videoagent-video-studio

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

🎬 VideoAgent Video Studio

🎬 VideoAgent Video Studio

Use when: User asks to generate a video, create a video from text, animate an image, make a short clip, or produce AI video.
Generate short AI videos with 7 backends. This skill picks the right mode (text-to-video or image-to-video), enhances the prompt for best results, and returns the video URL.

适用场景: 用户要求生成视频、从文本创建视频、为图片添加动画、制作短视频片段或生成AI视频时使用。
借助7种后端服务生成AI短视频。该技能会选择合适的模式(文本转视频或图片转视频)、优化提示词以获得最佳效果,并返回视频URL。

Quick Reference

快速参考

User IntentModeTypical Duration
"Make a video of..." (no image)
text-to-video
4–10 s
"Animate this image" / "Make this move"
image-to-video
4–6 s
"Turn this into a video with..."
image-to-video
4–6 s
Cinematic, story, adPrefer
text-to-video
with detailed prompt
5–10 s
用户意图模式典型时长
"制作一段关于……的视频"(无图片)
text-to-video
4–10 秒
"为这张图片添加动画" / "让这个动起来"
image-to-video
4–6 秒
"把这个转换成带有……的视频"
image-to-video
4–6 秒
电影质感、故事类、广告类优先使用
text-to-video
并搭配详细提示词
5–10 秒

Generation Modes

生成模式

ModeDescriptionModels
text-to-videoText prompt only → videominimax, kling, veo, hunyuan, grok, seedance
image-to-videoSingle image + prompt → animated clipminimax, kling, veo, pixverse, grok, seedance
reference-basedReference images/video → consistent outputminimax, kling, veo, hunyuan, grok, seedance
模式描述模型
text-to-video仅需文本提示词 → 视频minimax, kling, veo, hunyuan, grok, seedance
image-to-video单张图片 + 提示词 → 动画片段minimax, kling, veo, pixverse, grok, seedance
reference-based参考图片/视频 → 风格一致的输出minimax, kling, veo, hunyuan, grok, seedance

Models (use
--model <id>
)

模型(使用
--model <id>

Model IDT2VI2VReferenceNotes
minimax
Subject reference image, character consistency
kling
Multi-element / character / keyframe (O3)
veo
Google Veo 3.1, multiple reference images
hunyuan
Video-to-video style transfer
pixverse
Stylized image-to-video
grok
Video editing via reference video
seedance
Seedance 1.5 Pro, synchronized audio, 4–12 s
Full model details and endpoint reference: references/models.md.

模型IDT2VI2V参考模式说明
minimax
支持主体参考图片、角色一致性
kling
多元素/角色/关键帧(O3)
veo
Google Veo 3.1,支持多张参考图片
hunyuan
视频转视频风格迁移
pixverse
风格化图片转视频
grok
通过参考视频进行视频编辑
seedance
Seedance 1.5 Pro,同步音频,时长4–12秒
完整模型详情及端点参考:references/models.md

How to Generate a Video

如何生成视频

Step 1 — Choose mode and enhance the prompt

步骤1 — 选择模式并优化提示词

  • Text-to-video: Expand with subject, action, camera movement, lighting, and style. Be specific about motion (e.g. "camera slowly zooms in", "character walks left to right").
  • Image-to-video: Describe the motion to apply to the image (e.g. "gentle breeze in the hair", "camera pans across the scene"). See references/prompt_guide.md for patterns.
  • text-to-video:补充主体、动作、镜头运动、光线和风格细节。明确描述动作(例如“镜头缓慢推进”、“角色从左向右行走”)。
  • image-to-video:描述要应用到图片上的动作(例如“头发随微风轻动”、“镜头扫过场景”)。可参考references/prompt_guide.md中的提示词模板。

Step 2 — Run the script

步骤2 — 运行脚本

Text-to-video:
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --prompt "<enhanced prompt>" \
  --duration <seconds> \
  --aspect-ratio <ratio>
Image-to-video:
bash
node {baseDir}/tools/generate.js \
  --mode image-to-video \
  --prompt "<motion description>" \
  --image-url "<public image URL>" \
  --duration <seconds> \
  --aspect-ratio <ratio>
Parameters:
ParameterDefaultDescription
--mode
text-to-video
text-to-video
or
image-to-video
--prompt
(required)Scene or motion description
--image-url
Required for
image-to-video
; public image URL
--duration
5
Length in seconds (typically 4–10)
--aspect-ratio
16:9
16:9
,
9:16
,
1:1
,
4:3
,
3:4
--model
auto
Model ID (e.g.
kling
,
veo
,
grok
,
seedance
);
auto
= proxy picks
Other commands:
CommandDescription
node tools/generate.js --list-models
List available models from the proxy
node tools/generate.js --status --job-id <id>
Check async job status
文本转视频:
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --prompt "<优化后的提示词>" \
  --duration <秒数> \
  --aspect-ratio <比例>
图片转视频:
bash
node {baseDir}/tools/generate.js \
  --mode image-to-video \
  --prompt "<动作描述>" \
  --image-url "<公开图片URL>" \
  --duration <秒数> \
  --aspect-ratio <比例>
参数说明:
参数默认值描述
--mode
text-to-video
可选
text-to-video
image-to-video
--prompt
(必填)场景或动作描述
--image-url
image-to-video
模式必填;公开图片URL
--duration
5
视频时长(通常为4–10秒)
--aspect-ratio
16:9
可选
16:9
,
9:16
,
1:1
,
4:3
,
3:4
--model
auto
模型ID(例如
kling
,
veo
,
grok
,
seedance
);
auto
表示由代理自动选择
其他命令:
命令描述
node tools/generate.js --list-models
列出代理支持的所有可用模型
node tools/generate.js --status --job-id <id>
检查异步任务状态

