← All guides

Google · Chat app

How to Generate AI Images in Gemini

Connect PixelMCP to Gemini and you can ask for images in plain language, right in your conversation. Gemini picks the right model (Nano Banana, GPT Image, FLUX, Seedream or Recraft), PixelMCP generates the images and they appear in the chat, ready to download.

Add PixelMCP to the Gemini app as a custom app.

Before you start: 18+, in the US, personal Google Account with Keep Activity on. English only for now. You'll also need a PixelMCP account. Get 100 free credits
  1. 1

    Add a custom app

    At gemini.google.com open Settings → Connected Apps, and under Custom apps click Add a custom app.

  2. 2

    Paste the URL and sign in

    Paste this MCP server URL, click Next, then sign in to PixelMCP and approve access:

    https://pixelmcp.com/mcp
  3. 3

    Use it

    In a chat, type @ and select PixelMCP, then describe the image you want.

Things to try

  • “@PixelMCP make a 16:9 social card announcing our new podcast episode.”

Image models you can use in Gemini

Not sure which to pick? Compare the models.

FAQ

What do I need to use PixelMCP in Gemini?+

18+, in the US, personal Google Account with Keep Activity on. English only for now. You also need a PixelMCP account, which starts with 100 free credits.

Which image models can I use in Gemini?+

Nano Banana 2 and Pro, GPT Image 2 and GPT Image 2 HD, FLUX.2 Pro and Klein, Seedream 5.0 Pro and Recraft V4.1. Name a model in your prompt or let the assistant choose.

How much does it cost?+

You pay per image with credits, from 6 credits (6¢) an image. There's no subscription and credits never expire. New accounts get 100 free credits.

How long does setup take?+

About a minute. Add the PixelMCP server URL to Gemini, sign in once, and you're ready to generate.

Menus change often. If a label here doesn't match what you see, look for “Connectors”, “MCP” or “Integrations” in Gemini's settings, or check Google's docs.