工作流 /
视频 /
SVD 文生图到图生视频
SVD 文生图到图生视频
SVD Text to Image to Video
通过首先从文本提示创建图像来生成视频。
视频
15 个节点 17 次使用 ComfyUI ≥ 0.3.31 ComfyUI 14 KB
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。
节点构成
KSampler
× 2
CLIPTextEncode
× 2
VAEDecode
× 2
EmptyLatentImage
× 1
CheckpointLoaderSimple
× 1
SVD_img2vid_Conditioning
× 1
VideoLinearCFGGuidance
× 1
ImageOnlyCheckpointLoader
× 1
CreateVideo
× 1
PreviewImage
× 1
MarkdownNote
× 1
SaveVideo
× 1
官方标注的模型
SVDStability
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "858d315b-00e0-4802-b61b-fadbacbedaaf",
3 "revision": 0,
4 "last_node_id": 25,
5 "last_link_id": 42,
6 "nodes": [
7 {
8 "id": 3,
9 "type": "KSampler",
10 "pos": [
11 720,
12 1180
13 ],
14 "size": [
15 315,
16 262
17 ],
18 "flags": [],
19 "order": 11,
20 "mode": 0,
21 "inputs": [
22 {
23 "name": "model",
24 "type": "MODEL",
25 "link": 39
26 },
27 {
28 "name": "positive",
29 "type": "CONDITIONING",
30 "link": 40
31 },
32 {
33 "name": "negative",
34 "type": "CONDITIONING",
35 "link": 17
36 },
37 {
38 "name": "latent_image",
39 "type": "LATENT",
40 "link": 18
41 }
42 ],
43 "outputs": [
44 {
45 "name": "LATENT",
46 "type": "LATENT",
47 "slot_index": 0,
48 "links": [
49 7
50 ]
51 }
52 ],
53 "properties": {
54 "Node name for S&R": "KSampler"
55 },
56 "widgets_values": [
57 237514639057514,
58 "randomize",
59 20,
60 2.5,
61 "euler",
62 "karras",
63 1
64 ]
65 },
66 {
67 "id": 18,
68 "type": "CLIPTextEncode",
69 "pos": [
70 342.3999938964844,
71 516.4000244140625
72 ],
73 "size": [
74 390,
75 130
76 ],
77 "flags": [],
78 "order": 4,
79 "mode": 0,
80 "inputs": [
81 {
82 "name": "clip",
83 "type": "CLIP",
84 "link": 29
85 }
86 ],
87 "outputs": [
88 {
89 "name": "CONDITIONING",
90 "type": "CONDITIONING",
91 "slot_index": 0,
92 "links": [
93 30
94 ]
95 }
96 ],
97 "properties": {
98 "Node name for S&R": "CLIPTextEncode"
99 },
100 "widgets_values": [
101 "photograph beautiful scenery nature mountains alps river rapids snow sky cumulus clouds"
102 ]
103 },
104 {
105 "id": 19,
106 "type": "CLIPTextEncode",
107 "pos": [
108 342.3999938964844,
109 696.4000244140625
110 ],
111 "size": [
112 390,
113 130
114 ],
115 "flags": [],
116 "order": 5,
117 "mode": 0,
118 "inputs": [
119 {
120 "name": "clip",
121 "type": "CLIP",
122 "link": 31
123 }
124 ],
125 "outputs": [
126 {
127 "name": "CONDITIONING",
128 "type": "CONDITIONING",
129 "slot_index": 0,
130 "links": [
131 32
132 ]
133 }
134 ],
135 "properties": {
136 "Node name for S&R": "CLIPTextEncode"
137 },
138 "widgets_values": [
139 "text, watermark"
140 ]
141 },
142 {
143 "id": 22,
144 "type": "EmptyLatentImage",
145 "pos": [
146 422.3999938964844,
147 866.4000244140625
148 ],
149 "size": [
150 310,
151 110
152 ],
153 "flags": [],
154 "order": 0,
155 "mode": 0,
156 "inputs": [],
157 "outputs": [
158 {
159 "name": "LATENT",
160 "type": "LATENT",
161 "links": [
162 37
163 ]
164 }
165 ],
166 "properties": {
167 "Node name for S&R": "EmptyLatentImage"
168 },
169 "widgets_values": [
170 1024,
171 576,
172 1
173 ]
