Image Generation

The Image Generation ability lets an agent create images from a description. The image model isn't a separate setting — it's whichever saved model you've ticked for Image-out in the model grid (see Models & Providers). The app figures out how to talk to that model automatically based on its provider, including OpenRouter image models (which use a different request style than OpenAI's — handled for you).

Generated images are saved with your other per-user files so they don't disappear when a provider link expires, and they appear inline in chat and on your Dashboard pages.

To read images you supply (rather than create new ones), see Image Vision (Reading Images).

Related: Abilities, Attachments & Voice Input (for images you supply).