Step 3 — Return the result

步骤3 — 返回结果

The script returns JSON:
json
{
  "success": true,
  "mode": "text-to-video",
  "videoUrl": "https://...",
  "duration": 5,
  "aspectRatio": "16:9"
}
Send
videoUrl
to the user.

脚本会返回JSON格式的结果:
json
{
  "success": true,
  "mode": "text-to-video",
  "videoUrl": "https://...",
  "duration": 5,
  "aspectRatio": "16:9"
}
videoUrl
发送给用户即可。

Example Conversations

对话示例

User: "Generate a short video of a cat walking in the rain, cinematic."
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --prompt "A cat walking through rain, wet streets, neon reflections, cinematic lighting, slow motion, 4K" \
  --duration 5 \
  --aspect-ratio 16:9

User: "Animate this photo" (user uploads a landscape)
bash
node {baseDir}/tools/generate.js \
  --mode image-to-video \
  --prompt "Gentle clouds moving across the sky, subtle grass movement, cinematic atmosphere" \
  --image-url "https://..." \
  --duration 5 \
  --aspect-ratio 16:9

User: "Make a 10-second vertical video of a coffee pour, slow motion."
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --prompt "Close-up of coffee pouring into a white cup, slow motion, steam rising, soft lighting, product shot" \
  --duration 10 \
  --aspect-ratio 9:16

User: "Use Google Veo for a cinematic shot."
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --model veo \
  --prompt "A dragon flying through cloudy skies, cinematic lighting, 8s" \
  --duration 8 \
  --aspect-ratio 16:9

User: "Animate this portrait."
bash
node {baseDir}/tools/generate.js \
  --mode image-to-video \
  --model grok \
  --prompt "Gentle smile, subtle head turn" \
  --image-url "https://..." \
  --duration 5

用户: "生成一段猫咪在雨中行走的电影质感短视频。"
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --prompt "A cat walking through rain, wet streets, neon reflections, cinematic lighting, slow motion, 4K" \
  --duration 5 \
  --aspect-ratio 16:9

用户: "给这张照片添加动画效果" (用户上传了一张风景图)
bash
node {baseDir}/tools/generate.js \
  --mode image-to-video \
  --prompt "Gentle clouds moving across the sky, subtle grass movement, cinematic atmosphere" \
  --image-url "https://..." \
  --duration 5 \
  --aspect-ratio 16:9

用户: "制作一段10秒的竖版慢动作咖啡倒入视频。"
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --prompt "Close-up of coffee pouring into a white cup, slow motion, steam rising, soft lighting, product shot" \
  --duration 10 \
  --aspect-ratio 9:16

用户: "用Google Veo生成一段电影质感的镜头。"
bash
node {baseDir}/tools/generate.js \
  --mode text-to-video \
  --model veo \
  --prompt "A dragon flying through cloudy skies, cinematic lighting, 8s" \
  --duration 8 \
  --aspect-ratio 16:9

用户: "给这张肖像照添加动画效果。"
bash
node {baseDir}/tools/generate.js \
  --mode image-to-video \
  --model grok \
  --prompt "Gentle smile, subtle head turn" \
  --image-url "https://..." \
  --duration 5

Setup

设置说明

Zero API keys by default. Requests go through a hosted proxy. Set these for a custom proxy or token:
VariableRequiredDescription
VIDEO_STUDIO_PROXY_URL
NoProxy base URL
VIDEO_STUDIO_TOKEN
NoAuth token if the proxy requires it

默认无需API密钥。请求会通过托管代理发送。若要使用自定义代理或令牌,可设置以下环境变量:
变量是否必填描述
VIDEO_STUDIO_PROXY_URL
代理基础URL
VIDEO_STUDIO_TOKEN
若代理需要验证,此处填写授权令牌

Knowledge Base

知识库

  • references/prompt_guide.md — Prompt patterns for text-to-video and image-to-video.
  • references/models.md — Model list, capabilities, and selection guide.
  • references/calling_guide.md — Per-model endpoint details, input parameters, and special handling.
  • references/prompt_guide.md — 文本转视频和图片转视频的提示词模板。
  • references/models.md — 模型列表、功能及选择指南。
  • references/calling_guide.md — 各模型的端点详情、输入参数及特殊处理说明。