 "type": "CheckpointLoaderSimple",
344 "pos": [
345 -230,
346 -1090
347 ],
348 "size": [
349 420,
350 110
351 ],
352 "flags": [],
353 "order": 3,
354 "mode": 0,
355 "inputs": [
356 {
357 "localized_name": "ckpt_name",
358 "name": "ckpt_name",
359 "type": "COMBO",
360 "widget": {
361 "name": "ckpt_name"
362 },
363 "link": 81
364 }
365 ],
366 "outputs": [
367 {
368 "localized_name": "MODEL",
369 "name": "MODEL",
370 "type": "MODEL",
371 "links": [
372 18
373 ]
374 },
375 {
376 "localized_name": "CLIP",
377 "name": "CLIP",
378 "type": "CLIP",
379 "links": [
380 43
381 ]
382 },
383 {
384 "localized_name": "VAE",
385 "name": "VAE",
386 "type": "VAE",
387 "links": [
388 21
389 ]
390 }
391 ],
392 "properties": {
393 "Node name for S&R": "CheckpointLoaderSimple",
394 "models": [
395 {
396 "name": "yue2_3b_int8_convrot.safetensors",
397 "url": "https://huggingface.co/Comfy-Org/YuE2/resolve/main/checkpoints/yue2_3b_int8_convrot.safetensors",
398 "directory": "checkpoints"
399 }
400 ]
401 },
402 "widgets_values": [
403 "yue2_3b_int8_convrot.safetensors"
404 ],
405 "widgets_values_named": {
406 "ckpt_name": "yue2_3b_int8_convrot.safetensors"
407 }
408 },
409 {
410 "id": 25,
411 "type": "YuE2GenerateMusic",
412 "pos": [
413 650,
414 -890
415 ],
416 "size": [
417 400,
418 410
419 ],
420 "flags": [],
421 "order": 6,
422 "mode": 0,
423 "inputs": [
424 {
425 "localized_name": "clip",
426 "name": "clip",
427 "type": "CLIP",
428 "link": 43
429 },
430 {
431 "localized_name": "style",
432 "name": "style",
433 "type": "STRING",
434 "widget": {
435 "name": "style"
436 },
437 "link": 95
438 },
439 {
440 "localized_name": "lyrics",
441 "name": "lyrics",
442 "type": "STRING",
443 "widget": {
444 "name": "lyrics"
445 },
446 "link": 96
447 },
448 {
449 "localized_name": "abc",
450 "name": "abc",
451 "type": "STRING",
452 "widget": {
453 "name": "abc"
454 },
455 "link": 94
456 },
457 {
458 "localized_name": "seed",
459 "name": "seed",
460 "type": "INT",
461 "widget": {
462 "name": "seed"
463 },
464 "link": 68
465 },
466 {
467 "localized_name": "max_duration",
468 "name": "max_duration",
469 "type": "FLOAT",
470 "widget": {
471 "name": "max_duration"
472 },
473 "link": 79
474 }
475 ],
476 "outputs": [
477 {
478 "localized_name": "CONDITIONING",
479 "name": "CONDITIONING",
480 "type": "CONDITIONING",
481 "links": [
482 49,
483 50
484 ]
485 },
486 {
487 "localized_name": "seconds",
488 "name": "seconds",
489 "type": "FLOAT",
490 "links": [
491 48,
492 51
493 ]
494 }
495 ],
496 "properties": {
497 "Node name for S&R": "YuE2GenerateMusic"
498 },
499 "widgets_values": [
500 "",
501 "",
502 "",
503 530976807293994,
504 "randomize",
505 "melody",
506 360,
507 1,
508 0.95,
509 100,
510 1.2
511 ],
512 "widgets_values_named": {
513 "style": "",
514 "lyrics": "",
515 "abc": "",
516 "seed": 530976807293994,
517 "control_after_generate": "randomize",
