ComfyPilotComfyPilot
工作流 / 音频 / ACE-Step 1.5 音乐生成（4B LLM）

ACE-Step 1.5 音乐生成（4B LLM）

ACE-Step 1.5 Music Generation (4B LLM )

输入文本提示词以生成音乐。此4B模型版本相比更小的变体输出更强的音频理解和作曲能力。

音频 13 个节点 14 次使用 ComfyUI ≥ 0.25.0 ComfyUI 18 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 4 个权重文件，其中 4 个能在本站模型库里找到。

ace_1.5_vae.safetensors 在模型库查看
acestep_v1.5_turbo.safetensors 在模型库查看
qwen_0.6b_ace15.safetensors 在模型库查看
qwen_4b_ace15.safetensors 在模型库查看

节点构成

PrimitiveNode × 2
UNETLoader × 1
VAELoader × 1
EmptyAceStep1.5LatentAudio × 1
ConditioningZeroOut × 1
KSampler × 1
ModelSamplingAuraFlow × 1
VAEDecodeAudio × 1
DualCLIPLoader × 1
TextEncodeAceStepAudio1.5 × 1
SaveAudioMP3 × 1
MarkdownNote × 1

官方标注的模型

ACE-Step

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
2 "id": "88ac5dad-efd7-40bb-84fe-fbaefdee1fa9",
3 "revision": 0,
4 "last_node_id": 108,
5 "last_link_id": 263,
6 "nodes": [
7 {
8 "id": 104,
9 "type": "UNETLoader",
10 "pos": [
11 -170,
12 -790
13 ],
14 "size": [
15 380,
16 82
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "MODEL",
25 "type": "MODEL",
26 "links": [
27 260
28 ]
29 }
30 ],
31 "properties": {
32 "Node name for S&R": "UNETLoader",
33 "cnr_id": "comfy-core",
34 "ver": "0.11.1",
35 "models": [
36 {
37 "name": "acestep_v1.5_turbo.safetensors",
38 "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/diffusion_models/acestep_v1.5_turbo.safetensors",
39 "directory": "diffusion_models"
40 }
41 ],
42 "enableTabs": false,
43 "tabWidth": 65,
44 "tabXOffset": 10,
45 "hasSecondTab": false,
46 "secondTabText": "Send Back",
47 "secondTabOffset": 80,
48 "secondTabWidth": 65
49 },
50 "widgets_values": [
51 "acestep_v1.5_turbo.safetensors",
52 "default"
53 ]
54 },
55 {
56 "id": 106,
57 "type": "VAELoader",
58 "pos": [
59 -165,
60 -470
61 ],
62 "size": [
63 380,
64 58
65 ],
66 "flags": [],
67 "order": 1,
68 "mode": 0,
69 "inputs": [],
70 "outputs": [
71 {
72 "name": "VAE",
73 "type": "VAE",
74 "links": [
75 262
76 ]
77 }
78 ],
79 "properties": {
80 "Node name for S&R": "VAELoader",
81 "cnr_id": "comfy-core",
82 "ver": "0.11.1",
83 "models": [
84 {
85 "name": "ace_1.5_vae.safetensors",
86 "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/vae/ace_1.5_vae.safetensors",
87 "directory": "vae"
88 }
89 ],
90 "enableTabs": false,
91 "tabWidth": 65,
92 "tabXOffset": 10,
93 "hasSecondTab": false,
94 "secondTabText": "Send Back",
95 "secondTabOffset": 80,
96 "secondTabWidth": 65
97 },
98 "widgets_values": [
99 "ace_1.5_vae.safetensors"
100 ]
101 },
102 {
103 "id": 102,
104 "type": "PrimitiveNode",
105 "pos": [
106 -130,
107 -120
108 ],
109 "size": [
110 268.39945903485034,
111 82
112 ],
113 "flags": [],
114 "order": 2,
115 "mode": 0,
116 "inputs": [],
117 "outputs": [
118 {
119 "name": "INT",
120 "type": "INT",
121 "widget": {
122 "name": "seed"
123 },
124 "links": [
125 257,
126 258
127 ]
128 }
129 ],
130 "title": "seed",
131 "properties": {
132 "Run widget replace on values": false
133 },
134 "widgets_values": [
135 31,
136 "fixed"
137 ]
138 },
139 {
140 "id": 99,
