工作流 /
视频 /
HuMo 视频生成

HuMo 视频生成
HuMo Video Generation
基于音频、图像和文本生成视频,保持角色嘴唇同步。
视频
20 个节点 2 个输入 25 次使用 ComfyUI ≥ 0.3.60 ComfyUI 21 KB
需要的权重
这个工作流引用了 5 个权重文件,其中 5 个能在本站模型库里找到。
humo_17B_fp8_e4m3fn.safetensors
在模型库查看
lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
在模型库查看
umt5_xxl_fp8_e4m3fn_scaled.safetensors
在模型库查看
wan_2.1_vae.safetensors
在模型库查看
whisper_large_v3_fp16.safetensors
在模型库查看
节点构成
MarkdownNote
× 3
CLIPTextEncode
× 2
CLIPLoader
× 1
VAELoader
× 1
CreateVideo
× 1
VAEDecode
× 1
LoraLoaderModelOnly
× 1
UNETLoader
× 1
WanHuMoImageToVideo
× 1
AudioEncoderEncode
× 1
AudioEncoderLoader
× 1
KSampler
× 1
ModelSamplingSD3
× 1
SaveVideo
× 1
RecordAudio
× 1
LoadImage
× 1
官方标注的模型
HuMo
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "428ebf59-f870-43e5-b3a9-ad0c0b7b33f4",
3 "revision": 2,
4 "last_node_id": 75,
5 "last_link_id": 147,
6 "nodes": [
7 {
8 "id": 38,
9 "type": "CLIPLoader",
10 "pos": [
11 -50,
12 208
13 ],
14 "size": [
15 390,
16 106
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "CLIP",
25 "type": "CLIP",
26 "slot_index": 0,
27 "links": [
28 74,
29 75
30 ]
31 }
32 ],
33 "properties": {
34 "cnr_id": "comfy-core",
35 "ver": "0.3.59",
36 "Node name for S&R": "CLIPLoader",
37 "models": [
38 {
39 "name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
40 "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors",
41 "directory": "text_encoders"
42 }
43 ]
44 },
45 "widgets_values": [
46 "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
47 "wan",
48 "default"
49 ]
50 },
51 {
52 "id": 39,
53 "type": "VAELoader",
54 "pos": [
55 -50,
56 356
57 ],
58 "size": [
59 390,
60 58
61 ],
62 "flags": [],
63 "order": 1,
64 "mode": 0,
65 "inputs": [],
66 "outputs": [
67 {
68 "name": "VAE",
69 "type": "VAE",
70 "slot_index": 0,
71 "links": [
72 136,
73 137
74 ]
75 }
76 ],
77 "properties": {
78 "cnr_id": "comfy-core",
79 "ver": "0.3.59",
80 "Node name for S&R": "VAELoader",
81 "models": [
82 {
83 "name": "wan_2.1_vae.safetensors",
84 "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors",
85 "directory": "vae"
86 }
87 ]
88 },
89 "widgets_values": [
90 "wan_2.1_vae.safetensors"
91 ]
92 },
93 {
94 "id": 60,
95 "type": "CreateVideo",
96 "pos": [
97 850,
98 650
99 ],
100 "size": [
101 230,
102 80
103 ],
104 "flags": [],
105 "order": 18,
106 "mode": 0,
107 "inputs": [
108 {
109 "name": "images",
110 "type": "IMAGE",
111 "link": 143
112 },
113 {
114 "name": "audio",
115 "shape": 7,
116 "type": "AUDIO",
117 "link": 120
118 }
119 ],
120 "outputs": [
121 {
122 "name": "VIDEO",
123 "type": "VIDEO",
124 "links": [
125 119
126 ]
127 }
128 ],
129 "properties": {
130 "cnr_id": "comfy-core",
131 "ver": "0.3.59",
132 "Node name for S&R": "CreateVideo"
133 },
134 "widgets_values": [
135 25
136 ]
137 },
138 {
139 "id": 63,
140 "type": "VAEDecode",
141 "pos": [
142 850,
143 560
144 ],
145 "size": [
146 140,
147 46
148 ],
149 "flags": [],
150 "order": 17,
151 "mode": 0,
152 "inputs": [
153 {
154 "name": "samples",
155 "type": "LATENT",
156 "link": 132
157 },
158 {
159 "name": "vae",
160 "type": "VAE",
161 "link": 136
162 }
163 ],
164 "outputs": [
165 {
166 "name": "IMAGE",
167 "type": "IMAGE",
168 "slot_index": 0,
169 "links": [
170 143
171 ]
172 }
173 ],
174 "properties": {
175 "cnr_id": "comfy-core",
176 "ver": "0.3.59",
177 "Node name for S&R": "VAEDecode"
178 },
179 "widgets_values": []
180 },
181 {
182 "id": 61,
183 "type": "LoraLoaderModelOnly",
