工作流 /
视频 /
Vidu Q4 预览：图生视频
Vidu Q4 预览：图生视频
Vidu Q4 Preview: Image to Video
使用 Vidu Q4 Preview 从单张静态图像生成电影级视频。这是一款富有表现力的旗舰模型，专为逼真的角色表演、戏剧性的镜头运动和惊艳的视觉效果而打造。提交 1 张图像即可获得 1 段成品视频，支持最多 15 张参考图像、3 段参考音频以及 2K 或 4K 输出。非常适合短片、营销内容和社交媒体叙事。
视频
4 个节点 1 个输入 29 次使用 ComfyUI ≥ 0.39.2 ComfyUI 8 KB
节点构成
LoadImage
× 1
SaveVideo
× 1
Vidu4ImageToVideoNode
× 1
MarkdownNote
× 1
官方标注的模型
Vidu Q4
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "9dba108f-dc7c-458a-9d8a-7f04fbb6ea38",
3 "revision": 0,
4 "last_node_id": 8,
5 "last_link_id": 6,
6 "nodes": [
7 {
8 "id": 5,
9 "type": "LoadImage",
10 "pos": [
11 138.01137600394165,
12 348.67557383216695
13 ],
14 "size": [
15 282.798828125,
16 102
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "IMAGE",
25 "type": "IMAGE",
26 "links": [
27 6
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 "model_turquoise_yellow_outfit.png",
41 "image"
42 ],
43 "widgets_values_named": {
44 "image": "model_turquoise_yellow_outfit.png",
45 "upload": "image"
46 }
47 },
48 {
49 "id": 6,
50 "type": "SaveVideo",
51 "pos": [
52 916.8102041289417,
53 348.67557383216695
54 ],
55 "size": [
56 532.0365912068158,
57 315.5668113587283
58 ],
59 "flags": [],
60 "order": 3,
61 "mode": 0,
62 "inputs": [
63 {
64 "name": "video",
65 "type": "VIDEO",
66 "link": 5
67 }
68 ],
69 "outputs": [
70 {
71 "name": "video",
72 "type": "VIDEO",
73 "links": []
74 }
75 ],
76 "properties": [],
77 "widgets_values": [
78 "video/Vidu_q4_preview_i2v",
79 "auto",
80 "auto",
81 "auto"
82 ],
83 "widgets_values_named": {
84 "filename_prefix": "video/Vidu_q4_preview_i2v",
85 "format": "auto",
86 "format.codec": "auto",
87 "codec": "auto"
88 }
89 },
90 {
91 "id": 7,
92 "type": "Vidu4ImageToVideoNode",
93 "pos": [
94 468.8102041289417,
95 348.67557383216695
96 ],
97 "size": [
98 400,
99 256
100 ],
101 "flags": [],
102 "order": 2,
103 "mode": 0,
104 "inputs": [
105 {
106 "name": "image",
107 "type": "IMAGE",
108 "link": 6
109 }
110 ],
111 "outputs": [
112 {
113 "name": "VIDEO",
114 "type": "VIDEO",
115 "links": [
116 5
117 ]
118 }
119 ],
120 "properties": {
121 "Node name for S&R": "Vidu4ImageToVideoNode"
122 },
123 "widgets_values": [
124 "Vidu Q4 Preview",
125 "5-second image-to-video luxury fashion editorial. Use the uploaded image as the exact first frame. Keep the same model’s face, short hair, shimmering teal suit, yellow shirt and yellow boots consistent across every cut. Preserve the curved white concrete wall, deep blue sky, strong sunlight and sharp architectural shadows.\nCreate a rapid sequence of distinct hard cuts, not smooth transitions:\n0–0.6s: Start from the original dramatic worm’s-eye view; the model looks down toward the lens.\n0.6–1.3s: Hard cut to a straight-down overhead full-body shot. The model pivots, creating a bold graphic shape against the white concrete.\n1.3–1.9s: Hard cut to an eye-level side profile; the model turns sharply toward camera.\n1.9–2.6s: Hard cut to a low-angle medium shot, framing the teal jacket against the blue sky.\n2.6–3.2s: Hard cut to a tight frontal portrait with a quick push-in as the model meets the lens.\n3.2–4.0s: Hard cut to a wide, slightly tilted architectural shot; the model takes one confident step and strikes a new pose.\n4.0–5.0s: Two quick cuts between an overhead view and a powerful low-angle full-body view. Finish on a brief, perfectly composed fashion-photo freeze.\nCrisp editorial pacing, striking changes in camera height and shot size, confident restrained posing, saturated teal-yellow-blue color blocking, premium campaign photography. Each cut reveals a new angle of the same outfit and location. No shoe-sole close-up, no slow orbit, no dissolve, no identity drift, no outfit changes, no text or watermark.",
