ComfyPilotComfyPilot
工作流 / 视频 / Wan 2.2 5B视频生成
Wan 2.2 5B视频生成

Wan 2.2 5B视频生成

Wan 2.2 5B Video Generation

快速文生视频和图生视频生成，拥有5B参数。针对快速原型设计和创意探索进行了优化。

视频 13 个节点 1 个输入 333 次使用 ComfyUI ≥ 0.3.46 ComfyUI 15 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 3 个权重文件，其中 3 个能在本站模型库里找到。

umt5_xxl_fp8_e4m3fn_scaled.safetensors 在模型库查看
wan2.2_ti2v_5B_fp16.safetensors 在模型库查看
wan2.2_vae.safetensors 在模型库查看

节点构成

CLIPTextEncode × 2
UNETLoader × 1
CLIPLoader × 1
VAELoader × 1
VAEDecode × 1
CreateVideo × 1
SaveVideo × 1
Wan22ImageToVideoLatent × 1
LoadImage × 1
KSampler × 1
ModelSamplingSD3 × 1
MarkdownNote × 1

官方标注的模型

Wan2.2Wan

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
2 "id": "91f6bbe2-ed41-4fd6-bac7-71d5b5864ecb",
3 "revision": 0,
4 "last_node_id": 59,
5 "last_link_id": 108,
6 "nodes": [
7 {
8 "id": 37,
9 "type": "UNETLoader",
10 "pos": [
11 -30,
12 50
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 94
29 ]
30 }
31 ],
32 "properties": {
33 "cnr_id": "comfy-core",
34 "ver": "0.3.45",
35 "Node name for S&R": "UNETLoader",
36 "models": [
37 {
38 "name": "wan2.2_ti2v_5B_fp16.safetensors",
39 "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors",
40 "directory": "diffusion_models"
41 }
42 ]
43 },
44 "widgets_values": [
45 "wan2.2_ti2v_5B_fp16.safetensors",
46 "default"
47 ]
48 },
49 {
50 "id": 38,
51 "type": "CLIPLoader",
52 "pos": [
53 -30,
54 190
55 ],
56 "size": [
57 350,
58 110
59 ],
60 "flags": [],
61 "order": 1,
62 "mode": 0,
63 "inputs": [],
64 "outputs": [
65 {
66 "name": "CLIP",
67 "type": "CLIP",
68 "slot_index": 0,
69 "links": [
70 74,
71 75
72 ]
73 }
74 ],
75 "properties": {
76 "cnr_id": "comfy-core",
77 "ver": "0.3.45",
78 "Node name for S&R": "CLIPLoader",
79 "models": [
80 {
81 "name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
82 "url": "https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors",
83 "directory": "text_encoders"
84 }
85 ]
86 },
87 "widgets_values": [
88 "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
89 "wan",
90 "default"
91 ]
92 },
93 {
94 "id": 39,
95 "type": "VAELoader",
96 "pos": [
97 -30,
98 350
99 ],
100 "size": [
101 350,
102 60
103 ],
104 "flags": [],
105 "order": 2,
106 "mode": 0,
107 "inputs": [],
108 "outputs": [
109 {
110 "name": "VAE",
111 "type": "VAE",
112 "slot_index": 0,
113 "links": [
114 76,
115 105
116 ]
117 }
118 ],
119 "properties": {
120 "cnr_id": "comfy-core",
121 "ver": "0.3.45",
122 "Node name for S&R": "VAELoader",
123 "models": [
124 {
125 "name": "wan2.2_vae.safetensors",
126 "url": "https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan2.2_vae.safetensors",
127 "directory": "vae"
128 }
129 ]
130 },
131 "widgets_values": [
132 "wan2.2_vae.safetensors"
133 ]
134 },
135 {
136 "id": 8,
137 "type": "VAEDecode",
138 "pos": [
139 1190,
140 150
141 ],
142 "size": [
143 210,
144 46
145 ],
146 "flags": [],
147 "order": 10,
148 "mode": 0,
149 "inputs": [
150 {
151 "name": "samples",
152 "type": "LATENT",
153 "link": 35
154 },
155 {
156 "name": "vae",
157 "type": "VAE",
158 "link": 76
159 }
160 ],
161 "outputs": [
162 {
