ComfyPilotComfyPilot
工作流 / 视频 / Seedance2.0 4K: 参考生视频
Seedance2.0 4K: 参考生视频

Seedance2.0 4K: 参考生视频

Seedance2.0 4K: Reference to Video

使用Seedance 2.0从单张输入图像生成基于参考的视频，输出原生4K分辨率、10位颜色深度，并保留清晰的精细细节。该工作流接收1张图像，输出1个视频。适用于需要下游调色的高分辨率动态图形、电影级VFX镜头，以及需要4K输出的专业视频制作。

视频 4 个节点 1 个输入 61 次使用 ComfyUI ≥ 0.33.2 ComfyUI 8 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。

节点构成

LoadImage × 1
SaveVideo × 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": "dd4be16c-c30f-460f-b895-7d22fb9e489c",
3 "revision": 0,
4 "last_node_id": 6,
5 "last_link_id": 4,
6 "nodes": [
7 {
8 "id": 3,
9 "type": "LoadImage",
10 "pos": [
11 -4670,
12 4030
13 ],
14 "size": [
15 530,
16 550
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "IMAGE",
25 "type": "IMAGE",
26 "links": [
27 3
28 ]
29 },
30 {
31 "name": "MASK",
32 "type": "MASK",
33 "links": null
34 }
35 ],
36 "properties": {
37 "Node name for S&R": "LoadImage"
38 },
39 "widgets_values": [
40 "green_rider.png",
41 "image"
42 ],
43 "widgets_values_named": {
44 "image": "green_rider.png",
45 "upload": "image"
46 }
47 },
48 {
49 "id": 4,
50 "type": "SaveVideo",
51 "pos": [
52 -3660,
53 4030
54 ],
55 "size": [
56 620,
57 150
58 ],
59 "flags": [],
60 "order": 3,
61 "mode": 0,
62 "inputs": [
63 {
64 "name": "video",
65 "type": "VIDEO",
66 "link": 4
67 }
68 ],
69 "outputs": [
70 {
71 "name": "video",
72 "type": "VIDEO",
73 "links": null
74 }
75 ],
76 "properties": [],
77 "widgets_values": [
78 "video/Seedance2.0_4k",
79 "auto",
80 "auto",
81 "auto"
82 ],
83 "widgets_values_named": {
84 "filename_prefix": "video/Seedance2.0_4k",
85 "format": "auto",
86 "format.codec": "auto",
87 "codec": "auto"
88 }
89 },
90 {
91 "id": 5,
92 "type": "ByteDance2ReferenceNodeV2",
93 "pos": [
94 -4100,
95 4030
96 ],
97 "size": [
98 400,
99 431
100 ],
101 "flags": [],
102 "order": 2,
103 "mode": 0,
104 "inputs": [
105 {
106 "name": "model.reference_images.image_1",
107 "shape": 7,
108 "type": "IMAGE",
109 "link": 3
110 },
111 {
112 "name": "model.reference_images.image_2",
113 "shape": 7,
114 "type": "IMAGE",
115 "link": null
116 },
117 {
118 "name": "model.reference_videos.video_1",
119 "shape": 7,
120 "type": "VIDEO",
121 "link": null
122 },
123 {
124 "name": "model.reference_audios.audio_1",
125 "shape": 7,
126 "type": "AUDIO",
127 "link": null
128 },
129 {
130 "name": "model.reference_assets.asset_1",
131 "shape": 7,
132 "type": "STRING",
133 "link": null
134 }
135 ],
136 "outputs": [
137 {
138 "name": "VIDEO",
139 "type": "VIDEO",
140 "links": [
141 4
142 ]
143 }
144 ],
145 "properties": {
146 "Node name for S&R": "ByteDance2ReferenceNodeV2"
147 },
148 "widgets_values": [
149 "Seedance 2.0",
150 "Using the attached character as the subject, generate a continuous cycling sequence where the environment transitions seamlessly. Medium profile tracking shot, locked 50mm focal length, steady steadicam pace matching the subject's ride. The same cute amigurumi-style character — green crochet/knit textured body, round face with dot eyes and pink blush, small head nubs, mint-green bicycle with black seat and handlebars, front basket with two yellow bells — pedals left to right at a calm, steady cadence. Identical character design, bicycle shape, yarn-like surface detail, proportions, and pedaling motion throughout; no morphing, no redesign, no wardrobe change.\n\nStarting in a soft pale mint-green infinity studio matching the reference, the environment morphs seamlessly through three biomes in one continuous shot: burnt-orange desert dunes at golden hour, a neon-soaked rainy city street with reflections in wet pavement, then a misty alpine pine forest with soft fog and cool diffused light. Each transition flows without hard cuts — studio floor becomes sand, sand becomes asphalt, rain mist becomes forest air — while the character and bike remain visually unchanged, like a toy brought through different dream worlds.\n\nStylized photorealistic 3D render, toy-core / amigurumi aesthetic, soft diffused lighting, gentle shadows, shallow depth of field, subtle film grain, whimsical yet cinematic",
