工作流 /
视频 /
Seedance 2.0: 参考生视频
Seedance 2.0: 参考生视频
Seedance 2.0: Reference to Video
根据参考图像和文本提示生成电影级视频。在保留主体身份和构图的同时，通过同步音频添加富有表现力的运动。通过详细提示控制摄像机移动和灯光。
视频
4 个节点 1 个输入 402 次使用 ComfyUI ≥ 0.33.2 ComfyUI 11 KB
节点构成
SaveVideo
× 1
LoadImage
× 1
ByteDance2ReferenceNodeV2
× 1
MarkdownNote
× 1
官方标注的模型
Seedance 2.0
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "9994178c-856f-479e-8ba6-cda3daf4a117",
3 "revision": 0,
4 "last_node_id": 362,
5 "last_link_id": 660,
6 "nodes": [
7 {
8 "id": 344,
9 "type": "SaveVideo",
10 "pos": [
11 450,
12 8270
13 ],
14 "size": [
15 520,
16 126
17 ],
18 "flags": {
19 "collapsed": false
20 },
21 "order": 3,
22 "mode": 0,
23 "inputs": [
24 {
25 "name": "video",
26 "type": "VIDEO",
27 "link": 659
28 }
29 ],
30 "outputs": [
31 {
32 "name": "video",
33 "type": "VIDEO",
34 "links": null
35 }
36 ],
37 "properties": {
38 "cnr_id": "comfy-core",
39 "ver": "0.19.3",
40 "enableTabs": false,
41 "tabWidth": 65,
42 "tabXOffset": 10,
43 "hasSecondTab": false,
44 "secondTabText": "Send Back",
45 "secondTabOffset": 80,
46 "secondTabWidth": 65,
47 "Node name for S&R": "SaveVideo",
48 "ue_properties": {
49 "widget_ue_connectable": [],
50 "version": "7.7",
51 "input_ue_unconnectable": []
52 }
53 },
54 "widgets_values": [
55 "video/Seedance2.0_r2v",
56 "auto",
57 "auto",
58 "auto"
59 ],
60 "widgets_values_named": {
61 "filename_prefix": "video/Seedance2.0_r2v",
62 "format": "auto",
63 "format.codec": "auto",
64 "codec": "auto"
65 }
66 },
67 {
68 "id": 356,
69 "type": "LoadImage",
70 "pos": [
71 -390,
72 8270
73 ],
74 "size": [
75 370,
76 460
77 ],
78 "flags": [],
79 "order": 0,
80 "mode": 0,
81 "inputs": [],
82 "outputs": [
83 {
84 "name": "IMAGE",
85 "type": "IMAGE",
86 "links": [
87 660
88 ]
89 },
90 {
91 "name": "MASK",
92 "type": "MASK",
93 "links": null
94 }
95 ],
96 "properties": {
97 "cnr_id": "comfy-core",
98 "ver": "0.19.3",
99 "Node name for S&R": "LoadImage",
100 "enableTabs": false,
101 "tabWidth": 65,
102 "tabXOffset": 10,
103 "hasSecondTab": false,
104 "secondTabText": "Send Back",
105 "secondTabOffset": 80,
106 "secondTabWidth": 65,
107 "ue_properties": {
108 "widget_ue_connectable": [],
109 "version": "7.7",
110 "input_ue_unconnectable": []
111 }
112 },
113 "widgets_values": [
114 "selfie_cartoon_style.png",
115 "image"
116 ],
117 "widgets_values_named": {
118 "image": "selfie_cartoon_style.png",
119 "upload": "image"
120 }
121 },
122 {
123 "id": 361,
124 "type": "ByteDance2ReferenceNodeV2",
125 "pos": [
126 20,
127 8270
128 ],
129 "size": [
130 400,
131 408
132 ],
133 "flags": [],
134 "order": 2,
135 "mode": 0,
136 "inputs": [
137 {
138 "name": "model.reference_images.image_1",
139 "shape": 7,
140 "type": "IMAGE",
141 "link": 660
142 },
143 {
144 "name": "model.reference_images.image_2",
145 "shape": 7,
146 "type": "IMAGE",
147 "link": null
148 },
149 {
150 "name": "model.reference_videos.video_1",
151 "shape": 7,
152 "type": "VIDEO",
153 "link": null
154 },
155 {
156 "name": "model.reference_audios.audio_1",
157 "shape": 7,
158 "type": "AUDIO",
159 "link": null
160 },
161 {
162 "name": "model.reference_assets.asset_1",
163 "shape": 7,
164 "type": "STRING",
165 "link": null
166 }
167 ],
168 "outputs": [
169 {
170 "name": "VIDEO",
171 "type": "VIDEO",
172 "links": [
173 659
174 ]
175 }
176 ],
177 "properties": {
178 "cnr_id": "comfy-core",
179 "ver": "0.34.0",
180 "Node name for S&R": "ByteDance2ReferenceNodeV2"
181 },
182 "widgets_values": [
183 "Seedance 2.0",
184 "fast-paced fashion showcase video, fisheye lens extreme wide-angle distortion, glitch transitions and digital distortion effects, first-person POV selfie perspective, the model is directly interacting with the camera (waving, gesturing, leaning in, moving close to the lens).\n\n[0:00-0:02] The model wears the FIRST reference outfit: cream fuzzy knit sweater, high-waisted light blue distressed straight-leg jeans, white low-top sneakers, brown leather crossbody bag, layered gold jewelry, white knit beanie. The outfit is fully visible, consistent in every frame, no replacement clothing, no missing items, no off-model garments. Scene: busy city street intersection, dynamic handheld camera movement, model leans in to take a mirror selfie, vibrant streetwear aesthetic.\n\n[0:02-0:04] Glitch transition to the SECOND reference outfit: white cropped tee, high-waisted wide-leg gray trousers, brown leather loafers, brown leather belt, round sunglasses, small white crossbody bag. The outfit is fully visible, consistent in every frame, no replacement clothing, no missing items, no off-model garments. Scene: minimalist urban sidewalk, model gestures to the camera, steps back to show full outfit, crisp neutral color grading.