工作流 /
视频 /
Wan万相 2.1 图生视频
Wan万相 2.1 图生视频
Wan 2.1 Image to Video
使用Wan 2.1从图像生成视频。
视频
15 个节点 1 个输入 69 次使用 ComfyUI ≥ 0.3.31 ComfyUI 16 KB
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。
clip_vision_h.safetensors
在模型库查看
umt5_xxl_fp8_e4m3fn_scaled.safetensors
在模型库查看
wan2.1_i2v_480p_14B_fp16.safetensors
在模型库查看
wan_2.1_vae.safetensors
在模型库查看
节点构成
CLIPTextEncode
× 2
UNETLoader
× 1
CLIPLoader
× 1
VAELoader
× 1
CLIPVisionLoader
× 1
ModelSamplingSD3
× 1
CreateVideo
× 1
KSampler
× 1
VAEDecode
× 1
SaveVideo
× 1
WanImageToVideo
× 1
CLIPVisionEncode
× 1
MarkdownNote
× 1
LoadImage
× 1
官方标注的模型
Wan2.1Wan
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "469720c1-eccb-42bf-835a-f2976736e0bf",
3 "revision": 0,
4 "last_node_id": 57,
5 "last_link_id": 113,
6 "nodes": [
7 {
8 "id": 37,
9 "type": "UNETLoader",
10 "pos": [
11 20,
12 70
13 ],
14 "size": [
15 346.7470703125,
16 82
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": [
28 110
29 ]
30 }
31 ],
32 "properties": {
33 "Node name for S&R": "UNETLoader",
34 "models": [
35 {
36 "name": "wan2.1_i2v_480p_14B_fp16.safetensors",
37 "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_i2v_480p_14B_fp16.safetensors",
38 "directory": "diffusion_models"
39 }
40 ]
41 },
42 "widgets_values": [
43 "wan2.1_i2v_480p_14B_fp16.safetensors",
44 "default"
45 ]
46 },
47 {
48 "id": 38,
49 "type": "CLIPLoader",
50 "pos": [
51 20,
52 190
53 ],
54 "size": [
55 350,
56 110
57 ],
58 "flags": [],
59 "order": 1,
60 "mode": 0,
61 "inputs": [],
62 "outputs": [
63 {
64 "name": "CLIP",
65 "type": "CLIP",
66 "slot_index": 0,
67 "links": [
68 74,
69 75
70 ]
71 }
72 ],
73 "properties": {
74 "Node name for S&R": "CLIPLoader",
75 "models": [
76 {
77 "name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
78 "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors",
79 "directory": "text_encoders"
80 }
81 ]
82 },
83 "widgets_values": [
84 "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
85 "wan",
86 "default"
87 ]
88 },
89 {
90 "id": 39,
91 "type": "VAELoader",
92 "pos": [
93 20,
94 350
95 ],
96 "size": [
97 350,
98 60
99 ],
100 "flags": [],
101 "order": 2,
102 "mode": 0,
103 "inputs": [],
104 "outputs": [
105 {
106 "name": "VAE",
107 "type": "VAE",
108 "slot_index": 0,
109 "links": [
110 76,
111 99
112 ]
113 }
114 ],
115 "properties": {
116 "Node name for S&R": "VAELoader",
117 "models": [
118 {
119 "name": "wan_2.1_vae.safetensors",
120 "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors",
121 "directory": "vae"
122 }
123 ]
124 },
125 "widgets_values": [
126 "wan_2.1_vae.safetensors"
127 ]
128 },
129 {
130 "id": 49,
131 "type": "CLIPVisionLoader",
132 "pos": [
133 20,
134 460
135 ],
136 "size": [
137 350,
138 60
139 ],
140 "flags": [],
141 "order": 3,
142 "mode": 0,
143 "inputs": [],
144 "outputs": [
145 {
146 "name": "CLIP_VISION",
147 "type": "CLIP_VISION",
148 "slot_index": 0,
149 "links": [
150 94
151 ]
152 }
153 ],
154 "properties": {
155 "Node name for S&R": "CLIPVisionLoader",
156 "models": [
157 {
158 "name": "clip_vision_h.safetensors",
159 "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors",
160 "directory": "clip_vision"
161 }
162 ]
163 },
164 "widgets_values": [
165 "clip_vision_h.safetensors"
166 ]
167 },
168 {
169 "id": 6,
170 "type": "CLIPTextEncode",
171 "pos": [
172 410,
173 80
174 ],
175 "size": [
176 422.84503173828125,
177 164.31304931640625
178 ],