184 "pos": [
185 -50,
186 84
187 ],
188 "size": [
189 390,
190 82
191 ],
192 "flags": [],
193 "order": 12,
194 "mode": 0,
195 "inputs": [
196 {
197 "name": "model",
198 "type": "MODEL",
199 "link": 122
200 }
201 ],
202 "outputs": [
203 {
204 "name": "MODEL",
205 "type": "MODEL",
206 "links": [
207 124
208 ]
209 }
210 ],
211 "properties": {
212 "cnr_id": "comfy-core",
213 "ver": "0.3.59",
214 "Node name for S&R": "LoraLoaderModelOnly",
215 "models": [
216 {
217 "name": "lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
218 "url": "https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
219 "directory": "loras"
220 }
221 ]
222 },
223 "widgets_values": [
224 "lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
225 1
226 ]
227 },
228 {
229 "id": 37,
230 "type": "UNETLoader",
231 "pos": [
232 -50,
233 -40
234 ],
235 "size": [
236 390,
237 82
238 ],
239 "flags": [],
240 "order": 2,
241 "mode": 0,
242 "inputs": [],
243 "outputs": [
244 {
245 "name": "MODEL",
246 "type": "MODEL",
247 "slot_index": 0,
248 "links": [
249 122
250 ]
251 }
252 ],
253 "properties": {
254 "cnr_id": "comfy-core",
255 "ver": "0.3.59",
256 "Node name for S&R": "UNETLoader",
257 "models": [
258 {
259 "name": "humo_17B_fp8_e4m3fn.safetensors",
260 "url": "https://huggingface.co/Comfy-Org/HuMo_ComfyUI/resolve/main/split_files/diffusion_models/humo_17B_fp8_e4m3fn.safetensors",
261 "directory": "diffusion_models"
262 }
263 ]
264 },
265 "widgets_values": [
266 "humo_17B_fp8_e4m3fn.safetensors",
267 "default"
268 ]
269 },
270 {
271 "id": 65,
272 "type": "WanHuMoImageToVideo",
273 "pos": [
274 850,
275 -30
276 ],
277 "size": [
278 270,
279 210
280 ],
281 "flags": [],
282 "order": 15,
283 "mode": 0,
284 "inputs": [
285 {
286 "name": "positive",
287 "type": "CONDITIONING",
288 "link": 139
289 },
290 {
291 "name": "negative",
292 "type": "CONDITIONING",
293 "link": 140
294 },
295 {
296 "name": "vae",
297 "type": "VAE",
298 "link": 137
299 },
300 {
301 "name": "audio_encoder_output",
302 "shape": 7,
303 "type": "AUDIO_ENCODER_OUTPUT",
304 "link": 141
305 },
306 {
307 "name": "ref_image",
308 "shape": 7,
309 "type": "IMAGE",
310 "link": 142
311 }
312 ],
313 "outputs": [
314 {
315 "name": "positive",
316 "type": "CONDITIONING",
317 "links": [
318 133
319 ]
320 },
321 {
322 "name": "negative",
323 "type": "CONDITIONING",
324 "links": [
325 134
326 ]
327 },
328 {
329 "name": "latent",
330 "type": "LATENT",
331 "links": [
332 135
333 ]
334 }
335 ],
336 "properties": {
337 "cnr_id": "comfy-core",
338 "ver": "0.3.59",
339 "Node name for S&R": "WanHuMoImageToVideo"
340 },
341 "widgets_values": [
342 640,
343 640,
344 97,
345 1
346 ]
347 },
348 {
349 "id": 56,
350 "type": "AudioEncoderEncode",
351 "pos": [
352 850,
353 780
354 ],
355 "size": [
356 285.087890625,
357 60
358 ],
359 "flags": {
360 "collapsed": false
361 },
362 "order": 13,
363 "mode": 0,
364 "inputs": [
365 {
366 "name": "audio_encoder",
367 "type": "AUDIO_ENCODER",
368 "link": 115
369 },
370 {
371 "name": "audio",
372 "type": "AUDIO",
373 "link": 147
374 }
375 ],
376 "outputs": [
377 {
378 "name": "AUDIO_ENCODER_OUTPUT",
379 "type": "AUDIO_ENCODER_OUTPUT",
380 "links": [
381 141
382 ]
383 }
384 ],
385 "properties": {
386 "cnr_id": "comfy-core",
387 "ver": "0.3.59",
388 "Node name for S&R": "AudioEncoderEncode"
389 },
390 "widgets_values": []
391 },
392 {
393 "id": 57,
394 "type": "AudioEncoderLoader",