\n\n[0:04-0:07] Glitch transition to the THIRD reference outfit: vintage blue denim jacket, white inner tee, high-waisted black straight-leg pants, black combat boots, white canvas crossbody bag. The outfit is fully visible, consistent in every frame, no replacement clothing, no missing items, no off-model garments. Scene: city street with skyscrapers, model waves and moves dynamically, cinematic motion blur, hyper-realistic, consistent character throughout the entire video.\n\nvibrant color grading, cinematic motion blur, hyper-realistic, consistent character and outfit in each time segment, no outfit mixing, no off-model details, sharp focus on clothing details in every frame.",
185 "720p",
186 "adaptive",
187 7,
188 true,
189 true,
190 false,
191 0,
192 "randomize",
193 false
194 ],
195 "widgets_values_named": {
196 "model": "Seedance 2.0",
197 "model.prompt": "fast-paced fashion showcase video, fisheye lens extreme wide-angle distortion, glitch transitions and digital distortion effects, first-person POV selfie perspective, the model is directly interacting with the camera (waving, gesturing, leaning in, moving close to the lens).\n\n[0:00-0:02] The model wears the FIRST reference outfit: cream fuzzy knit sweater, high-waisted light blue distressed straight-leg jeans, white low-top sneakers, brown leather crossbody bag, layered gold jewelry, white knit beanie. The outfit is fully visible, consistent in every frame, no replacement clothing, no missing items, no off-model garments. Scene: busy city street intersection, dynamic handheld camera movement, model leans in to take a mirror selfie, vibrant streetwear aesthetic.\n\n[0:02-0:04] Glitch transition to the SECOND reference outfit: white cropped tee, high-waisted wide-leg gray trousers, brown leather loafers, brown leather belt, round sunglasses, small white crossbody bag. The outfit is fully visible, consistent in every frame, no replacement clothing, no missing items, no off-model garments. Scene: minimalist urban sidewalk, model gestures to the camera, steps back to show full outfit, crisp neutral color grading.\n\n[0:04-0:07] Glitch transition to the THIRD reference outfit: vintage blue denim jacket, white inner tee, high-waisted black straight-leg pants, black combat boots, white canvas crossbody bag. The outfit is fully visible, consistent in every frame, no replacement clothing, no missing items, no off-model garments. Scene: city street with skyscrapers, model waves and moves dynamically, cinematic motion blur, hyper-realistic, consistent character throughout the entire video.\n\nvibrant color grading, cinematic motion blur, hyper-realistic, consistent character and outfit in each time segment, no outfit mixing, no off-model details, sharp focus on clothing details in every frame.",
198 "model.resolution": "720p",
199 "model.ratio": "adaptive",
200 "model.duration": 7,
201 "model.generate_audio": true,
202 "model.auto_downscale": true,
203 "model.auto_upscale": false,
204 "seed": 0,
205 "control_after_generate": "randomize",
206 "watermark": false
207 },
208 "color": "#432",
209 "bgcolor": "#653"
210 },
211 {
212 "id": 362,
213 "type": "MarkdownNote",
214 "pos": [
215 -790,
216 8270
217 ],
218 "size": [
219 350,
220 450
221 ],
222 "flags": [],
223 "order": 1,
224 "mode": 0,
225 "inputs": [],
226 "outputs": [],
227 "title": "Note: Input Asset",
228 "properties": [],
229 "widgets_values": [
230 "## Input Asset\n\n- [selfie_cartoon_style.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/selfie_cartoon_style.png)\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
231 ],
232 "widgets_values_named": {
233 "text": "## Input Asset\n\n- [selfie_cartoon_style.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/selfie_cartoon_style.png)\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
234 },
235 "color": "#222",
236 "bgcolor": "#000"
237 }
238 ],
239 "links": [
240 [
241 659,
242 361,
243 0,
244 344,
245 0,
246 "VIDEO"
247 ],
248 [
249 660,
250 356,
251 0,
252 361,
253 0,
254 "IMAGE"
255 ]
256 ],
257 "groups": [],
258 "config": [],
259 "extra": {
260 "ds": {
261 "scale": 1.3041076813268488,
262 "offset": [
263 1111.0385789211825,
264 -7994.530068151491
265 ]
266 },
267 "frontendVersion": "1.51.9",
268 "workflowRendererVersion": "Vue-corrected",
269 "ue_links": [],
270 "VHS_latentpreview": false,
271 "VHS_latentpreviewrate": 0,
272 "VHS_MetadataImage": true,
273 "VHS_KeepIntermediate": true
274 },
275 "version": 0.4
276}