174 },
175 {
176 "id": 16,
177 "type": "CheckpointLoaderSimple",
178 "pos": [
179 -10,
180 470
181 ],
182 "size": [
183 315,
184 98
185 ],
186 "flags": [],
187 "order": 1,
188 "mode": 0,
189 "inputs": [],
190 "outputs": [
191 {
192 "name": "MODEL",
193 "type": "MODEL",
194 "slot_index": 0,
195 "links": [
196 28
197 ]
198 },
199 {
200 "name": "CLIP",
201 "type": "CLIP",
202 "slot_index": 1,
203 "links": [
204 29,
205 31
206 ]
207 },
208 {
209 "name": "VAE",
210 "type": "VAE",
211 "links": [
212 34
213 ]
214 }
215 ],
216 "properties": {
217 "Node name for S&R": "CheckpointLoaderSimple",
218 "models": [
219 {
220 "name": "sd_xl_base_1.0.safetensors",
221 "url": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors?download=true",
222 "directory": "checkpoints"
223 }
224 ]
225 },
226 "widgets_values": [
227 "sd_xl_base_1.0.safetensors"
228 ]
229 },
230 {
231 "id": 8,
232 "type": "VAEDecode",
233 "pos": [
234 1060,
235 1180
236 ],
237 "size": [
238 210,
239 46
240 ],
241 "flags": [],
242 "order": 12,
243 "mode": 0,
244 "inputs": [
245 {
246 "name": "samples",
247 "type": "LATENT",
248 "link": 7
249 },
250 {
251 "name": "vae",
252 "type": "VAE",
253 "link": 26
254 }
255 ],
256 "outputs": [
257 {
258 "name": "IMAGE",
259 "type": "IMAGE",
260 "slot_index": 0,
261 "links": [
262 41
263 ]
264 }
265 ],
266 "properties": {
267 "Node name for S&R": "VAEDecode"
268 },
269 "widgets_values": []
270 },
271 {
272 "id": 12,
273 "type": "SVD_img2vid_Conditioning",
274 "pos": [
275 370,
276 1200
277 ],
278 "size": [
279 315,
280 218
281 ],
282 "flags": [],
283 "order": 9,
284 "mode": 0,
285 "inputs": [
286 {
287 "name": "clip_vision",
288 "type": "CLIP_VISION",
289 "link": 24
290 },
291 {
292 "name": "init_image",
293 "type": "IMAGE",
294 "link": 35
295 },
296 {
297 "name": "vae",
298 "type": "VAE",
299 "link": 25
300 }
301 ],
302 "outputs": [
303 {
304 "name": "positive",
305 "type": "CONDITIONING",
306 "slot_index": 0,
307 "links": [
308 40
309 ]
310 },
311 {
312 "name": "negative",
313 "type": "CONDITIONING",
314 "slot_index": 1,
315 "links": [
316 17
317 ]
318 },
319 {
320 "name": "latent",
321 "type": "LATENT",
322 "slot_index": 2,
323 "links": [
324 18
325 ]
326 }
327 ],
328 "properties": {
329 "Node name for S&R": "SVD_img2vid_Conditioning"
330 },
331 "widgets_values": [
332 1024,
333 576,
334 25,
335 127,
336 6,
337 0
338 ]
339 },
340 {
341 "id": 14,
342 "type": "VideoLinearCFGGuidance",
343 "pos": [
344 720,
345 1080
346 ],
347 "size": [
348 315,
349 58
350 ],
351 "flags": [],
352 "order": 6,
353 "mode": 0,
354 "inputs": [
355 {
356 "name": "model",
357 "type": "MODEL",
358 "link": 23
359 }
360 ],
361 "outputs": [
362 {
363 "name": "MODEL",
364 "type": "MODEL",
365 "slot_index": 0,
366 "links": [
367 39
368 ]
369 }
370 ],
371 "properties": {
372 "Node name for S&R": "VideoLinearCFGGuidance"
373 },
374 "widgets_values": [
375 1
376 ]
377 },
378 {
379 "id": 15,
380 "type": "ImageOnlyCheckpointLoader",
381 "pos": [
382 -50,
383 1040
384 ],
385 "size": [