163 "name": "IMAGE",
164 "type": "IMAGE",
165 "slot_index": 0,
166 "links": [
167 107
168 ]
169 }
170 ],
171 "properties": {
172 "cnr_id": "comfy-core",
173 "ver": "0.3.45",
174 "Node name for S&R": "VAEDecode"
175 },
176 "widgets_values": []
177 },
178 {
179 "id": 57,
180 "type": "CreateVideo",
181 "pos": [
182 1200,
183 240
184 ],
185 "size": [
186 270,
187 78
188 ],
189 "flags": [],
190 "order": 11,
191 "mode": 0,
192 "inputs": [
193 {
194 "name": "images",
195 "type": "IMAGE",
196 "link": 107
197 },
198 {
199 "name": "audio",
200 "shape": 7,
201 "type": "AUDIO",
202 "link": null
203 }
204 ],
205 "outputs": [
206 {
207 "name": "VIDEO",
208 "type": "VIDEO",
209 "links": [
210 108
211 ]
212 }
213 ],
214 "properties": {
215 "cnr_id": "comfy-core",
216 "ver": "0.3.45",
217 "Node name for S&R": "CreateVideo"
218 },
219 "widgets_values": [
220 24
221 ]
222 },
223 {
224 "id": 58,
225 "type": "SaveVideo",
226 "pos": [
227 1200,
228 370
229 ],
230 "size": [
231 660,
232 450
233 ],
234 "flags": [],
235 "order": 12,
236 "mode": 0,
237 "inputs": [
238 {
239 "name": "video",
240 "type": "VIDEO",
241 "link": 108
242 }
243 ],
244 "outputs": [],
245 "properties": {
246 "cnr_id": "comfy-core",
247 "ver": "0.3.45",
248 "Node name for S&R": "SaveVideo"
249 },
250 "widgets_values": [
251 "video/ComfyUI",
252 "auto",
253 "auto"
254 ]
255 },
256 {
257 "id": 55,
258 "type": "Wan22ImageToVideoLatent",
259 "pos": [
260 380,
261 540
262 ],
263 "size": [
264 271.9126892089844,
265 150
266 ],
267 "flags": [],
268 "order": 8,
269 "mode": 0,
270 "inputs": [
271 {
272 "name": "vae",
273 "type": "VAE",
274 "link": 105
275 },
276 {
277 "name": "start_image",
278 "shape": 7,
279 "type": "IMAGE",
280 "link": 106
281 }
282 ],
283 "outputs": [
284 {
285 "name": "LATENT",
286 "type": "LATENT",
287 "links": [
288 104
289 ]
290 }
291 ],
292 "properties": {
293 "cnr_id": "comfy-core",
294 "ver": "0.3.45",
295 "Node name for S&R": "Wan22ImageToVideoLatent"
296 },
297 "widgets_values": [
298 1280,
299 704,
300 121,
301 1
302 ]
303 },
304 {
305 "id": 56,
306 "type": "LoadImage",
307 "pos": [
308 0,
309 540
310 ],
311 "size": [
312 274.080078125,
313 314
314 ],
315 "flags": [],
316 "order": 3,
317 "mode": 4,
318 "inputs": [],
319 "outputs": [
320 {
321 "name": "IMAGE",
322 "type": "IMAGE",
323 "links": [
324 106
325 ]
326 },
327 {
328 "name": "MASK",
329 "type": "MASK",
330 "links": null
331 }
332 ],
333 "properties": {
334 "cnr_id": "comfy-core",
335 "ver": "0.3.45",
336 "Node name for S&R": "LoadImage"
337 },
338 "widgets_values": [
339 "example.png",
340 "image"
341 ]
342 },
343 {
344 "id": 7,
345 "type": "CLIPTextEncode",
346 "pos": [
347 380,
348 260
349 ],
350 "size": [
351 425.27801513671875,
352 180.6060791015625
353 ],
354 "flags": [],
355 "order": 7,
356 "mode": 0,
357 "inputs": [
358 {
359 "name": "clip",
360 "type": "CLIP",
361 "link": 75
362 }
363 ],
364 "outputs": [
365 {
366 "name": "CONDITIONING",
367 "type": "CONDITIONING",
368 "slot_index": 0,
369 "links": [
370 52
371 ]
372 }
373 ],
374 "title": "CLIP Text Encode (Negative Prompt)",