179 "flags": [],
180 "order": 7,
181 "mode": 0,
182 "inputs": [
183 {
184 "name": "clip",
185 "type": "CLIP",
186 "link": 74
187 }
188 ],
189 "outputs": [
190 {
191 "name": "CONDITIONING",
192 "type": "CONDITIONING",
193 "slot_index": 0,
194 "links": [
195 97
196 ]
197 }
198 ],
199 "title": "CLIP Text Encode (Positive Prompt)",
200 "properties": {
201 "Node name for S&R": "CLIPTextEncode"
202 },
203 "widgets_values": [
204 "a cute anime girl with massive fennec ears and a big fluffy tail wearing a maid outfit turning around"
205 ],
206 "color": "#232",
207 "bgcolor": "#353"
208 },
209 {
210 "id": 54,
211 "type": "ModelSamplingSD3",
212 "pos": [
213 860,
214 30
215 ],
216 "size": [
217 290,
218 60
219 ],
220 "flags": [],
221 "order": 6,
222 "mode": 0,
223 "inputs": [
224 {
225 "name": "model",
226 "type": "MODEL",
227 "link": 110
228 }
229 ],
230 "outputs": [
231 {
232 "name": "MODEL",
233 "type": "MODEL",
234 "slot_index": 0,
235 "links": [
236 111
237 ]
238 }
239 ],
240 "properties": {
241 "Node name for S&R": "ModelSamplingSD3"
242 },
243 "widgets_values": [
244 8
245 ]
246 },
247 {
248 "id": 55,
249 "type": "CreateVideo",
250 "pos": [
251 1190,
252 30
253 ],
254 "size": [
255 270,
256 78
257 ],
258 "flags": [],
259 "order": 13,
260 "mode": 0,
261 "inputs": [
262 {
263 "name": "images",
264 "type": "IMAGE",
265 "link": 112
266 },
267 {
268 "name": "audio",
269 "shape": 7,
270 "type": "AUDIO",
271 "link": null
272 }
273 ],
274 "outputs": [
275 {
276 "name": "VIDEO",
277 "type": "VIDEO",
278 "links": [
279 113
280 ]
281 }
282 ],
283 "properties": {
284 "Node name for S&R": "CreateVideo"
285 },
286 "widgets_values": [
287 16
288 ]
289 },
290 {
291 "id": 3,
292 "type": "KSampler",
293 "pos": [
294 860,
295 140
296 ],
297 "size": [
298 315,
299 262
300 ],
301 "flags": [],
302 "order": 11,
303 "mode": 0,
304 "inputs": [
305 {
306 "name": "model",
307 "type": "MODEL",
308 "link": 111
309 },
310 {
311 "name": "positive",
312 "type": "CONDITIONING",
313 "link": 101
314 },
315 {
316 "name": "negative",
317 "type": "CONDITIONING",
318 "link": 102
319 },
320 {
321 "name": "latent_image",
322 "type": "LATENT",
323 "link": 103
324 }
325 ],
326 "outputs": [
327 {
328 "name": "LATENT",
329 "type": "LATENT",
330 "slot_index": 0,
331 "links": [
332 35
333 ]
334 }
335 ],
336 "properties": {
337 "Node name for S&R": "KSampler"
338 },
339 "widgets_values": [
340 987948718394761,
341 "randomize",
342 20,
343 6,
344 "uni_pc",
345 "simple",
346 1
347 ]
348 },
349 {
350 "id": 8,
351 "type": "VAEDecode",
352 "pos": [
353 960,
354 450
355 ],
356 "size": [
357 210,
358 46
359 ],
360 "flags": [],
361 "order": 12,
362 "mode": 0,
363 "inputs": [
364 {
365 "name": "samples",
366 "type": "LATENT",
367 "link": 35
368 },
369 {
370 "name": "vae",
371 "type": "VAE",
372 "link": 76
373 }
374 ],
375 "outputs": [
376 {
377 "name": "IMAGE",
378 "type": "IMAGE",
379 "slot_index": 0,
380 "links": [
381 112
382 ]
383 }
384 ],
385 "properties": {
386 "Node name for S&R": "VAEDecode"
387 },
388 "widgets_values": []
389 },
390 {
391 "id": 56,
392 "type": "SaveVideo",
393 "pos": [
394 1200,
395 160
396 ],
397 "size": [
398 740,
399 540
400 ],
401 "flags": [],
402 "order": 14,
403 "mode": 0,
404 "inputs": [
405 {
406 "name": "video",
407 "type": "VIDEO",
408 "link": 113
409 }
410 ],
411 "outputs": [],
412 "properties": {
413 "Node name for S&R": "SaveVideo"
414 },