395 "pos": [
396 -50,
397 456
398 ],
399 "size": [
400 390,
401 60
402 ],
403 "flags": [],
404 "order": 3,
405 "mode": 0,
406 "inputs": [],
407 "outputs": [
408 {
409 "name": "AUDIO_ENCODER",
410 "type": "AUDIO_ENCODER",
411 "links": [
412 115
413 ]
414 }
415 ],
416 "properties": {
417 "cnr_id": "comfy-core",
418 "ver": "0.3.59",
419 "Node name for S&R": "AudioEncoderLoader",
420 "models": [
421 {
422 "name": "whisper_large_v3_fp16.safetensors",
423 "url": "https://huggingface.co/Comfy-Org/HuMo_ComfyUI/resolve/main/split_files/audio_encoders/whisper_large_v3_fp16.safetensors",
424 "directory": "audio_encoders"
425 }
426 ]
427 },
428 "widgets_values": [
429 "whisper_large_v3_fp16.safetensors"
430 ]
431 },
432 {
433 "id": 66,
434 "type": "MarkdownNote",
435 "pos": [
436 -590,
437 70
438 ],
439 "size": [
440 500,
441 490
442 ],
443 "flags": [],
444 "order": 4,
445 "mode": 0,
446 "inputs": [],
447 "outputs": [],
448 "title": "Note: Model links",
449 "properties": [],
450 "widgets_values": [
451 "\n## Model links\n\n- [Hugging Face:Comfy-Org/HuMo_ComfyUI](https://huggingface.co/Comfy-Org/HuMo_ComfyUI)\n- [ModelScope:Comfy-Org/HuMo_ComfyUI](https://modelscope.cn/models/Comfy-Org/HuMo_ComfyUI)\n- [Hugging Face:Comfy-Org/Wan_2.1_ComfyUI_repackaged](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged)\n- [ModelScope:Comfy-Org/Wan_2.1_ComfyUI_repackaged](https://modelscope.cn/models/Comfy-Org/Wan_2.1_ComfyUI_repackaged)\n- [Hugging Face:Comfy-Org/Wan_2.2_ComfyUI_Repackaged](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged)\n- [ModelScope:Comfy-Org/Wan_2.2_ComfyUI_Repackaged](https://modelscope.cn/models/Comfy-Org/Wan_2.2_ComfyUI_Repackaged)\n\n\n**diffusion_models**\n\n- [humo_17B_fp8_e4m3fn.safetensors](https://huggingface.co/Comfy-Org/HuMo_ComfyUI/resolve/main/split_files/diffusion_models/humo_17B_fp8_e4m3fn.safetensors) (15.89 GB)\n\n**loras**\n- [lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors) (703.8 MB)\n\n**text_encoders**\n- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors) (6.27 GB)\n\n**vae**\n- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors) (242.1 MB)\n\n**audio_encoders**\n- [whisper_large_v3_fp16.safetensors](https://huggingface.co/Comfy-Org/HuMo_ComfyUI/resolve/main/split_files/audio_encoders/whisper_large_v3_fp16.safetensors) (2.88 GB)\n\n\n```\n📂 ComfyUI/\n├─ 📂 models/\n│ ├─ 📂 diffusion_models/\n│ │ └── humo_17B_fp8_e4m3fn.safetensors\n│ ├─ 📂 text_encoders/\n│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ ├─ 📂 audio_encoders/\n│ │ └── whisper_large_v3_fp16.safetensors \n│ └─ 📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n"
452 ],
453 "color": "#222",
454 "bgcolor": "#000"
455 },
456 {
457 "id": 6,
458 "type": "CLIPTextEncode",
459 "pos": [
460 380,
461 60
462 ],
463 "size": [
464 420,
465 220
466 ],
467 "flags": [],
468 "order": 10,
469 "mode": 0,
470 "inputs": [
471 {
472 "name": "clip",
473 "type": "CLIP",
474 "link": 74
475 }
476 ],
477 "outputs": [
478 {
479 "name": "CONDITIONING",
480 "type": "CONDITIONING",
481 "slot_index": 0,
482 "links": [
483 139
484 ]
485 }
486 ],
487 "title": "CLIP Text Encode (Positive Prompt)",
488 "properties": {
489 "cnr_id": "comfy-core",
490 "ver": "0.3.59",
491 "Node name for S&R": "CLIPTextEncode"
492 },
493 "widgets_values": [
494 "A young boy in sci-fi style clothing is talking to the camera in an alien desert."
