画像から動画への変換LABSCO SUMMARY
One image in, one short clip out — with the model constraints spelled out.
The useful part of the documentation is the constraint table: length and resolution are not free choices, they depend on which model you pick, and getting that wrong is the usual first failure. Generation is asynchronous by nature, so plan on a poll rather than a single blocking call.
What it is
An MCP server for Vidu's image-to-video API. Generation is asynchronous, so the surface is three steps: upload an image if you have a local file, start a generation from an image URL with a prompt and model settings, and poll the returned task id until the clip is ready.
What you get
- Image-to-video generation from an
image_url, with an optional textpromptof up to 1500 characters, aseedfor reproducibility,movement_amplitudeto control how much motion is in frame, and an optionalcallback_urlfor asynchronous notification - Model choice between viduq1, vidu1.5 and vidu2.0, with the length and resolution constraints each one imposes — viduq1 does 5 second clips at 1080p only, while vidu1.5 and vidu2.0 do 4 or 8 seconds, with 8 second output limited to 720p
- Background music on 4 second clips through the
bgmflag - A status check that takes the
task_idreturned by generation and reports progress along with credit usage - An upload step taking
image_pathandimage_type, for png, webp, jpeg or jpg files
Requirements
A Vidu API key from vidu.com, supplied as VIDU_API_KEY. Node.js v14 or newer; the package is vidu-mcp-server (1.0.0 in package.json). Build with npm run build and point the client at build/index.js. Uploads are capped at 10MB, while images referenced by URL may be up to 50MB.
Setup effort
Build from source
USE CASES
01
Animating a still you already have online
Pass the image URL with a short prompt and a movement setting, then poll until the clip is ready.
02
Working from a local file
Upload the image first, then run generation against the returned reference.
03
Producing a repeatable result
Fix the seed so the same image and prompt return the same clip when you re-run it.
3 tools
Listed in project docs. Your client may show a different list.
生成状況の確認画像アップロードBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- Node.js
- VIDU_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
MCP Clients
Gemini CLI
GEMINI CLI · JSON
{
"mcpServers": {
"vidu": {
"command": "node",
"args": [
"<YOUR_PATH_TO_VIDU_MCP_SERVER>/build/index.js"
],
"env": {
"VIDU_API_KEY": "<YOUR_VIDU_API_KEY>"
}
}
}
}