151 "4k",
152 "adaptive",
153 5,
154 true,
155 true,
156 false,
157 0,
158 "randomize",
159 false
160 ],
161 "widgets_values_named": {
162 "model": "Seedance 2.0",
163 "model.prompt": "Using the attached character as the subject, generate a continuous cycling sequence where the environment transitions seamlessly. Medium profile tracking shot, locked 50mm focal length, steady steadicam pace matching the subject's ride. The same cute amigurumi-style character — green crochet/knit textured body, round face with dot eyes and pink blush, small head nubs, mint-green bicycle with black seat and handlebars, front basket with two yellow bells — pedals left to right at a calm, steady cadence. Identical character design, bicycle shape, yarn-like surface detail, proportions, and pedaling motion throughout; no morphing, no redesign, no wardrobe change.\n\nStarting in a soft pale mint-green infinity studio matching the reference, the environment morphs seamlessly through three biomes in one continuous shot: burnt-orange desert dunes at golden hour, a neon-soaked rainy city street with reflections in wet pavement, then a misty alpine pine forest with soft fog and cool diffused light. Each transition flows without hard cuts — studio floor becomes sand, sand becomes asphalt, rain mist becomes forest air — while the character and bike remain visually unchanged, like a toy brought through different dream worlds.\n\nStylized photorealistic 3D render, toy-core / amigurumi aesthetic, soft diffused lighting, gentle shadows, shallow depth of field, subtle film grain, whimsical yet cinematic",
164 "model.resolution": "4k",
165 "model.ratio": "adaptive",
166 "model.duration": 5,
167 "model.generate_audio": true,
168 "model.auto_downscale": true,
169 "model.auto_upscale": false,
170 "seed": 0,
171 "control_after_generate": "randomize",
172 "watermark": false
173 },
174 "color": "#432",
175 "bgcolor": "#653"
176 },
177 {
178 "id": 6,
179 "type": "MarkdownNote",
180 "pos": [
181 -5040,
182 4030
183 ],
184 "size": [
185 350,
186 350
187 ],
188 "flags": [],
189 "order": 1,
190 "mode": 0,
191 "inputs": [],
192 "outputs": [],
193 "properties": [],
194 "widgets_values": [
195 "## Input Asset\n\n- [green_rider.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/green_rider.png)\n\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"
196 ],
197 "widgets_values_named": {
198 "text": "## Input Asset\n\n- [green_rider.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/green_rider.png)\n\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"
199 },
200 "color": "#222",
201 "bgcolor": "#000"
202 }
203 ],
204 "links": [
205 [
206 3,
207 3,
208 0,
209 5,
210 0,
211 "IMAGE"
212 ],
213 [
214 4,
215 5,
216 0,
217 4,
218 0,
219 "VIDEO"
220 ]
221 ],
222 "groups": [],
223 "config": [],
224 "extra": {
225 "ds": {
226 "scale": 0.6578751780584943,
227 "offset": [
228 5462.065502367709,
229 -3341.3034498626494
230 ]
231 },
232 "frontendVersion": "1.51.9",
233 "VHS_latentpreview": false,
234 "VHS_latentpreviewrate": 0,
235 "VHS_MetadataImage": true,
236 "VHS_KeepIntermediate": true
237 },
238 "version": 0.4
239}