518 "mode": "melody",
519 "max_duration": 360,
520 "temperature": 1,
521 "top_p": 0.95,
522 "top_k": 100,
523 "repetition_penalty": 1.2
524 }
525 },
526 {
527 "id": 18,
528 "type": "ConditioningZeroOut",
529 "pos": [
530 1150,
531 -870
532 ],
533 "size": [
534 230,
535 40
536 ],
537 "flags": [],
538 "order": 4,
539 "mode": 0,
540 "inputs": [
541 {
542 "localized_name": "conditioning",
543 "name": "conditioning",
544 "type": "CONDITIONING",
545 "link": 50
546 }
547 ],
548 "outputs": [
549 {
550 "localized_name": "CONDITIONING",
551 "name": "CONDITIONING",
552 "type": "CONDITIONING",
553 "links": [
554 26
555 ]
556 }
557 ],
558 "properties": {
559 "Node name for S&R": "ConditioningZeroOut"
560 }
561 },
562 {
563 "id": 23,
564 "type": "PreviewAny",
565 "pos": [
566 1150,
567 -750
568 ],
569 "size": [
570 270,
571 140
572 ],
573 "flags": [],
574 "order": 5,
575 "mode": 0,
576 "inputs": [
577 {
578 "localized_name": "source",
579 "name": "source",
580 "type": "*",
581 "link": 51
582 }
583 ],
584 "outputs": [
585 {
586 "localized_name": "STRING",
587 "name": "STRING",
588 "type": "STRING",
589 "links": null
590 }
591 ],
592 "properties": {
593 "Node name for S&R": "PreviewAny"
594 },
595 "widgets_values": [],
596 "widgets_values_named": []
597 },
598 {
599 "id": 8,
600 "type": "KSampler",
601 "pos": [
602 1680,
603 -940
604 ],
605 "size": [
606 330,
607 270
608 ],
609 "flags": [],
610 "order": 1,
611 "mode": 0,
612 "inputs": [
613 {
614 "localized_name": "model",
615 "name": "model",
616 "type": "MODEL",
617 "link": 18
618 },
619 {
620 "localized_name": "positive",
621 "name": "positive",
622 "type": "CONDITIONING",
623 "link": 49
624 },
625 {
626 "localized_name": "negative",
627 "name": "negative",
628 "type": "CONDITIONING",
629 "link": 26
630 },
631 {
632 "localized_name": "latent_image",
633 "name": "latent_image",
634 "type": "LATENT",
635 "link": 8
636 },
637 {
638 "localized_name": "seed",
639 "name": "seed",
640 "type": "INT",
641 "widget": {
642 "name": "seed"
643 },
644 "link": 69
645 }
646 ],
647 "outputs": [
648 {
649 "localized_name": "LATENT",
650 "name": "LATENT",
651 "type": "LATENT",
652 "links": [
653 9
654 ]
655 }
656 ],
657 "properties": {
658 "Node name for S&R": "KSampler"
659 },
660 "widgets_values": [
661 42,
662 "fixed",
663 32,
664 1,
665 "dpm_2",
666 "sgm_uniform",
667 1
668 ],
669 "widgets_values_named": {
670 "seed": 42,
671 "control_after_generate": "fixed",
672 "steps": 32,
673 "cfg": 1,
674 "sampler_name": "dpm_2",
675 "scheduler": "sgm_uniform",
676 "denoise": 1
677 }
678 },
679 {
680 "id": 5,
681 "type": "EmptyYuE2LatentAudio",
682 "pos": [
683 1890,
684 -470
685 ],
686 "size": [
687 230,
688 90
689 ],
690 "flags": [],
691 "order": 0,
692 "mode": 0,
693 "inputs": [
694 {
695 "localized_name": "seconds",
696 "name": "seconds",
697 "type": "FLOAT",
698 "widget": {