375 "properties": {
376 "cnr_id": "comfy-core",
377 "ver": "0.3.45",
378 "Node name for S&R": "CLIPTextEncode"
379 },
380 "widgets_values": [
381 "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"
382 ],
383 "color": "#322",
384 "bgcolor": "#533"
385 },
386 {
387 "id": 6,
388 "type": "CLIPTextEncode",
389 "pos": [
390 380,
391 50
392 ],
393 "size": [
394 422.84503173828125,
395 164.31304931640625
396 ],
397 "flags": [],
398 "order": 6,
399 "mode": 0,
400 "inputs": [
401 {
402 "name": "clip",
403 "type": "CLIP",
404 "link": 74
405 }
406 ],
407 "outputs": [
408 {
409 "name": "CONDITIONING",
410 "type": "CONDITIONING",
411 "slot_index": 0,
412 "links": [
413 46
414 ]
415 }
416 ],
417 "title": "CLIP Text Encode (Positive Prompt)",
418 "properties": {
419 "cnr_id": "comfy-core",
420 "ver": "0.3.45",
421 "Node name for S&R": "CLIPTextEncode"
422 },
423 "widgets_values": [
424 "Low contrast. In a retro 1970s-style subway station, a street musician plays in dim colors and rough textures. He wears an old jacket, playing guitar with focus. Commuters hurry by, and a small crowd gathers to listen. The camera slowly moves right, capturing the blend of music and city noise, with old subway signs and mottled walls in the background."
425 ],
426 "color": "#232",
427 "bgcolor": "#353"
428 },
429 {
430 "id": 3,
431 "type": "KSampler",
432 "pos": [
433 850,
434 130
435 ],
436 "size": [
437 315,
438 262
439 ],
440 "flags": [],
441 "order": 9,
442 "mode": 0,
443 "inputs": [
444 {
445 "name": "model",
446 "type": "MODEL",
447 "link": 95
448 },
449 {
450 "name": "positive",
451 "type": "CONDITIONING",
452 "link": 46
453 },
454 {
455 "name": "negative",
456 "type": "CONDITIONING",
457 "link": 52
458 },
459 {
460 "name": "latent_image",
461 "type": "LATENT",
462 "link": 104
463 }
464 ],
465 "outputs": [
466 {
467 "name": "LATENT",
468 "type": "LATENT",
469 "slot_index": 0,
470 "links": [
471 35
472 ]
473 }
474 ],
475 "properties": {
476 "cnr_id": "comfy-core",
477 "ver": "0.3.45",
478 "Node name for S&R": "KSampler"
479 },
480 "widgets_values": [
481 898471028164125,
482 "randomize",
483 20,
484 5,
485 "uni_pc",
486 "simple",
487 1
488 ]
489 },
490 {
491 "id": 48,
492 "type": "ModelSamplingSD3",
493 "pos": [
494 850,
495 20
496 ],
497 "size": [
498 210,
499 58
500 ],
501 "flags": {
502 "collapsed": false
503 },
504 "order": 5,
505 "mode": 0,
506 "inputs": [
507 {
508 "name": "model",
509 "type": "MODEL",
510 "link": 94
511 }
512 ],
513 "outputs": [
514 {
515 "name": "MODEL",
516 "type": "MODEL",
517 "slot_index": 0,
518 "links": [
519 95
520 ]
521 }
522 ],
523 "properties": {
524 "cnr_id": "comfy-core",
525 "ver": "0.3.45",
526 "Node name for S&R": "ModelSamplingSD3"
527 },
528 "widgets_values": [
529 8
530 ]
531 },
532 {
533 "id": 59,
534 "type": "MarkdownNote",
535 "pos": [
536 -550,
537 10
538 ],
539 "size": [
540 480,
541 340
542 ],
543 "flags": [],
544 "order": 4,
545 "mode": 0,
546 "inputs": [],
547 "outputs": [],
548 "title": "Model Links",
549 "properties": [],
550 "widgets_values": [