386 369.6000061035156,
387 98
388 ],
389 "flags": [],
390 "order": 2,
391 "mode": 0,
392 "inputs": [],
393 "outputs": [
394 {
395 "name": "MODEL",
396 "type": "MODEL",
397 "slot_index": 0,
398 "links": [
399 23
400 ]
401 },
402 {
403 "name": "CLIP_VISION",
404 "type": "CLIP_VISION",
405 "slot_index": 1,
406 "links": [
407 24
408 ]
409 },
410 {
411 "name": "VAE",
412 "type": "VAE",
413 "slot_index": 2,
414 "links": [
415 25,
416 26
417 ]
418 }
419 ],
420 "properties": {
421 "Node name for S&R": "ImageOnlyCheckpointLoader",
422 "models": [
423 {
424 "name": "svd_xt.safetensors",
425 "url": "https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/resolve/main/svd_xt.safetensors?download=true",
426 "directory": "checkpoints"
427 }
428 ]
429 },
430 "widgets_values": [
431 "svd_xt.safetensors"
432 ]
433 },
434 {
435 "id": 25,
436 "type": "CreateVideo",
437 "pos": [
438 1060,
439 1270
440 ],
441 "size": [
442 210,
443 90
444 ],
445 "flags": [],
446 "order": 13,
447 "mode": 0,
448 "inputs": [
449 {
450 "name": "images",
451 "type": "IMAGE",
452 "link": 41
453 },
454 {
455 "name": "audio",
456 "shape": 7,
457 "type": "AUDIO",
458 "link": null
459 }
460 ],
461 "outputs": [
462 {
463 "name": "VIDEO",
464 "type": "VIDEO",
465 "links": [
466 42
467 ]
468 }
469 ],
470 "properties": {
471 "Node name for S&R": "CreateVideo"
472 },
473 "widgets_values": [
474 10
475 ]
476 },
477 {
478 "id": 17,
479 "type": "KSampler",
480 "pos": [
481 770,
482 520
483 ],
484 "size": [
485 315,
486 262
487 ],
488 "flags": [],
489 "order": 7,
490 "mode": 0,
491 "inputs": [
492 {
493 "name": "model",
494 "type": "MODEL",
495 "link": 28
496 },
497 {
498 "name": "positive",
499 "type": "CONDITIONING",
500 "link": 30
501 },
502 {
503 "name": "negative",
504 "type": "CONDITIONING",
505 "link": 32
506 },
507 {
508 "name": "latent_image",
509 "type": "LATENT",
510 "link": 37
511 }
512 ],
513 "outputs": [
514 {
515 "name": "LATENT",
516 "type": "LATENT",
517 "slot_index": 0,
518 "links": [
519 33
520 ]
521 }
522 ],
523 "properties": {
524 "Node name for S&R": "KSampler"
525 },
526 "widgets_values": [
527 144698910769133,
528 "randomize",
529 15,
530 8,
531 "uni_pc_bh2",
532 "normal",
533 1
534 ]
535 },
536 {
537 "id": 20,
538 "type": "VAEDecode",
539 "pos": [
540 770,
541 830
542 ],
543 "size": [
544 210,
545 46
546 ],
547 "flags": [],
548 "order": 8,
549 "mode": 0,
550 "inputs": [
551 {
552 "name": "samples",
553 "type": "LATENT",
554 "link": 33
555 },
556 {
557 "name": "vae",
558 "type": "VAE",
559 "link": 34
560 }
561 ],
562 "outputs": [
563 {
564 "name": "IMAGE",
565 "type": "IMAGE",
566 "slot_index": 0,
567 "links": [
568 35,
569 36
570 ]
571 }
572 ],
573 "properties": {
574 "Node name for S&R": "VAEDecode"
575 },
576 "widgets_values": []
577 },
578 {
579 "id": 21,
580 "type": "PreviewImage",
581 "pos": [
582 1100,
583 520
584 ],
585 "size": [
586 275.95001220703125,
587 246
588 ],
589 "flags": [],
590 "order": 10,
591 "mode": 0,
592 "inputs": [
593 {
594 "name": "images",
