Image Studio: AI Image Generator for Study

From a text prompt describing what you want — like "a labeled diagram of the human heart" — and, in the Image Studio, from up to 3 reference images you upload or pick from your content library. In-page and flashcard generation are text-prompt only; reference images are a Image Studio feature.

It depends where you generate. From inside a page or flashcard, the image you pick is attached directly to that study component. From the Image Studio, images are saved with their prompt, model, preset, and aspect ratio — downloadable on paid plans. In chat, the image is embedded right in the conversation.

In pages and flashcards you choose between three styles — Cartoon, Realistic, and Sketch. The Image Studio goes further: pick one or more models — Nano Banana 2 Lite, GPT Image, and Grok Imagine, alongside the default Muse Image — plus study-ready presets (like labeled diagrams or anatomy) and an aspect ratio (1:1, 16:9, 9:16, 4:3, or 3:4), or skip the controls entirely and describe what you want in the Image Studio chat.

Generated images aren't editable directly. To change one, regenerate with a new prompt, or in the Image Studio use it as a reference image and remix from there. The Image Studio's reference-image workflow is the way to iterate on a visual you've already made.

Yes. During beta, Free includes 2 lifetime images with no reset, Premium 40 per week, and Laureate 80 per week, shared across Image Studio and chat. Each image or edit uses one image per selected model, separately from AI Creation Credits. Failed images return their allowance. Paid allowances reset weekly with no rollover and may change during beta. Normal Chat message limits still apply.

In Image Studio, each selected model produces one image and uses one image from your weekly allowance. Select several models to compare them side by side. Images produced inside other agent-created artifacts remain included in those features.

Yes, in the Image Studio. Upload 1–3 reference images from your device, or select images you've made before from your content library, and generate edits or variations from them. In-page and flashcard generation are text-prompt only.

In-page and flashcard generation are the fast path: type a prompt, pick Cartoon, Realistic, or Sketch, and the image attaches to your study component. The Image Studio is for advanced work — multiple models, presets, aspect ratios, reference images, and a chat where you can describe changes in plain language — and is where you experiment before embedding the result.

Quality and how closely an image follows your prompt depend on the underlying model, so very complex or highly specific requests may not land on the first try. Refine your prompt and regenerate, or use a reference image in the Image Studio to steer the result closer to what you have in mind.