• EXPANSION
  • VARIATION
  • ITERATION
  • HUMAN

How to extend and modify images with your AI

Connect your agent to Leonardo.ai to change existing pictures or grow their borders. You'll move from a single file to a set of new, expanded, or styled compositions.

Ask AI about this page

Short answer

How can I extend or change an image using my AI?

You upload a source image and tell your agent how to change it or where to add more space. The AI then generates new versions that either expand the frame or apply new styles to the original content.

The results

What you'll get

The AI handles the pixel work based on your specific instructions.

EXPANSION

Wider compositions

The AI adds new scenery around your original photo. This lets you turn tight shots into wide landscapes.

VARIATION

New art styles

You can take a photo and ask the AI to redraw it in a different aesthetic. It keeps the core structure while changing the look.

ITERATION

Multiple options

The agent produces several different versions of your request. You can pick the best one or try a different prompt.

HUMAN

Creative control

The AI does the rendering, but you provide the vision. You'll need to refine your prompts to get the exact result you want.

The workflow

What your AI does when the image arrives.

The AI processes your file and applies your instructions to create new visuals.

  1. Upload source

    Your agent takes your initial file and prepares it for the generation process.

    upload_init_image
  2. Analyze frame

    The AI looks at the existing image to understand the context and boundaries.

    upload_init_image
  3. Generate changes

    The agent creates new versions of the image based on your specific text instructions.

    create_variation
  4. Deliver output

    The AI provides the final modified or expanded images for you to use.

    create_variation

Try it

Copy these to start.

Use these prompts to begin working with your agent.

Starting points

These are opening lines. Replace the bracketed descriptions with your own details.

Leonardo.ai Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_y9qRzWWnGSVBvmQMYzSP2JGQCYBThJESo5HQfoqx/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 — Leonardo.ai capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "leonardoai-generative-ai-models-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_y9qRzWWnGSVBvmQMYzSP2JGQCYBThJESo5HQfoqx/mcp"
    }
  }
}
Copy into chat04
  • Take this image and unzoom it to show more of the mountain range.

  • Use this photo as a base to create a variation in a watercolor style.

  • Expand the boundaries of this portrait to make it a wide landscape shot.

  • Modify this image to change the lighting from midday sun to a sunset glow.

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

Start here

Connect Leonardo.ai once, then ask.

Link your account once and your agent is ready. Your login stays encrypted on our side.

Connect Leonardo.ai to your AI

FAQ

How this task behaves

  • 01

    Can the AI edit specific small objects in my photo?

    No. The tools are for creating variations of the whole image or expanding the borders.

  • 02

    Will the AI change my original uploaded file?

    No. The AI generates new images based on your upload. Your original file stays exactly as it is.

  • 03

    Can I use this to remove people from a background?

    No. The current tools focus on expanding the frame or changing the style, not on object removal.

  • 04

    Does the AI keep faces identical in every variation?

    No. While the AI uses the original for guidance, facial features can change during the variation process.

  • 05

    Can the AI create a video from my image?

    No. The available tools are strictly for image-to-image transformations and unzooming.

  • More questions about Leonardo.ai? See everything the Leonardo.ai Connector can do

Connect Leonardo.ai to Claude, Cursor, ChatGPT & more