• STATIC
  • MOTION
  • REFINEMENT
  • ITERATION

How to generate images and videos with your AI

Connect Z.AI to your agent to turn descriptions into visual media. Once connected, your AI handles the heavy lifting of creation.

Ask AI about this page

Short answer

How can I make images and videos using my AI?

You give your AI a text description, and it uses Z.AI to render the visual. This works for both static pictures and moving clips. You'll see the results directly in your chat.

Visual outcomes

What you get

The different types of media your agent can produce.

STATIC

High-quality images

The AI produces single frames based on your text. These are ready for use in documents or presentations.

MOTION

Video clips

Your agent creates short video sequences from your descriptions. These clips bring your ideas to life through movement.

REFINEMENT

Human review

You look over the generated media to ensure it matches your vision. You decide if the output is perfect or needs a new prompt.

ITERATION

Prompt adjustments

If the image or video isn't right, you tell your AI what to change. It uses the new details to try again.

The workflow

What your AI does when a prompt arrives.

The AI translates your words into technical instructions for the media engine.

  1. Create images

    Your agent takes your description and triggers the image creation process.

    generate_image

  2. Create videos

    For motion requests, the AI initiates the video generation sequence.

    generate_video

  3. Track progress

    Since video takes time, the AI monitors the status of the generation task.

    get_async_result

  4. Deliver media

    The AI checks the final status and presents the completed file to you.

    get_async_result

Try it

Copy these to start.

Use these prompts to test the connection immediately.

Starting points

These are basic ideas. Swap out the bracketed text with your own specific details.

Z.AI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_YbDoY2kX4ZG9rzJgMpkdkPO2uOhqn2U6SvelxeRg/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Z.AI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "zai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_YbDoY2kX4ZG9rzJgMpkdkPO2uOhqn2U6SvelxeRg/mcp"
    }
  }
}
Copy into chat04

  • Generate an image of a futuristic city skyline in a cyberpunk style.

  • Create a 5-second video clip of waves crashing against a rocky shore.

  • Make a high-quality image of a golden retriever wearing a space suit.

  • Generate a video of a forest during autumn with leaves falling slowly.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Z.AI once, then ask.

Click the link to set up the connection. Your credentials stay encrypted, and you can find the full tool list on the Connector page.

Connect Z.AI to your AI

FAQ

Common questions

  • 01

    Can the AI edit an existing image I upload?

    No. The current tools only create new visuals from text prompts.

  • 02

    Does the AI decide when the video is finished?

    The AI uses a tool to check the status, but you are the one who decides if the final result is acceptable.

  • 03

    Can I generate audio along with the video?

    No. This connector is strictly for image and video generation.

  • 04

    How does the AI handle long video requests?

    The AI uses an asynchronous process to track the task until the video is ready for you.

  • 05

    Can the AI delete files it previously generated?

    No. The tools only allow for the creation and status checking of new assets.

  • More questions about Z.AI? The Connector page answers them. See everything the Z.AI Connector can do

Connect Z.AI to Claude, Cursor, ChatGPT & more