141 "type": "PrimitiveNode",
142 "pos": [
143 -120,
144 -300
145 ],
146 "size": [
147 278.97400302222843,
148 82
149 ],
150 "flags": [],
151 "order": 3,
152 "mode": 0,
153 "inputs": [],
154 "outputs": [
155 {
156 "name": "FLOAT",
157 "type": "FLOAT",
158 "widget": {
159 "name": "seconds"
160 },
161 "links": [
162 250,
163 251
164 ]
165 }
166 ],
167 "title": "Song Duration",
168 "properties": {
169 "Run widget replace on values": false
170 },
171 "widgets_values": [
172 120,
173 "fixed"
174 ]
175 },
176 {
177 "id": 98,
178 "type": "EmptyAceStep1.5LatentAudio",
179 "pos": [
180 -150,
181 10
182 ],
183 "size": [
184 314.90390625,
185 82
186 ],
187 "flags": [],
188 "order": 7,
189 "mode": 0,
190 "inputs": [
191 {
192 "name": "seconds",
193 "type": "FLOAT",
194 "widget": {
195 "name": "seconds"
196 },
197 "link": 250
198 }
199 ],
200 "outputs": [
201 {
202 "name": "LATENT",
203 "type": "LATENT",
204 "links": [
205 249
206 ]
207 }
208 ],
209 "properties": {
210 "Node name for S&R": "EmptyAceStep1.5LatentAudio",
211 "cnr_id": "comfy-core",
212 "ver": "0.11.1",
213 "enableTabs": false,
214 "tabWidth": 65,
215 "tabXOffset": 10,
216 "hasSecondTab": false,
217 "secondTabText": "Send Back",
218 "secondTabOffset": 80,
219 "secondTabWidth": 65
220 },
221 "widgets_values": [
222 120,
223 1
224 ]
225 },
226 {
227 "id": 47,
228 "type": "ConditioningZeroOut",
229 "pos": [
230 670,
231 50
232 ],
233 "size": [
234 204.75,
235 26
236 ],
237 "flags": [],
238 "order": 9,
239 "mode": 0,
240 "inputs": [
241 {
242 "name": "conditioning",
243 "type": "CONDITIONING",
244 "link": 255
245 }
246 ],
247 "outputs": [
248 {
249 "name": "CONDITIONING",
250 "type": "CONDITIONING",
251 "links": [
252 119
253 ]
254 }
255 ],
256 "properties": {
257 "Node name for S&R": "ConditioningZeroOut",
258 "cnr_id": "comfy-core",
259 "ver": "0.11.1",
260 "enableTabs": false,
261 "tabWidth": 65,
262 "tabXOffset": 10,
263 "hasSecondTab": false,
264 "secondTabText": "Send Back",
265 "secondTabOffset": 80,
266 "secondTabWidth": 65
267 },
268 "widgets_values": []
269 },
270 {
271 "id": 3,
272 "type": "KSampler",
273 "pos": [
274 930,
275 -680
276 ],
277 "size": [
278 329.39477481889753,
279 262
280 ],
281 "flags": [],
282 "order": 10,
283 "mode": 0,
284 "inputs": [
285 {
286 "name": "model",
287 "type": "MODEL",
288 "link": 175
289 },
290 {
291 "name": "positive",
292 "type": "CONDITIONING",
293 "link": 254
294 },
295 {
296 "name": "negative",
297 "type": "CONDITIONING",
298 "link": 119
299 },
300 {
301 "name": "latent_image",
302 "type": "LATENT",
303 "link": 249
304 },
305 {
306 "name": "seed",
307 "type": "INT",
308 "widget": {
309 "name": "seed"
310 },
311 "link": 258
312 }
313 ],
314 "outputs": [
315 {
316 "name": "LATENT",
317 "type": "LATENT",
318 "slot_index": 0,
319 "links": [
320 256
321 ]
322 }
323 ],
324 "properties": {
325 "Node name for S&R": "KSampler",
326 "cnr_id": "comfy-core",
327 "ver": "0.11.1",
328 "enableTabs": false,
329 "tabWidth": 65,
330 "tabXOffset": 10,
331 "hasSecondTab": false,
