Images
Illustrations generated from the scene, in the chat.
Turn on image generation per conversation in the settings drawer, or as a preset default. Replies can then produce a scene illustration automatically.
After a reply lands, a prompt-writer model writes an image prompt and the image model renders it. The reply is never delayed. The image appears when ready.
A placeholder marks the spot while generating. If generation fails, the chat continues without the image.
Pick any catalog image model, or let the engine choose a free one. The prompt-writer uses your utility model. Custom-provider image models go straight to your endpoint.
Upload reference images in the settings drawer to keep faces, outfits, or styles consistent. The primary character's avatar can be included automatically.
Up to six references ride along per request, capped by what the image model accepts.
Style templates prefill the prompt instruction with a look: photorealistic, anime, painterly, and more. Edit the instruction after applying a template.
With preview enabled, the written image prompt pauses for review: edit it, approve it, or skip the image.
Any generated image can be regenerated from its overlay menu. The new render replaces the old one in the same spot.
Images live in messages as {{inlay::<id>}} tokens rendering from local storage. Exported conversations carry the bytes, so images survive the trip.