Copilot can generate images with GPT Image 2.5 Flare
In public preview, a Copilot chat can generate or edit an image, preview it, and save it into the project. A watermark is off unless you opt in.
Official source (opens in a new tab)
GitHub's changelog for 28 October 2026 says you can generate and edit images in natural language inside GitHub Copilot. When you ask for an image, the selected reasoning model calls an image tool powered by GPT Image 2.5 Flare, previews the result in the chat, and saves it to the project. The feature is in public preview for Copilot Pro, Pro+, Business, and Enterprise, in Visual Studio Code, the GitHub Copilot app, and Copilot CLI.
Organization and enterprise owners can turn image generation off by disabling that model in Copilot model policies. A visible "Made with AI" watermark is optional and off by default. GitHub says image generation is billed separately from the chat model, on image tokens that count toward the plan's AI credits.
Who it's for: someone already in a Copilot chat who needs a visual asset in the project, and does not want to leave for a separate image tool.
Fits: Best for Images stays Midjourney. This is a preview inside a coding chat, not a generator you open to make the frame. GitHub Copilot stays fourth on Best for Vibe Coding. The image guide does not add Copilot. The verdicts are unchanged.