ComfyPilotComfyPilot
工作流 / 音频 / Stable Audio 1.0：文生音频
Stable Audio 1.0：文生音频

Stable Audio 1.0：文生音频

Stable Audio 1.0: Text to Audio

使用Stable Audio从文本提示生成音频。

音频 9 个节点 28 次使用 ComfyUI ≥ 0.25.0 ComfyUI 11 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 1 个能在本站模型库里找到。

stable-audio-open-1.0.safetensors 在模型库查看
t5-base.safetensors 模型库暂未收录

节点构成

CLIPTextEncode × 2
CheckpointLoaderSimple × 1
CLIPLoader × 1
EmptyLatentAudio × 1
KSampler × 1
VAEDecodeAudio × 1
MarkdownNote × 1
SaveAudioAdvanced × 1

官方标注的模型

StabilityStable Audio

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
2 "id": "5fa61cc8-29d9-4deb-9f90-02d3c00b63b3",
3 "revision": 0,
4 "last_node_id": 20,
5 "last_link_id": 28,
6 "nodes": [
7 {
8 "id": 4,
9 "type": "CheckpointLoaderSimple",
10 "pos": [
11 -30,
12 290
13 ],
14 "size": [
15 340,
16 150
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "MODEL",
25 "type": "MODEL",
26 "slot_index": 0,
27 "links": [
28 18
29 ]
30 },
31 {
32 "name": "CLIP",
33 "type": "CLIP",
34 "slot_index": 1,
35 "links": []
36 },
37 {
38 "name": "VAE",
39 "type": "VAE",
40 "slot_index": 2,
41 "links": [
42 14
43 ]
44 }
45 ],
46 "properties": {
47 "Node name for S&R": "CheckpointLoaderSimple",
48 "models": [
49 {
50 "name": "stable-audio-open-1.0.safetensors",
51 "url": "https://huggingface.co/Comfy-Org/stable-audio-open-1.0_repackaged/resolve/main/stable-audio-open-1.0.safetensors",
52 "directory": "checkpoints"
53 }
54 ]
55 },
56 "widgets_values": [
57 "stable-audio-open-1.0.safetensors"
58 ],
59 "widgets_values_named": {
60 "ckpt_name": "stable-audio-open-1.0.safetensors"
61 }
62 },
63 {
64 "id": 6,
65 "type": "CLIPTextEncode",
66 "pos": [
67 370,
68 80
69 ],
70 "size": [
71 440,
72 150
73 ],
74 "flags": [],
75 "order": 4,
76 "mode": 0,
77 "inputs": [
78 {
79 "name": "clip",
80 "type": "CLIP",
81 "link": 25
82 }
83 ],
84 "outputs": [
85 {
86 "name": "CONDITIONING",
87 "type": "CONDITIONING",
88 "slot_index": 0,
89 "links": [
90 4
91 ]
92 }
93 ],
94 "properties": {
95 "Node name for S&R": "CLIPTextEncode"
96 },
97 "widgets_values": [
98 "heaven church electronic dance music"
99 ],
100 "widgets_values_named": {
101 "text": "heaven church electronic dance music"
102 },
103 "color": "#232",
104 "bgcolor": "#353"
105 },
106 {
107 "id": 7,
108 "type": "CLIPTextEncode",
109 "pos": [
110 370,
111 270
112 ],
113 "size": [
114 440,
115 150
116 ],
117 "flags": [],
118 "order": 5,
119 "mode": 0,
120 "inputs": [
121 {
122 "name": "clip",
123 "type": "CLIP",
124 "link": 26
125 }
126 ],
127 "outputs": [
128 {
129 "name": "CONDITIONING",
130 "type": "CONDITIONING",
131 "slot_index": 0,
132 "links": [
133 6
134 ]
135 }
136 ],
137 "properties": {
138 "Node name for S&R": "CLIPTextEncode"
139 },
140 "widgets_values": [
141 ""
142 ],
143 "widgets_values_named": {
144 "text": ""
145 },
146 "color": "#322",
147 "bgcolor": "#533"
148 },
149 {
150 "id": 10,
151 "type": "CLIPLoader",
152 "pos": [
153 -30,
154 90
155 ],
156 "size": [
157 340,
158 138
159 ],
160 "flags": [],
161 "order": 1,
162 "mode": 0,
163 "inputs": [],
164 "outputs": [
165 {
166 "name": "CLIP",
167 "type": "CLIP",
168 "slot_index": 0,
169 "links": [
170 25,
171 26
172 ]
173 }
174 ],
175 "properties": {