126 "720p",
127 5,
128 true,
129 390272314,
130 "randomize",
131 "randomize"
132 ],
133 "widgets_values_named": {
134 "model": "Vidu Q4 Preview",
135 "model.prompt": "5-second image-to-video luxury fashion editorial. Use the uploaded image as the exact first frame. Keep the same model’s face, short hair, shimmering teal suit, yellow shirt and yellow boots consistent across every cut. Preserve the curved white concrete wall, deep blue sky, strong sunlight and sharp architectural shadows.\nCreate a rapid sequence of distinct hard cuts, not smooth transitions:\n0–0.6s: Start from the original dramatic worm’s-eye view; the model looks down toward the lens.\n0.6–1.3s: Hard cut to a straight-down overhead full-body shot. The model pivots, creating a bold graphic shape against the white concrete.\n1.3–1.9s: Hard cut to an eye-level side profile; the model turns sharply toward camera.\n1.9–2.6s: Hard cut to a low-angle medium shot, framing the teal jacket against the blue sky.\n2.6–3.2s: Hard cut to a tight frontal portrait with a quick push-in as the model meets the lens.\n3.2–4.0s: Hard cut to a wide, slightly tilted architectural shot; the model takes one confident step and strikes a new pose.\n4.0–5.0s: Two quick cuts between an overhead view and a powerful low-angle full-body view. Finish on a brief, perfectly composed fashion-photo freeze.\nCrisp editorial pacing, striking changes in camera height and shot size, confident restrained posing, saturated teal-yellow-blue color blocking, premium campaign photography. Each cut reveals a new angle of the same outfit and location. No shoe-sole close-up, no slow orbit, no dissolve, no identity drift, no outfit changes, no text or watermark.",
136 "model.resolution": "720p",
137 "model.duration": 5,
138 "model.audio": true,
139 "model.seed": 390272314,
140 "control_after_generate#1": "randomize",
141 "control_after_generate": "randomize"
142 },
143 "color": "#432",
144 "bgcolor": "#653"
145 },
146 {
147 "id": 8,
148 "type": "MarkdownNote",
149 "pos": [
150 -182.1055641312007,
151 349.68152891038545
152 ],
153 "size": [
154 280.4703073532121,
155 303.50638016831334
156 ],
157 "flags": [],
158 "order": 1,
159 "mode": 0,
160 "inputs": [],
161 "outputs": [],
162 "properties": [],
163 "widgets_values": [
164 "## Input Asset\n\n- [model_turquoise_yellow_outfit.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/model_turquoise_yellow_outfit.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"
165 ],
166 "widgets_values_named": {
167 "text": "## Input Asset\n\n- [model_turquoise_yellow_outfit.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/model_turquoise_yellow_outfit.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"
168 },
169 "color": "#222",
170 "bgcolor": "#000"
171 }
172 ],
173 "links": [
174 [
175 5,
176 7,
177 0,
178 6,
179 0,
180 "VIDEO"
181 ],
182 [
183 6,
184 5,
185 0,
186 7,
187 0,
188 "IMAGE"
189 ]
190 ],
191 "groups": [],
192 "config": [],
193 "extra": {
194 "ds": {
195 "scale": 0.6364787156517925,
196 "offset": [
197 776.1788068304434,
198 186.83989851532942
199 ]
200 },
201 "frontendVersion": "1.56.2",
202 "VHS_KeepIntermediate": true,
203 "VHS_MetadataImage": true,
204 "VHS_latentpreview": false,
205 "VHS_latentpreviewrate": 0
206 },
207 "version": 0.4
208}