595 "type": "IMAGE",
596 "link": 36
597 }
598 ],
599 "outputs": [],
600 "properties": {
601 "Node name for S&R": "PreviewImage"
602 },
603 "widgets_values": []
604 },
605 {
606 "id": 23,
607 "type": "MarkdownNote",
608 "pos": [
609 -270,
610 470
611 ],
612 "size": [
613 225,
614 88
615 ],
616 "flags": [],
617 "order": 3,
618 "mode": 0,
619 "inputs": [],
620 "outputs": [],
621 "properties": [],
622 "widgets_values": [
623 "🛈 [Learn more about this workflow](https://comfyanonymous.github.io/ComfyUI_examples/video/#image-to-video)"
624 ],
625 "color": "#222",
626 "bgcolor": "#000"
627 },
628 {
629 "id": 24,
630 "type": "SaveVideo",
631 "pos": [
632 1430,
633 770
634 ],
635 "size": [
636 740,
637 690
638 ],
639 "flags": [],
640 "order": 14,
641 "mode": 0,
642 "inputs": [
643 {
644 "name": "video",
645 "type": "VIDEO",
646 "link": 42
647 }
648 ],
649 "outputs": [],
650 "properties": {
651 "Node name for S&R": "SaveVideo"
652 },
653 "widgets_values": [
654 "video/ComfyUI",
655 "auto",
656 "auto"
657 ]
658 }
659 ],
660 "links": [
661 [
662 7,
663 3,
664 0,
665 8,
666 0,
667 "LATENT"
668 ],
669 [
670 17,
671 12,
672 1,
673 3,
674 2,
675 "CONDITIONING"
676 ],
677 [
678 18,
679 12,
680 2,
681 3,
682 3,
683 "LATENT"
684 ],
685 [
686 23,
687 15,
688 0,
689 14,
690 0,
691 "MODEL"
692 ],
693 [
694 24,
695 15,
696 1,
697 12,
698 0,
699 "CLIP_VISION"
700 ],
701 [
702 25,
703 15,
704 2,
705 12,
706 2,
707 "VAE"
708 ],
709 [
710 26,
711 15,
712 2,
713 8,
714 1,
715 "VAE"
716 ],
717 [
718 28,
719 16,
720 0,
721 17,
722 0,
723 "MODEL"
724 ],
725 [
726 29,
727 16,
728 1,
729 18,
730 0,
731 "CLIP"
732 ],
733 [
734 30,
735 18,
736 0,
737 17,
738 1,
739 "CONDITIONING"
740 ],
741 [
742 31,
743 16,
744 1,
745 19,
746 0,
747 "CLIP"
748 ],
749 [
750 32,
751 19,
752 0,
753 17,
754 2,
755 "CONDITIONING"
756 ],
757 [
758 33,
759 17,
760 0,
761 20,
762 0,
763 "LATENT"
764 ],
765 [
766 34,
767 16,
768 2,
769 20,
770 1,
771 "VAE"
772 ],
773 [
774 35,
775 20,
776 0,
777 12,
778 1,
779 "IMAGE"
780 ],
781 [
782 36,
783 20,
784 0,
785 21,
786 0,
787 "IMAGE"
788 ],
789 [
790 37,
791 22,
792 0,
793 17,
794 3,
795 "LATENT"
796 ],
797 [
798 39,
799 14,
800 0,
801 3,
802 0,
803 "MODEL"
804 ],
805 [
806 40,
807 12,
808 0,
809 3,
810 1,
811 "CONDITIONING"
812 ],
813 [
814 41,
815 8,
816 0,
817 25,
818 0,
819 "IMAGE"
820 ],
821 [
822 42,
823 25,
824 0,
825 24,
826 0,
827 "VIDEO"
828 ]
829 ],
830 "groups": [
831 {
832 "id": 1,
833 "title": "Image to Video",
834 "bounding": [
835 340,
836 1000,
837 1060,
838 460
839 ],
840 "color": "#8A8",
841 "font_size": 24,
842 "flags": []
843 },
844 {
845 "id": 2,
846 "title": "Text to Image",
847 "bounding": [
848 330,
849 440,
850 1070,
851 540
852 ],
853 "color": "#3f789e",
854 "font_size": 24,
855 "flags": []
856 }
857 ],
858 "config": [],
859 "extra": {
860 "ds": {
861 "scale": 0.3960581064139741,
862 "offset": [
863 1152.773540720571,
864 -102.38984601593666
865 ]
866 },
867 "frontendVersion": "1.25.3"
868 },
869 "version": 0.4
870}