699 "name": "seconds"
700 },
701 "link": 48
702 }
703 ],
704 "outputs": [
705 {
706 "localized_name": "LATENT",
707 "name": "LATENT",
708 "type": "LATENT",
709 "links": [
710 8
711 ]
712 }
713 ],
714 "properties": {
715 "Node name for S&R": "EmptyYuE2LatentAudio"
716 },
717 "widgets_values": [
718 120,
719 1
720 ],
721 "widgets_values_named": {
722 "seconds": 120,
723 "batch_size": 1
724 },
725 "color": "#323",
726 "bgcolor": "#535"
727 },
728 {
729 "id": 9,
730 "type": "VAEDecodeAudio",
731 "pos": [
732 2060,
733 -860
734 ],
735 "size": [
736 230,
737 60
738 ],
739 "flags": [],
740 "order": 2,
741 "mode": 0,
742 "inputs": [
743 {
744 "localized_name": "samples",
745 "name": "samples",
746 "type": "LATENT",
747 "link": 9
748 },
749 {
750 "localized_name": "vae",
751 "name": "vae",
752 "type": "VAE",
753 "link": 21
754 }
755 ],
756 "outputs": [
757 {
758 "localized_name": "AUDIO",
759 "name": "AUDIO",
760 "type": "AUDIO",
761 "links": [
762 31
763 ]
764 }
765 ],
766 "properties": {
767 "Node name for S&R": "VAEDecodeAudio"
768 }
769 },
770 {
771 "id": 34,
772 "type": "SeedNode",
773 "pos": [
774 730,
775 -410
776 ],
777 "size": [
778 270,
779 90
780 ],
781 "flags": [],
782 "order": 7,
783 "mode": 0,
784 "inputs": [
785 {
786 "localized_name": "seed",
787 "name": "seed",
788 "type": "INT",
789 "widget": {
790 "name": "seed"
791 },
792 "link": 80
793 }
794 ],
795 "outputs": [
796 {
797 "localized_name": "seed",
798 "name": "seed",
799 "type": "INT",
800 "links": [
801 68,
802 69
803 ]
804 }
805 ],
806 "properties": {
807 "Node name for S&R": "SeedNode"
808 },
809 "widgets_values": [
810 0,
811 "randomize"
812 ],
813 "widgets_values_named": {
814 "seed": 0,
815 "fixed": "randomize"
816 }
817 },
818 {
819 "id": 41,
820 "type": "SheetSage2AudioToABC",
821 "pos": [
822 -150,
823 -650
824 ],
825 "size": [
826 230,
827 90
828 ],
829 "flags": [],
830 "order": 8,
831 "mode": 0,
832 "inputs": [
833 {
834 "localized_name": "audio_encoder",
835 "name": "audio_encoder",
836 "type": "AUDIO_ENCODER",
837 "link": 84
838 },
839 {
840 "localized_name": "audio",
841 "name": "audio",
842 "type": "AUDIO",
843 "link": 90
844 }
845 ],
846 "outputs": [
847 {
848 "localized_name": "abc",
849 "name": "abc",
850 "shape": 6,
851 "type": "STRING",
852 "links": [
853 93
854 ]
855 }
856 ],
857 "properties": {
858 "Node name for S&R": "SheetSage2AudioToABC"
859 },
860 "widgets_values": [
861 "melody"
862 ],
863 "widgets_values_named": {
864 "mode": "melody"
865 }
866 },
867 {
868 "id": 43,
869 "type": "AudioEncoderLoader",
870 "pos": [
871 -240,
872 -920
873 ],
874 "size": [
875 420,
876 80
877 ],
878 "flags": [],
879 "order": 9,
880 "mode": 0,
881 "inputs": [
882 {
883 "localized_name": "audio_encoder_name",
884 "name": "audio_encoder_name",
885 "type": "COMBO",
886 "widget": {
887 "name": "audio_encoder_name"
888 },
889 "link": 91