176 "Node name for S&R": "CLIPLoader",
177 "models": [
178 {
179 "name": "t5-base.safetensors",
180 "url": "https://huggingface.co/ComfyUI-Wiki/t5-base/resolve/main/t5-base.safetensors",
181 "directory": "text_encoders"
182 }
183 ]
184 },
185 "widgets_values": [
186 "t5-base.safetensors",
187 "stable_audio",
188 "default"
189 ],
190 "widgets_values_named": {
191 "clip_name": "t5-base.safetensors",
192 "type": "stable_audio",
193 "device": "default"
194 }
195 },
196 {
197 "id": 11,
198 "type": "EmptyLatentAudio",
199 "pos": [
200 10,
201 580
202 ],
203 "size": [
204 240,
205 114
206 ],
207 "flags": [],
208 "order": 2,
209 "mode": 0,
210 "inputs": [],
211 "outputs": [
212 {
213 "name": "LATENT",
214 "type": "LATENT",
215 "links": [
216 12
217 ]
218 }
219 ],
220 "properties": {
221 "Node name for S&R": "EmptyLatentAudio"
222 },
223 "widgets_values": [
224 47.6,
225 1
226 ],
227 "widgets_values_named": {
228 "seconds": 47.6,
229 "batch_size": 1
230 }
231 },
232 {
233 "id": 3,
234 "type": "KSampler",
235 "pos": [
236 860,
237 50
238 ],
239 "size": [
240 320,
241 286
242 ],
243 "flags": [],
244 "order": 6,
245 "mode": 0,
246 "inputs": [
247 {
248 "name": "model",
249 "type": "MODEL",
250 "link": 18
251 },
252 {
253 "name": "positive",
254 "type": "CONDITIONING",
255 "link": 4
256 },
257 {
258 "name": "negative",
259 "type": "CONDITIONING",
260 "link": 6
261 },
262 {
263 "name": "latent_image",
264 "type": "LATENT",
265 "link": 12
266 }
267 ],
268 "outputs": [
269 {
270 "name": "LATENT",
271 "type": "LATENT",
272 "slot_index": 0,
273 "links": [
274 13
275 ]
276 }
277 ],
278 "properties": {
279 "Node name for S&R": "KSampler"
280 },
281 "widgets_values": [
282 840755638734093,
283 "randomize",
284 50,
285 4.98,
286 "dpmpp_3m_sde_gpu",
287 "exponential",
288 1
289 ],
290 "widgets_values_named": {
291 "seed": 840755638734093,
292 "control_after_generate": "randomize",
293 "steps": 50,
294 "cfg": 4.98,
295 "sampler_name": "dpmpp_3m_sde_gpu",
296 "scheduler": "exponential",
297 "denoise": 1
298 }
299 },
300 {
301 "id": 12,
302 "type": "VAEDecodeAudio",
303 "pos": [
304 1200,
305 60
306 ],
307 "size": [
308 225,
309 78
310 ],
311 "flags": [],
312 "order": 7,
313 "mode": 0,
314 "inputs": [
315 {
316 "name": "samples",
317 "type": "LATENT",
318 "link": 13
319 },
320 {
321 "name": "vae",
322 "type": "VAE",
323 "link": 14
324 }
325 ],
326 "outputs": [
327 {
328 "name": "AUDIO",
329 "type": "AUDIO",
330 "slot_index": 0,
331 "links": [
332 28
333 ]
334 }
335 ],
336 "properties": {
337 "Node name for S&R": "VAEDecodeAudio"
338 }
339 },
340 {
341 "id": 18,
342 "type": "MarkdownNote",
343 "pos": [
344 -500,
345 60
346 ],
347 "size": [
348 410,
349 378
350 ],
351 "flags": [],
352 "order": 3,
353 "mode": 0,
354 "inputs": [],
355 "outputs": [],
356 "properties": [],
357 "widgets_values": [