415 "widgets_values": [
416 "video/ComfyUI",
417 "auto",
418 "auto"
419 ]
420 },
421 {
422 "id": 50,
423 "type": "WanImageToVideo",
424 "pos": [
425 460,
426 560
427 ],
428 "size": [
429 320,
430 220
431 ],
432 "flags": [],
433 "order": 10,
434 "mode": 0,
435 "inputs": [
436 {
437 "name": "positive",
438 "type": "CONDITIONING",
439 "link": 97
440 },
441 {
442 "name": "negative",
443 "type": "CONDITIONING",
444 "link": 98
445 },
446 {
447 "name": "vae",
448 "type": "VAE",
449 "link": 99
450 },
451 {
452 "name": "clip_vision_output",
453 "shape": 7,
454 "type": "CLIP_VISION_OUTPUT",
455 "link": 107
456 },
457 {
458 "name": "start_image",
459 "shape": 7,
460 "type": "IMAGE",
461 "link": 106
462 }
463 ],
464 "outputs": [
465 {
466 "name": "positive",
467 "type": "CONDITIONING",
468 "slot_index": 0,
469 "links": [
470 101
471 ]
472 },
473 {
474 "name": "negative",
475 "type": "CONDITIONING",
476 "slot_index": 1,
477 "links": [
478 102
479 ]
480 },
481 {
482 "name": "latent",
483 "type": "LATENT",
484 "slot_index": 2,
485 "links": [
486 103
487 ]
488 }
489 ],
490 "properties": {
491 "Node name for S&R": "WanImageToVideo"
492 },
493 "widgets_values": [
494 512,
495 512,
496 33,
497 1
498 ]
499 },
500 {
501 "id": 51,
502 "type": "CLIPVisionEncode",
503 "pos": [
504 460,
505 860
506 ],
507 "size": [
508 253.60000610351562,
509 78
510 ],
511 "flags": [],
512 "order": 9,
513 "mode": 0,
514 "inputs": [
515 {
516 "name": "clip_vision",
517 "type": "CLIP_VISION",
518 "link": 94
519 },
520 {
521 "name": "image",
522 "type": "IMAGE",
523 "link": 109
524 }
525 ],
526 "outputs": [
527 {
528 "name": "CLIP_VISION_OUTPUT",
529 "type": "CLIP_VISION_OUTPUT",
530 "slot_index": 0,
531 "links": [
532 107
533 ]
534 }
535 ],
536 "properties": {
537 "Node name for S&R": "CLIPVisionEncode"
538 },
539 "widgets_values": [
540 "none"
541 ]
542 },
543 {
544 "id": 7,
545 "type": "CLIPTextEncode",
546 "pos": [
547 410,
548 280
549 ],
550 "size": [
551 425.27801513671875,
552 180.6060791015625
553 ],
554 "flags": [],
555 "order": 8,
556 "mode": 0,
557 "inputs": [
558 {
559 "name": "clip",
560 "type": "CLIP",
561 "link": 75
562 }
563 ],
564 "outputs": [
565 {
566 "name": "CONDITIONING",
567 "type": "CONDITIONING",
568 "slot_index": 0,
569 "links": [
570 98
571 ]
572 }
573 ],
574 "title": "CLIP Text Encode (Negative Prompt)",
575 "properties": {
576 "Node name for S&R": "CLIPTextEncode"
577 },
578 "widgets_values": [
579 "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"
580 ],
581 "color": "#223",
582 "bgcolor": "#335"
583 },
584 {
585 "id": 57,
586 "type": "MarkdownNote",
587 "pos": [
588 -600,
589 30
590 ],
591 "size": [
592 590,
593 430
594 ],
595 "flags": [],
596 "order": 4,
597 "mode": 0,
598 "inputs": [],
599 "outputs": [],
600 "properties": [],
601 "widgets_values": [
602 "[Tutorial](https://docs.comfy.org/tutorials/video/wan/wan-video)\n\n## Model links\n\n- [Hugging Face:Comfy-Org/Wan_2.1_ComfyUI_repackaged](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged)\n\n**ModelScope mirrors** (alternative repo location)\n\n- [ModelScope:Comfy-Org/Wan_2.1_ComfyUI_repackaged](https://modelscope.cn/models/Comfy-Org/Wan_2.1_ComfyUI_repackaged)\n\n**text_encoders**\n\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**clip_vision**\n\n- [clip_vision_h.