332 "secondTabText": "Send Back",
333 "secondTabOffset": 80,
334 "secondTabWidth": 65
335 },
336 "widgets_values": [
337 31,
338 "fixed",
339 8,
340 1,
341 "euler",
342 "simple",
343 1
344 ]
345 },
346 {
347 "id": 78,
348 "type": "ModelSamplingAuraFlow",
349 "pos": [
350 930,
351 -810
352 ],
353 "size": [
354 329.39477481889753,
355 60
356 ],
357 "flags": [],
358 "order": 6,
359 "mode": 0,
360 "inputs": [
361 {
362 "name": "model",
363 "type": "MODEL",
364 "link": 260
365 }
366 ],
367 "outputs": [
368 {
369 "name": "MODEL",
370 "type": "MODEL",
371 "links": [
372 175
373 ]
374 }
375 ],
376 "properties": {
377 "Node name for S&R": "ModelSamplingAuraFlow",
378 "cnr_id": "comfy-core",
379 "ver": "0.11.1",
380 "enableTabs": false,
381 "tabWidth": 65,
382 "tabXOffset": 10,
383 "hasSecondTab": false,
384 "secondTabText": "Send Back",
385 "secondTabOffset": 80,
386 "secondTabWidth": 65
387 },
388 "widgets_values": [
389 3
390 ]
391 },
392 {
393 "id": 18,
394 "type": "VAEDecodeAudio",
395 "pos": [
396 1280,
397 -800
398 ],
399 "size": [
400 164.8375,
401 46
402 ],
403 "flags": [],
404 "order": 11,
405 "mode": 0,
406 "inputs": [
407 {
408 "name": "samples",
409 "type": "LATENT",
410 "link": 256
411 },
412 {
413 "name": "vae",
414 "type": "VAE",
415 "link": 262
416 }
417 ],
418 "outputs": [
419 {
420 "name": "AUDIO",
421 "type": "AUDIO",
422 "links": [
423 263
424 ]
425 }
426 ],
427 "properties": {
428 "Node name for S&R": "VAEDecodeAudio",
429 "cnr_id": "comfy-core",
430 "ver": "0.11.1",
431 "enableTabs": false,
432 "tabWidth": 65,
433 "tabXOffset": 10,
434 "hasSecondTab": false,
435 "secondTabText": "Send Back",
436 "secondTabOffset": 80,
437 "secondTabWidth": 65
438 },
439 "widgets_values": []
440 },
441 {
442 "id": 105,
443 "type": "DualCLIPLoader",
444 "pos": [
445 -165,
446 -660
447 ],
448 "size": [
449 380,
450 130
451 ],
452 "flags": [],
453 "order": 4,
454 "mode": 0,
455 "inputs": [],
456 "outputs": [
457 {
458 "name": "CLIP",
459 "type": "CLIP",
460 "links": [
461 261
462 ]
463 }
464 ],
465 "properties": {
466 "Node name for S&R": "DualCLIPLoader",
467 "cnr_id": "comfy-core",
468 "ver": "0.11.1",
469 "models": [
470 {
471 "name": "qwen_0.6b_ace15.safetensors",
472 "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_0.6b_ace15.safetensors",
473 "directory": "text_encoders"
474 },
475 {
476 "name": "qwen_4b_ace15.safetensors",
477 "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_4b_ace15.safetensors",
478 "directory": "text_encoders"
479 }
480 ],
481 "enableTabs": false,
482 "tabWidth": 65,
483 "tabXOffset": 10,
484 "hasSecondTab": false,
485 "secondTabText": "Send Back",
486 "secondTabOffset": 80,
487 "secondTabWidth": 65
488 },
489 "widgets_values": [
490 "qwen_0.6b_ace15.safetensors",
491 "qwen_4b_ace15.safetensors",
492 "ace",
493 "default"
494 ]
495 },
496 {
497 "id": 94,
498 "type": "TextEncodeAceStepAudio1.5",
499 "pos": [
500 270,
501 -790
502 ],
503 "size": [
504 611.9184354063266,
505 679.7643386829468
506 ],
507 "flags": [],
508 "order": 8,
509 "mode": 0,