358 "\n## Model links\n\n- [Hugging Face:Comfy-Org/stable-audio-open-1.0_repackaged](https://huggingface.co/Comfy-Org/stable-audio-open-1.0_repackaged)\n\n**ModelScope mirrors** (alternative repo location)\n\n- [ModelScope:Comfy-Org/stable-audio-open-1.0_repackaged](https://modelscope.cn/models/Comfy-Org/stable-audio-open-1.0_repackaged)\n\n**checkpoints**\n\n- [stable-audio-open-1.0.safetensors](https://huggingface.co/Comfy-Org/stable-audio-open-1.0_repackaged/resolve/main/stable-audio-open-1.0.safetensors) (4.52 GB)\n\n**text_encoders**\n\n- [t5-base.safetensors](https://huggingface.co/ComfyUI-Wiki/t5-base/resolve/main/t5-base.safetensors) (850.3 MB)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 checkpoints/\n│ │ └── stable-audio-open-1.0.safetensors\n│ └── 📂 text_encoders/\n│ └── t5-base.safetensors\n```\n"
359 ],
360 "widgets_values_named": {
361 "text": "\n## Model links\n\n- [Hugging Face:Comfy-Org/stable-audio-open-1.0_repackaged](https://huggingface.co/Comfy-Org/stable-audio-open-1.0_repackaged)\n\n**ModelScope mirrors** (alternative repo location)\n\n- [ModelScope:Comfy-Org/stable-audio-open-1.0_repackaged](https://modelscope.cn/models/Comfy-Org/stable-audio-open-1.0_repackaged)\n\n**checkpoints**\n\n- [stable-audio-open-1.0.safetensors](https://huggingface.co/Comfy-Org/stable-audio-open-1.0_repackaged/resolve/main/stable-audio-open-1.0.safetensors) (4.52 GB)\n\n**text_encoders**\n\n- [t5-base.safetensors](https://huggingface.co/ComfyUI-Wiki/t5-base/resolve/main/t5-base.safetensors) (850.3 MB)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 checkpoints/\n│ │ └── stable-audio-open-1.0.safetensors\n│ └── 📂 text_encoders/\n│ └── t5-base.safetensors\n```\n"
362 },
363 "color": "#222",
364 "bgcolor": "#000"
365 },
366 {
367 "id": 20,
368 "type": "SaveAudioAdvanced",
369 "pos": [
370 1200,
371 180
372 ],
373 "size": [
374 270,
375 150
376 ],
377 "flags": [],
378 "order": 8,
379 "mode": 0,
380 "inputs": [
381 {
382 "name": "audio",
383 "type": "AUDIO",
384 "link": 28
385 }
386 ],
387 "outputs": [
388 {
389 "name": "audio",
390 "type": "AUDIO",
391 "links": null
392 }
393 ],
394 "properties": [],
395 "widgets_values": [
396 "audio/ComfyUI",
397 "flac"
398 ],
399 "widgets_values_named": {
400 "filename_prefix": "audio/ComfyUI",
401 "format": "flac"
402 }
403 }
404 ],
405 "links": [
406 [
407 4,
408 6,
409 0,
410 3,
411 1,
412 "CONDITIONING"
413 ],
414 [
415 6,
416 7,
417 0,
418 3,
419 2,
420 "CONDITIONING"
421 ],
422 [
423 12,
424 11,
425 0,
426 3,
427 3,
428 "LATENT"
429 ],
430 [
431 13,
432 3,
433 0,
434 12,
435 0,
436 "LATENT"
437 ],
438 [
439 14,
440 4,
441 2,
442 12,
443 1,
444 "VAE"
445 ],
446 [
447 18,
448 4,
449 0,
450 3,
451 0,
452 "MODEL"
453 ],
454 [
455 25,
456 10,
457 0,
458 6,
459 0,
460 "CLIP"
461 ],
462 [
463 26,
464 10,
465 0,
466 7,
467 0,
468 "CLIP"
469 ],
470 [
471 28,
472 12,
473 0,
474 20,
475 0,
476 "AUDIO"
477 ]
478 ],
479 "groups": [
480 {
481 "id": 1,
482 "title": "Models",
483 "bounding": [
484 -70,
485 10,
486 410,
487 470
488 ],
489 "color": "#3f789e",
490 "flags": []
491 },
492 {
493 "id": 2,
494 "title": "Duration",
495 "bounding": [
496 -70,
497 510,
498 410,
499 200
500 ],
501 "color": "#3f789e",
502 "flags": []
503 },
504 {
505 "id": 3,
506 "title": "Pormpt",
507 "bounding": [
508 360,
509 10,
510 470,
511 470
512 ],
513 "color": "#3f789e",
514 "flags": []
515 }
516 ],
517 "config": [],
518 "extra": {
519 "ds": {
520 "scale": 1.1296006569186263,
521 "offset": [
522 -476.210770956474,
523 338.00280862616074
524 ]
525 },
526 "frontendVersion": "1.51.9"
527 },
528 "version": 0.4
529}