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors) (1.18 GB)\n\n**diffusion_models**\n\n- [wan2.1_i2v_480p_14B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_i2v_480p_14B_fp16.safetensors) (30.54 GB)\n\n**vae**\n\n- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors) (242.1 MB)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│ ├── 📂 text_encoders/\n│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors\n│ ├── 📂 clip_vision/\n│ │ └── clip_vision_h.safetensors\n│ ├── 📂 diffusion_models/\n│ │ └── wan2.1_i2v_480p_14B_fp16.safetensors\n│ └── 📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n"
603 ],
604 "color": "#222",
605 "bgcolor": "#000"
606 },
607 {
608 "id": 52,
609 "type": "LoadImage",
610 "pos": [
611 30,
612 620
613 ],
614 "size": [
615 315,
616 314
617 ],
618 "flags": [],
619 "order": 5,
620 "mode": 0,
621 "inputs": [],
622 "outputs": [
623 {
624 "name": "IMAGE",
625 "type": "IMAGE",
626 "slot_index": 0,
627 "links": [
628 106,
629 109
630 ]
631 },
632 {
633 "name": "MASK",
634 "type": "MASK",
635 "slot_index": 1,
636 "links": null
637 }
638 ],
639 "properties": {
640 "Node name for S&R": "LoadImage"
641 },
642 "widgets_values": [
643 "image_to_video_wan_start_image.png",
644 "image"
645 ]
646 }
647 ],
648 "links": [
649 [
650 35,
651 3,
652 0,
653 8,
654 0,
655 "LATENT"
656 ],
657 [
658 74,
659 38,
660 0,
661 6,
662 0,
663 "CLIP"
664 ],
665 [
666 75,
667 38,
668 0,
669 7,
670 0,
671 "CLIP"
672 ],
673 [
674 76,
675 39,
676 0,
677 8,
678 1,
679 "VAE"
680 ],
681 [
682 94,
683 49,
684 0,
685 51,
686 0,
687 "CLIP_VISION"
688 ],
689 [
690 97,
691 6,
692 0,
693 50,
694 0,
695 "CONDITIONING"
696 ],
697 [
698 98,
699 7,
700 0,
701 50,
702 1,
703 "CONDITIONING"
704 ],
705 [
706 99,
707 39,
708 0,
709 50,
710 2,
711 "VAE"
712 ],
713 [
714 101,
715 50,
716 0,
717 3,
718 1,
719 "CONDITIONING"
720 ],
721 [
722 102,
723 50,
724 1,
725 3,
726 2,
727 "CONDITIONING"
728 ],
729 [
730 103,
731 50,
732 2,
733 3,
734 3,
735 "LATENT"
736 ],
737 [
738 106,
739 52,
740 0,
741 50,
742 4,
743 "IMAGE"
744 ],
745 [
746 107,
747 51,
748 0,
749 50,
750 3,
751 "CLIP_VISION_OUTPUT"
752 ],
753 [
754 109,
755 52,
756 0,
757 51,
758 1,
759 "IMAGE"
760 ],
761 [
762 110,
763 37,
764 0,
765 54,
766 0,
767 "MODEL"
768 ],
769 [
770 111,
771 54,
772 0,
773 3,
774 0,
775 "MODEL"
776 ],
777 [
778 112,
779 8,
780 0,
781 55,
782 0,
783 "IMAGE"
784 ],
785 [
786 113,
787 55,
788 0,
789 56,
790 0,
791 "VIDEO"
792 ]
793 ],
794 "groups": [
795 {
796 "id": 1,
797 "title": "Step1 - Load models",
798 "bounding": [
799 10,
800 0,
801 370,
802 533.5999755859375
803 ],
804 "color": "#3f789e",
805 "font_size": 24,
806 "flags": []
807 },
808 {
809 "id": 2,
810 "title": "Step2 - Upload start_image",
811 "bounding": [
812 10,
813 550,
814 370,
815 400
816 ],
817 "color": "#3f789e",
818 "font_size": 24,
819 "flags": []
820 },
821 {
822 "id": 3,
823 "title": "Step4 - Prompt",
824 "bounding": [
825 400,
826 0,
827 445.27801513671875,
828 467.2060852050781
829 ],
830 "color": "#3f789e",
831 "font_size": 24,
832 "flags": []
833 },
834 {
835 "id": 4,
836 "title": "Step3 - Video size",
837 "bounding": [
838 400,
839 480,
840 440,
841 310
842 ],
843 "color": "#3f789e",
844 "font_size": 24,
845 "flags": []
846 }
847 ],
848 "config": [],
849 "extra": {
850 "ds": {
851 "scale": 1.0159611845439778,
852 "offset": [
853 369.61463579251983,
854 -313.38208398559794
855 ]
856 },
857 "frontendVersion": "1.29.2"
858 },
859 "version": 0.4
860}