495 ],
496 "color": "#232",
497 "bgcolor": "#353"
498 },
499 {
500 "id": 64,
501 "type": "KSampler",
502 "pos": [
503 840,
504 250
505 ],
506 "size": [
507 270,
508 474
509 ],
510 "flags": [],
511 "order": 16,
512 "mode": 0,
513 "inputs": [
514 {
515 "name": "model",
516 "type": "MODEL",
517 "link": 138
518 },
519 {
520 "name": "positive",
521 "type": "CONDITIONING",
522 "link": 133
523 },
524 {
525 "name": "negative",
526 "type": "CONDITIONING",
527 "link": 134
528 },
529 {
530 "name": "latent_image",
531 "type": "LATENT",
532 "link": 135
533 }
534 ],
535 "outputs": [
536 {
537 "name": "LATENT",
538 "type": "LATENT",
539 "slot_index": 0,
540 "links": [
541 132
542 ]
543 }
544 ],
545 "properties": {
546 "cnr_id": "comfy-core",
547 "ver": "0.3.59",
548 "Node name for S&R": "KSampler"
549 },
550 "widgets_values": [
551 1067760026265042,
552 "randomize",
553 6,
554 1,
555 "uni_pc",
556 "simple",
557 1
558 ]
559 },
560 {
561 "id": 48,
562 "type": "ModelSamplingSD3",
563 "pos": [
564 420,
565 -90
566 ],
567 "size": [
568 280,
569 58
570 ],
571 "flags": [],
572 "order": 14,
573 "mode": 0,
574 "inputs": [
575 {
576 "name": "model",
577 "type": "MODEL",
578 "link": 124
579 }
580 ],
581 "outputs": [
582 {
583 "name": "MODEL",
584 "type": "MODEL",
585 "slot_index": 0,
586 "links": [
587 138
588 ]
589 }
590 ],
591 "properties": {
592 "cnr_id": "comfy-core",
593 "ver": "0.3.59",
594 "Node name for S&R": "ModelSamplingSD3"
595 },
596 "widgets_values": [
597 8
598 ]
599 },
600 {
601 "id": 67,
602 "type": "MarkdownNote",
603 "pos": [
604 -590,
605 -90
606 ],
607 "size": [
608 500,
609 120
610 ],
611 "flags": [],
612 "order": 5,
613 "mode": 0,
614 "inputs": [],
615 "outputs": [],
616 "title": "Note: About HuMo",
617 "properties": [],
618 "widgets_values": [
619 "HuMo is a human-centric video generation tool that creates controllable, high-quality human videos from multimodal inputs (text, images, audio), supporting text-image guided customization, text-audio driven audio-motion sync, and 480P(832x480)/720P(1280x720) resolutions.\n"
620 ],
621 "color": "#222",
622 "bgcolor": "#000"
623 },
624 {
625 "id": 75,
626 "type": "MarkdownNote",
627 "pos": [
628 380,
629 1020
630 ],
631 "size": [
632 430,
633 100
634 ],
635 "flags": [],
636 "order": 6,
637 "mode": 0,
638 "inputs": [],
639 "outputs": [],
640 "title": "Note: About HuMo",
641 "properties": [],
642 "widgets_values": [
643 "If you want to use your recorded audio, please connect the audio output to the nodes that were previously linked to the LoadAudio node."