890 }
891 ],
892 "outputs": [
893 {
894 "localized_name": "AUDIO_ENCODER",
895 "name": "AUDIO_ENCODER",
896 "type": "AUDIO_ENCODER",
897 "links": [
898 84
899 ]
900 }
901 ],
902 "properties": {
903 "Node name for S&R": "AudioEncoderLoader",
904 "models": [
905 {
906 "name": "sheetsage2_bf16.safetensors",
907 "url": "https://huggingface.co/Comfy-Org/YuE2/resolve/main/audio_encoders/sheetsage2_bf16.safetensors",
908 "directory": "audio_encoders"
909 }
910 ]
911 },
912 "widgets_values": [
913 "sheetsage2_bf16.safetensors"
914 ],
915 "widgets_values_named": {
916 "audio_encoder_name": "sheetsage2_bf16.safetensors"
917 }
918 },
919 {
920 "id": 44,
921 "type": "PreviewAny",
922 "pos": [
923 -250,
924 -500
925 ],
926 "size": [
927 470,
928 300
929 ],
930 "flags": [],
931 "order": 10,
932 "mode": 0,
933 "inputs": [
934 {
935 "localized_name": "source",
936 "name": "source",
937 "type": "*",
938 "link": 93
939 }
940 ],
941 "outputs": [
942 {
943 "localized_name": "STRING",
944 "name": "STRING",
945 "type": "STRING",
946 "links": [
947 94
948 ]
949 }
950 ],
951 "properties": {
952 "Node name for S&R": "PreviewAny"
953 },
954 "widgets_values": [],
955 "widgets_values_named": []
956 }
957 ],
958 "groups": [
959 {
960 "id": 3,
961 "title": "Model",
962 "bounding": [
963 -330,
964 -1180,
965 620,
966 430
967 ],
968 "color": "#3f789e",
969 "flags": []
970 },
971 {
972 "id": 2,
973 "title": "ABC",
974 "bounding": [
975 -330,
976 -730,
977 620,
978 560
979 ],
980 "color": "#3f789e",
981 "flags": []
982 },
983 {
984 "id": 6,
985 "title": "Conditioning",
986 "bounding": [
987 390,
988 -1080,
989 1160,
990 790
991 ],
992 "color": "#3f789e",
993 "flags": []
994 },
995 {
996 "id": 4,
997 "title": "Duration",
998 "bounding": [
999 1640,
1000 -570,
1001 720,
1002 280
1003 ],
1004 "color": "#3f789e",
1005 "flags": []
1006 },
1007 {
1008 "id": 5,
1009 "title": "Sampling & Decode",
1010 "bounding": [
1011 1640,
1012 -1080,
1013 720,
1014 480
1015 ],
1016 "color": "#3f789e",
1017 "flags": []
1018 }
1019 ],
1020 "links": [
1021 {
1022 "id": 43,
1023 "origin_id": 15,
1024 "origin_slot": 1,
1025 "target_id": 25,
1026 "target_slot": 0,
1027 "type": "CLIP"
1028 },
1029 {
1030 "id": 50,
1031 "origin_id": 25,
1032 "origin_slot": 0,
1033 "target_id": 18,
1034 "target_slot": 0,
1035 "type": "CONDITIONING"
1036 },
1037 {
1038 "id": 51,
1039 "origin_id": 25,
1040 "origin_slot": 1,
1041 "target_id": 23,
1042 "target_slot": 0,
1043 "type": "FLOAT"
1044 },
1045 {
1046 "id": 18,
1047 "origin_id": 15,
1048 "origin_slot": 0,
1049 "target_id": 8,
1050 "target_slot": 0,
1051 "type": "MODEL"
1052 },
1053 {
1054 "id": 49,
1055 "origin_id": 25,
1056 "origin_slot": 0,
1057 "target_id": 8,
1058 "target_slot": 1,
1059 "type": "CONDITIONING"
1060 },
1061 {
1062 "id": 26,
1063 "origin_id": 18,
1064 "origin_slot": 0,
1065 "target_id": 8,
1066 "target_slot": 2,
