Generate and edit images directly in Copilot
By Steven Van ·
Image generation is in public preview on paid Copilot plans, works in VS Code, the Copilot app and CLI, and can be disabled by admins.
Copilot can now generate and edit images from natural language. The selected reasoning model calls a dedicated image-generation tool powered by GPT Image 2.5 Flare, shows a preview inline, and saves the result to the project. GitHub says this removes the need to leave Copilot for a separate tool, re-describe the request, and bring the image back by hand, as set out in the release note.
How it works
Images can be requested conversationally in any Copilot chat session, either as a new request or in the middle of a coding task. Copilot previews the generated image inline and saves it directly to the workspace. To try it, open a Copilot chat in VS Code, the GitHub Copilot app, or Copilot CLI and describe the image you want.
Controls
- Organization and enterprise owners can turn off image generation by disabling the image generation model in Copilot model policies.
- A visible "Made with AI" watermark can be added to images Copilot generates and edits. It is off by default and is opt-in.
Availability and billing
Image generation is in public preview for Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. It is billed separately from the chat model, based on image tokens that count toward the plan's AI credits.