644 ],
645 "color": "#222",
646 "bgcolor": "#000"
647 },
648 {
649 "id": 7,
650 "type": "CLIPTextEncode",
651 "pos": [
652 380,
653 320
654 ],
655 "size": [
656 425.27801513671875,
657 180.6060791015625
658 ],
659 "flags": [],
660 "order": 11,
661 "mode": 0,
662 "inputs": [
663 {
664 "name": "clip",
665 "type": "CLIP",
666 "link": 75
667 }
668 ],
669 "outputs": [
670 {
671 "name": "CONDITIONING",
672 "type": "CONDITIONING",
673 "slot_index": 0,
674 "links": [
675 140
676 ]
677 }
678 ],
679 "title": "CLIP Text Encode (Negative Prompt)",
680 "properties": {
681 "cnr_id": "comfy-core",
682 "ver": "0.3.59",
683 "Node name for S&R": "CLIPTextEncode"
684 },
685 "widgets_values": [
686 "色调艳丽,过曝,静态,细节模糊不清,字幕,风格,作品,画作,画面,静止,整体发灰,最差质量,低质量,JPEG压缩残留,丑陋的,残缺的,多余的手指,画得不好的手部,画得不好的脸部,畸形的,毁容的,形态畸形的肢体,手指融合,静止不动的画面,杂乱的背景,三条腿,背景人很多,倒着走"
687 ],
688 "color": "#223",
689 "bgcolor": "#335"
690 },
691 {
692 "id": 59,
693 "type": "SaveVideo",
694 "pos": [
695 1150,
696 -80
697 ],
698 "size": [
699 1070,
700 1168
701 ],
702 "flags": [],
703 "order": 19,
704 "mode": 0,
705 "inputs": [
706 {
707 "name": "video",
708 "type": "VIDEO",
709 "link": 119
710 }
711 ],
712 "outputs": [],
713 "properties": {
714 "cnr_id": "comfy-core",
715 "ver": "0.3.59",
716 "Node name for S&R": "SaveVideo"
717 },
718 "widgets_values": [
719 "video/ComfyUI",
720 "auto",
721 "auto"
722 ]
723 },
724 {
725 "id": 68,
726 "type": "RecordAudio",
727 "pos": [
728 440,
729 830
730 ],
731 "size": [
732 270,
733 112
734 ],
735 "flags": [],
736 "order": 7,
737 "mode": 4,
738 "inputs": [],
739 "outputs": [
740 {
741 "name": "AUDIO",
742 "type": "AUDIO",
743 "links": []
744 }
745 ],
746 "properties": {
747 "cnr_id": "comfy-core",
748 "ver": "0.3.59",
749 "Node name for S&R": "RecordAudio"
750 },
751 "widgets_values": [
752 "",
753 ""
754 ]
755 },
756 {
757 "id": 49,
758 "type": "LoadImage",
759 "pos": [
760 10,
761 640
762 ],
763 "size": [
764 274.080078125,
765 314.00006103515625
766 ],
767 "flags": [],
768 "order": 8,
769 "mode": 0,
770 "inputs": [],
771 "outputs": [
772 {
773 "name": "IMAGE",
774 "type": "IMAGE",
775 "links": [
776 142
777 ]
778 },
779 {
780 "name": "MASK",
781 "type": "MASK",
782 "links": null
783 }
784 ],
785 "properties": {
786 "cnr_id": "comfy-core",
787 "ver": "0.3.59",
788 "Node name for S&R": "LoadImage"
789 },
790 "widgets_values": [
791 "video_humo_reference_image.png",
792 "image"
793 ]
794 },
795 {
796 "id": 58,
797 "type": "LoadAudio",
798 "pos": [
799 430,
800 640
801 ],
802 "size": [
803 285.087890625,
804 136
805 ],
806 "flags": [],
807 "order": 9,
808 "mode": 0,
809 "inputs": [],
810 "outputs": [
811 {
812 "name": "AUDIO",
813 "type": "AUDIO",
814 "links": [
815 120,
816 147
817 ]
818 }
819 ],
820 "properties": {
821 "cnr_id": "comfy-core",
822 "ver": "0.3.59",
823 "Node name for S&R": "LoadAudio"
824 },