1067 "type": "CONDITIONING"
1068 },
1069 {
1070 "id": 8,
1071 "origin_id": 5,
1072 "origin_slot": 0,
1073 "target_id": 8,
1074 "target_slot": 3,
1075 "type": "LATENT"
1076 },
1077 {
1078 "id": 48,
1079 "origin_id": 25,
1080 "origin_slot": 1,
1081 "target_id": 5,
1082 "target_slot": 0,
1083 "type": "FLOAT"
1084 },
1085 {
1086 "id": 9,
1087 "origin_id": 8,
1088 "origin_slot": 0,
1089 "target_id": 9,
1090 "target_slot": 0,
1091 "type": "LATENT"
1092 },
1093 {
1094 "id": 21,
1095 "origin_id": 15,
1096 "origin_slot": 2,
1097 "target_id": 9,
1098 "target_slot": 1,
1099 "type": "VAE"
1100 },
1101 {
1102 "id": 31,
1103 "origin_id": 9,
1104 "origin_slot": 0,
1105 "target_id": -20,
1106 "target_slot": 0,
1107 "type": "AUDIO"
1108 },
1109 {
1110 "id": 68,
1111 "origin_id": 34,
1112 "origin_slot": 0,
1113 "target_id": 25,
1114 "target_slot": 4,
1115 "type": "INT"
1116 },
1117 {
1118 "id": 69,
1119 "origin_id": 34,
1120 "origin_slot": 0,
1121 "target_id": 8,
1122 "target_slot": 4,
1123 "type": "INT"
1124 },
1125 {
1126 "id": 79,
1127 "origin_id": -10,
1128 "origin_slot": 2,
1129 "target_id": 25,
1130 "target_slot": 5,
1131 "type": "FLOAT"
1132 },
1133 {
1134 "id": 80,
1135 "origin_id": -10,
1136 "origin_slot": 3,
1137 "target_id": 34,
1138 "target_slot": 0,
1139 "type": "INT"
1140 },
1141 {
1142 "id": 81,
1143 "origin_id": -10,
1144 "origin_slot": 4,
1145 "target_id": 15,
1146 "target_slot": 0,
1147 "type": "COMBO"
1148 },
1149 {
1150 "id": 84,
1151 "origin_id": 43,
1152 "origin_slot": 0,
1153 "target_id": 41,
1154 "target_slot": 0,
1155 "type": "AUDIO_ENCODER"
1156 },
1157 {
1158 "id": 90,
1159 "origin_id": -10,
1160 "origin_slot": 5,
1161 "target_id": 41,
1162 "target_slot": 1,
1163 "type": "AUDIO"
1164 },
1165 {
1166 "id": 91,
1167 "origin_id": -10,
1168 "origin_slot": 6,
1169 "target_id": 43,
1170 "target_slot": 0,
1171 "type": "COMBO"
1172 },
1173 {
1174 "id": 93,
1175 "origin_id": 41,
1176 "origin_slot": 0,
1177 "target_id": 44,
1178 "target_slot": 0,
1179 "type": "STRING"
1180 },
1181 {
1182 "id": 94,
1183 "origin_id": 44,
1184 "origin_slot": 0,
1185 "target_id": 25,
1186 "target_slot": 3,
1187 "type": "STRING"
1188 },
1189 {
1190 "id": 95,
1191 "origin_id": -10,
1192 "origin_slot": 0,
1193 "target_id": 25,
1194 "target_slot": 1,
1195 "type": "STRING"
1196 },
1197 {
1198 "id": 96,
1199 "origin_id": -10,
1200 "origin_slot": 1,
1201 "target_id": 25,
1202 "target_slot": 2,
1203 "type": "STRING"
1204 }
1205 ],
1206 "extra": []
1207 }
1208 ]
1209 },
1210 "config": [],
1211 "extra": {
1212 "frontendVersion": "1.52.7",
1213 "VHS_latentpreview": false,
1214 "VHS_latentpreviewrate": 0,
1215 "VHS_MetadataImage": true,
1216 "VHS_KeepIntermediate": true,
1217 "ds": {
1218 "scale": 0.29081731783854076,
1219 "offset": [
1220 957.4907031583202,
1221 1262.2951649422725
1222 ]
1223 }
1224 },
1225 "version": 0.4
1226}