551 "## Model Links\n\n- [Hugging Face:Comfy-Org/Wan_2.2_ComfyUI_Repackaged](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged)\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_2.2_ComfyUI_Repackaged](https://modelscope.cn/models/Comfy-Org/Wan_2.2_ComfyUI_Repackaged)\n- [ModelScope:Comfy-Org/Wan_2.1_ComfyUI_repackaged](https://modelscope.cn/models/Comfy-Org/Wan_2.1_ComfyUI_repackaged)\n\n[Tutorial](https://docs.comfy.org/tutorials/video/wan/wan2_2\n) \n\n**Diffusion Model**\n- [wan2.2_ti2v_5B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors) (9.31 GB)\n\n**VAE**\n- [wan2.2_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/vae/wan2.2_vae.safetensors) (1.31 GB)\n\n**Text Encoder** \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\nFile save location\n\n```\nComfyUI/\n├───📂 models/\n│ ├───📂 diffusion_models/\n│ │ └───wan2.2_ti2v_5B_fp16.safetensors\n│ ├───📂 text_encoders/\n│ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ └───📂 vae/\n│ └── wan2.2_vae.safetensors\n```\n"
552 ],
553 "color": "#222",
554 "bgcolor": "#000"
555 }
556 ],
557 "links": [
558 [
559 35,
560 3,
561 0,
562 8,
563 0,
564 "LATENT"
565 ],
566 [
567 46,
568 6,
569 0,
570 3,
571 1,
572 "CONDITIONING"
573 ],
574 [
575 52,
576 7,
577 0,
578 3,
579 2,
580 "CONDITIONING"
581 ],
582 [
583 74,
584 38,
585 0,
586 6,
587 0,
588 "CLIP"
589 ],
590 [
591 75,
592 38,
593 0,
594 7,
595 0,
596 "CLIP"
597 ],
598 [
599 76,
600 39,
601 0,
602 8,
603 1,
604 "VAE"
605 ],
606 [
607 94,
608 37,
609 0,
610 48,
611 0,
612 "MODEL"
613 ],
614 [
615 95,
616 48,
617 0,
618 3,
619 0,
620 "MODEL"
621 ],
622 [
623 104,
624 55,
625 0,
626 3,
627 3,
628 "LATENT"
629 ],
630 [
631 105,
632 39,
633 0,
634 55,
635 0,
636 "VAE"
637 ],
638 [
639 106,
640 56,
641 0,
642 55,
643 1,
644 "IMAGE"
645 ],
646 [
647 107,
648 8,
649 0,
650 57,
651 0,
652 "IMAGE"
653 ],
654 [
655 108,
656 57,
657 0,
658 58,
659 0,
660 "VIDEO"
661 ]
662 ],
663 "groups": [
664 {
665 "id": 1,
666 "title": "Step1 - Load models",
667 "bounding": [
668 -50,
669 -20,
670 400,
671 453.6000061035156
672 ],
673 "color": "#3f789e",
674 "font_size": 24,
675 "flags": []
676 },
677 {
678 "id": 2,
679 "title": "Step3 - Prompt",
680 "bounding": [
681 370,
682 -20,
683 448.27801513671875,
684 473.2060852050781
685 ],
686 "color": "#3f789e",
687 "font_size": 24,
688 "flags": []
689 },
690 {
691 "id": 3,
692 "title": "For i2v, use Ctrl + B to enable",
693 "bounding": [
694 -50,
695 450,
696 400,
697 420
698 ],
699 "color": "#3f789e",
700 "font_size": 24,
701 "flags": []
702 },
703 {
704 "id": 4,
705 "title": "Video Size & length",
706 "bounding": [
707 370,
708 470,
709 291.9127197265625,
710 233.60000610351562
711 ],
712 "color": "#3f789e",
713 "font_size": 24,
714 "flags": []
715 }
716 ],
717 "config": [],
718 "extra": {
719 "ds": {
720 "scale": 0.46462425349300085,
721 "offset": [
722 847.5372059811432,
723 288.7938392118285
724 ]
725 },
726 "frontendVersion": "1.27.10",
727 "VHS_latentpreview": false,
728 "VHS_latentpreviewrate": 0,
729 "VHS_MetadataImage": true,
730 "VHS_KeepIntermediate": true
731 },
732 "version": 0.4
733}