510 "inputs": [
511 {
512 "name": "clip",
513 "type": "CLIP",
514 "link": 261
515 },
516 {
517 "name": "seed",
518 "type": "INT",
519 "widget": {
520 "name": "seed"
521 },
522 "link": 257
523 },
524 {
525 "name": "duration",
526 "type": "FLOAT",
527 "widget": {
528 "name": "duration"
529 },
530 "link": 251
531 }
532 ],
533 "outputs": [
534 {
535 "name": "CONDITIONING",
536 "type": "CONDITIONING",
537 "links": [
538 254,
539 255
540 ]
541 }
542 ],
543 "properties": {
544 "Node name for S&R": "TextEncodeAceStepAudio1.5",
545 "cnr_id": "comfy-core",
546 "ver": "0.11.1",
547 "enableTabs": false,
548 "tabWidth": 65,
549 "tabXOffset": 10,
550 "hasSecondTab": false,
551 "secondTabText": "Send Back",
552 "secondTabOffset": 80,
553 "secondTabWidth": 65
554 },
555 "widgets_values": [
556 "Rock: A powerful, high-energy modern rock track with a raw and rebellious edge.\nDriven by distorted electric guitars, punchy live drums, and a strong bassline.\nThe song builds dynamically from tension to explosion, balancing aggression and emotion.",
557 "[Verse 1]\nStatic in the air, I feel it in my bones\nEvery step I take, I’m carving out my own\nNo more shadows telling me who to be\nI draw the line, now watch me break free\n\n[Pre-Chorus]\nHear the sound, it’s getting louder\nPressure turning into power\nI won’t wait, I won’t fall back\nThis is the moment, this is the attack\n\n[Chorus]\nShout it out, I’m alive tonight\nBurning bright in the dead of night\nHands up, feel the ground shake\nThis is everything I’m gonna take\n\n[Bridge]\nSilence hits before the storm\nHeart beats fast, I transform\n\n[Final Chorus]\nShout it out, I’m alive tonight\nNo more fear, no need to hide\nTurn it up, let the walls break\nThis is the fire you can’t escape",
558 31,
559 "fixed",
560 190,
561 120,
562 "4",
563 "en",
564 "E minor",
565 true,
566 2,
567 0.85,
568 0.9,
569 0,
570 0
571 ]
572 },
573 {
574 "id": 107,
575 "type": "SaveAudioMP3",
576 "pos": [
577 1280,
578 -670
579 ],
580 "size": [
581 700,
582 136
583 ],
584 "flags": [],
585 "order": 12,
586 "mode": 0,
587 "inputs": [
588 {
589 "name": "audio",
590 "type": "AUDIO",
591 "link": 263
592 }
593 ],
594 "outputs": [],
595 "properties": {
596 "Node name for S&R": "SaveAudioMP3",
597 "cnr_id": "comfy-core",
598 "ver": "0.11.1",
599 "enableTabs": false,
600 "tabWidth": 65,
601 "tabXOffset": 10,
602 "hasSecondTab": false,
603 "secondTabText": "Send Back",
604 "secondTabOffset": 80,
605 "secondTabWidth": 65
606 },
607 "widgets_values": [
608 "audio/ComfyUI",
609 "V0"
610 ]
611 },
612 {
613 "id": 108,
614 "type": "MarkdownNote",
615 "pos": [
616 -730,
617 -830
618 ],
619 "size": [
620 520,
621 530
622 ],
623 "flags": [],
624 "order": 5,
625 "mode": 0,
626 "inputs": [],
627 "outputs": [],
628 "properties": [],
629 "widgets_values": [
