工作流 /
视频 /
HeyGen Video 1.0：图生视频
HeyGen Video 1.0：图生视频
HeyGen Video 1.0: Image to Video
使用 HeyGen Video 1.0，从单张图像生成一段 5-15 秒的 CLIP，包含同步的对话和声音，视频从该精确帧开始，并保持图像的比例，分辨率为 480p 或 768p。提示词同时驱动动作和台词，输出一个视频。非常适合为人像或产品照片赋予声音、无需拍摄即可制作口播视频，以及让静态图像栩栩如生。
视频
4 个节点 1 个输入 534 次使用 ComfyUI ≥ 0.38.1 ComfyUI 8 KB
节点构成
SaveVideo
× 1
LoadImage
× 1
MarkdownNote
× 1
HeyGenImageToVideoNode
× 1
官方标注的模型
HeyGen
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "3c8ca601-c178-435d-9591-08d629acff15",
3 "revision": 0,
4 "last_node_id": 11,
5 "last_link_id": 10,
6 "nodes": [
7 {
8 "id": 3,
9 "type": "SaveVideo",
10 "pos": [
11 -410,
12 1290
13 ],
14 "size": [
15 530,
16 520
17 ],
18 "flags": [],
19 "order": 3,
20 "mode": 0,
21 "inputs": [
22 {
23 "name": "video",
24 "type": "VIDEO",
25 "link": 6
26 }
27 ],
28 "outputs": [
29 {
30 "name": "video",
31 "type": "VIDEO",
32 "links": null
33 }
34 ],
35 "properties": [],
36 "widgets_values": [
37 "video/HeyGen_video_1.0_i2v",
38 "auto",
39 "auto",
40 "auto"
41 ],
42 "widgets_values_named": {
43 "filename_prefix": "video/HeyGen_video_1.0_i2v",
44 "format": "auto",
45 "format.codec": "auto",
46 "codec": "auto"
47 }
48 },
49 {
50 "id": 5,
51 "type": "LoadImage",
52 "pos": [
53 -1300,
54 1290
55 ],
56 "size": [
57 400,
58 500
59 ],
60 "flags": [],
61 "order": 0,
62 "mode": 0,
63 "inputs": [],
64 "outputs": [
65 {
66 "name": "IMAGE",
67 "type": "IMAGE",
68 "links": [
69 7
70 ]
71 },
72 {
73 "name": "MASK",
74 "type": "MASK",
75 "links": null
76 }
77 ],
78 "properties": {
79 "Node name for S&R": "LoadImage"
80 },
81 "widgets_values": [
82 "model_red_curls_ring.png",
83 "image"
84 ],
85 "widgets_values_named": {
86 "image": "model_red_curls_ring.png",
87 "upload": "image"
88 }
89 },
90 {
91 "id": 8,
92 "type": "MarkdownNote",
93 "pos": [
94 -1780,
95 1290
96 ],
97 "size": [
98 430,
99 360
100 ],
101 "flags": [],
102 "order": 1,
103 "mode": 0,
104 "inputs": [],
105 "outputs": [],
106 "properties": [],
107 "widgets_values": [
108 "## Input Assets\n\n- [model_red_curls_ring.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/model_red_curls_ring.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"
109 ],
110 "widgets_values_named": {
111 "text": "## Input Assets\n\n- [model_red_curls_ring.png](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/model_red_curls_ring.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"
112 },
113 "color": "#222",
114 "bgcolor": "#000"
115 },
116 {
117 "id": 9,
118 "type": "HeyGenImageToVideoNode",
119 "pos": [
120 -850,
121 1290
122 ],
123 "size": [
124 400,
125 340
126 ],
127 "flags": [],
128 "order": 2,
129 "mode": 0,
130 "inputs": [
131 {
132 "name": "model.image",
133 "type": "IMAGE",
134 "link": 7
135 }
136 ],
137 "outputs": [
138 {
139 "name": "VIDEO",
140 "type": "VIDEO",
141 "links": [
142 6
143 ]
144 }
145 ],
146 "properties": {
147 "Node name for S&R": "HeyGenImageToVideoNode"
148 },
149 "widgets_values": [
150 "heygen-video-1",
151 "The woman from the first frame raises her hand in one slow, steady move from her jaw until the ring is held right in front of the lens, the ring's face turned straight to the camera and filling the middle of the frame. For the first three seconds nothing else moves and she says nothing: the ring is the brightest, sharpest thing in the shot, closer to the lens than her face. Then she settles her eyes on the lens and speaks straight to camera in an easy, conversational selling tone, unhurried, about two words per second: \"One ring, every outfit. This is the only one I pack.\" Her arm stays steady while she talks. At the end of the line she tips her wrist a few degrees so the highlight travels across the ring, then blinks once and holds. Shot on an ARRI Alexa Mini LF, 85mm T1.8, locked off on a tripod at eye level, the same soft key light as the first frame, shallow depth of field, fine film grain, true-to-life muted colour, no teal-orange grade, natural skin texture with visible pores and fine lines, no retouching, no beauty filter, no glamour lighting. No readable text, logos, brand names, printed words or badges anywhere in frame, hands have exactly five fingers, nothing CG-looking, no plastic skin. Quiet studio room tone, a faint fabric rustle as she raises her arm, her voice close to the mic and dry. No music.",
152 5,
153 "768p",
154 3006221932,
155 "randomize",
156 "randomize"
157 ],
158 "widgets_values_named": {
159 "model": "heygen-video-1",
160 "model.prompt": "The woman from the first frame raises her hand in one slow, steady move from her jaw until the ring is held right in front of the lens, the ring's face turned straight to the camera and filling the middle of the frame. For the first three seconds nothing else moves and she says nothing: the ring is the brightest, sharpest thing in the shot, closer to the lens than her face. Then she settles her eyes on the lens and speaks straight to camera in an easy, conversational selling tone, unhurried, about two words per second: \"One ring, every outfit. This is the only one I pack.\" Her arm stays steady while she talks. At the end of the line she tips her wrist a few degrees so the highlight travels across the ring, then blinks once and holds. Shot on an ARRI Alexa Mini LF, 85mm T1.8, locked off on a tripod at eye level, the same soft key light as the first frame, shallow depth of field, fine film grain, true-to-life muted colour, no teal-orange grade, natural skin texture with visible pores and fine lines, no retouching, no beauty filter, no glamour lighting. No readable text, logos, brand names, printed words or badges anywhere in frame, hands have exactly five fingers, nothing CG-looking, no plastic skin. Quiet studio room tone, a faint fabric rustle as she raises her arm, her voice close to the mic and dry. No music.",
161 "model.duration": 5,
162 "model.resolution": "768p",
163 "model.seed": 3006221932,
164 "control_after_generate#1": "randomize",
165 "control_after_generate": "randomize"
166 },
167 "color": "#432",
168 "bgcolor": "#653"
169 }
170 ],
171 "links": [
172 [
173 6,
174 9,
175 0,
176 3,
177 0,
178 "VIDEO"
179 ],
180 [
181 7,
182 5,
183 0,
184 9,
185 0,
186 "IMAGE"
187 ]
188 ],
189 "groups": [],
190 "config": [],
191 "extra": {
192 "ds": {
193 "scale": 0.6341302786512443,
194 "offset": [
195 1905.4746439101023,
196 -842.4995185648063
197 ]
198 },
199 "frontendVersion": "1.56.0"
200 },
201 "version": 0.4
202}