825 "widgets_values": [
826 "video_humo_input_audio.wav",
827 null,
828 null
829 ]
830 }
831 ],
832 "links": [
833 [
834 74,
835 38,
836 0,
837 6,
838 0,
839 "CLIP"
840 ],
841 [
842 75,
843 38,
844 0,
845 7,
846 0,
847 "CLIP"
848 ],
849 [
850 115,
851 57,
852 0,
853 56,
854 0,
855 "AUDIO_ENCODER"
856 ],
857 [
858 119,
859 60,
860 0,
861 59,
862 0,
863 "VIDEO"
864 ],
865 [
866 120,
867 58,
868 0,
869 60,
870 1,
871 "AUDIO"
872 ],
873 [
874 122,
875 37,
876 0,
877 61,
878 0,
879 "MODEL"
880 ],
881 [
882 124,
883 61,
884 0,
885 48,
886 0,
887 "MODEL"
888 ],
889 [
890 132,
891 64,
892 0,
893 63,
894 0,
895 "LATENT"
896 ],
897 [
898 133,
899 65,
900 0,
901 64,
902 1,
903 "CONDITIONING"
904 ],
905 [
906 134,
907 65,
908 1,
909 64,
910 2,
911 "CONDITIONING"
912 ],
913 [
914 135,
915 65,
916 2,
917 64,
918 3,
919 "LATENT"
920 ],
921 [
922 136,
923 39,
924 0,
925 63,
926 1,
927 "VAE"
928 ],
929 [
930 137,
931 39,
932 0,
933 65,
934 2,
935 "VAE"
936 ],
937 [
938 138,
939 48,
940 0,
941 64,
942 0,
943 "MODEL"
944 ],
945 [
946 139,
947 6,
948 0,
949 65,
950 0,
951 "CONDITIONING"
952 ],
953 [
954 140,
955 7,
956 0,
957 65,
958 1,
959 "CONDITIONING"
960 ],
961 [
962 141,
963 56,
964 0,
965 65,
966 3,
967 "AUDIO_ENCODER_OUTPUT"
968 ],
969 [
970 142,
971 49,
972 0,
973 65,
974 4,
975 "IMAGE"
976 ],
977 [
978 143,
979 63,
980 0,
981 60,
982 0,
983 "IMAGE"
984 ],
985 [
986 147,
987 58,
988 0,
989 56,
990 1,
991 "AUDIO"
992 ]
993 ],
994 "groups": [
995 {
996 "id": 1,
997 "title": "Step 1 - Load models",
998 "bounding": [
999 -70,
1000 -120,
1001 430,
1002 660
1003 ],
1004 "color": "#3f789e",
1005 "font_size": 24,
1006 "flags": []
1007 },
1008 {
1009 "id": 2,
1010 "title": "Step 4 - Prompt",
1011 "bounding": [
1012 370,
1013 -10,
1014 450,
1015 550
1016 ],
1017 "color": "#3f789e",
1018 "font_size": 24,
1019 "flags": []
1020 },
1021 {
1022 "id": 3,
1023 "title": "Step 3 - Upload or record audio",
1024 "bounding": [
1025 370,
1026 550,
1027 450,
1028 420
1029 ],
1030 "color": "#3f789e",
1031 "font_size": 24,
1032 "flags": []
1033 },
1034 {
1035 "id": 4,
1036 "title": "Step2 - Upload reference image",
1037 "bounding": [
1038 -70,
1039 550,
1040 430,
1041 420
1042 ],
1043 "color": "#3f789e",
1044 "font_size": 24,
1045 "flags": []
1046 },
1047 {
1048 "id": 5,
1049 "title": "Step 5 - Video size",
1050 "bounding": [
1051 840,
1052 -100,
1053 290,
1054 293.6000061035156
1055 ],
1056 "color": "#3f789e",
1057 "font_size": 24,
1058 "flags": []
1059 }
1060 ],
1061 "config": [],
1062 "extra": {
1063 "ds": {
1064 "scale": 0.5024794688220987,
1065 "offset": [
1066 748.712585289151,
1067 452.86254113586153
1068 ]
1069 },
1070 "frontendVersion": "1.27.10",
1071 "VHS_latentpreview": false,
1072 "VHS_latentpreviewrate": 0,
1073 "VHS_MetadataImage": true,
1074 "VHS_KeepIntermediate": true
1075 },
1076 "version": 0.4
1077}