630 "Guide: [Subgraph](https://docs.comfy.org/interface/features/subgraph)\n\n## Model Links\n\n- [Hugging Face:Comfy-Org/ace_step_1.5_ComfyUI_files](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files)\n\n**ModelScope mirrors** (alternative repo location)\n\n- [ModelScope:Comfy-Org/ace_step_1.5_ComfyUI_files](https://modelscope.cn/models/Comfy-Org/ace_step_1.5_ComfyUI_files)\n\n**diffusion_models**\n\n- [acestep_v1.5_turbo.safetensors](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/diffusion_models/acestep_v1.5_turbo.safetensors) (4.46 GB)\n\n**vae**\n\n- [ace_1.5_vae.safetensors](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/vae/ace_1.5_vae.safetensors) (321.8 MB)\n\n**text_encoders**\n\n- [qwen_0.6b_ace15.safetensors](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_0.6b_ace15.safetensors) (1.11 GB)\n- [qwen_4b_ace15.safetensors](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_4b_ace15.safetensors) (7.8 GB)\n\n## Model Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 diffusion_models/\n│ │ └── acestep_v1.5_turbo.safetensors\n│ ├── 📂 vae/\n│ │ └── ace_1.5_vae.safetensors\n│ └── 📂 text_encoders/\n│ ├── qwen_0.6b_ace15.safetensors\n│ └── qwen_4b_ace15.safetensors\n```\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"
631 ],
632 "color": "#222",
633 "bgcolor": "#000"
634 }
635 ],
636 "links": [
637 [
638 119,
639 47,
640 0,
641 3,
642 2,
643 "CONDITIONING"
644 ],
645 [
646 175,
647 78,
648 0,
649 3,
650 0,
651 "MODEL"
652 ],
653 [
654 249,
655 98,
656 0,
657 3,
658 3,
659 "LATENT"
660 ],
661 [
662 250,
663 99,
664 0,
665 98,
666 0,
667 "FLOAT"
668 ],
669 [
670 251,
671 99,
672 0,
673 94,
674 2,
675 "FLOAT"
676 ],
677 [
678 254,
679 94,
680 0,
681 3,
682 1,
683 "CONDITIONING"
684 ],
685 [
686 255,
687 94,
688 0,
689 47,
690 0,
691 "CONDITIONING"
692 ],
693 [
694 256,
695 3,
696 0,
697 18,
698 0,
699 "LATENT"
700 ],
701 [
702 257,
703 102,
704 0,
705 94,
706 1,
707 "INT"
708 ],
709 [
710 258,
711 102,
712 0,
713 3,
714 4,
715 "INT"
716 ],
717 [
718 260,
719 104,
720 0,
721 78,
722 0,
723 "MODEL"
724 ],
725 [
726 261,
727 105,
728 0,
729 94,
730 0,
731 "CLIP"
732 ],
733 [
734 262,
735 106,
736 0,
737 18,
738 1,
739 "VAE"
740 ],
741 [
742 263,
743 18,
744 0,
745 107,
746 0,
747 "AUDIO"
748 ]
749 ],
750 "groups": [
751 {
752 "id": 1,
753 "title": "Step 1 - Load Models",
754 "bounding": [
755 -180,
756 -860,
757 405,
758 461.6
759 ],
760 "color": "#3f789e",
761 "font_size": 24,
762 "flags": []
763 },
764 {
765 "id": 2,
766 "title": "Step 2 - Duration",
767 "bounding": [
768 -180,
769 -370,
770 400,
771 170
772 ],
773 "color": "#3f789e",
774 "font_size": 24,
775 "flags": []
776 },
777 {
778 "id": 3,
779 "title": "Step3 - Prompt",
780 "bounding": [
781 260,
782 -860,
783 640,
784 960
785 ],
786 "color": "#3f789e",
787 "font_size": 24,
788 "flags": []
789 }
790 ],
791 "config": [],
792 "extra": {
793 "ds": {
794 "scale": 0.4778528745347265,
795 "offset": [
796 1182.2237274901522,
797 1509.517528995496
798 ]
799 },
800 "frontendVersion": "1.38.0",
801 "workflowRendererVersion": "LG",
802 "VHS_latentpreview": false,
803 "VHS_latentpreviewrate": 0,
804 "VHS_MetadataImage": true,
805 "VHS_KeepIntermediate": true
806 },
807 "version": 0.4
808}