An Infinite Visual Browser

Flipbook is an infinite visual browser where every page you see is a generated image, not HTML. There are no text overlays, no predefined links, no buttons — just pixels rendered on demand. You click anywhere on the image to dive deeper into that topic, and the Flipbook infinite visual browser generates a brand new visual page in real time.

Yes. All text you see in the Flipbook infinite visual browser is rendered as pixels by the image model. There are no text overlays applied on top of the images. Occasionally, the model might render text imperfectly or in the wrong place — this improves as the underlying models get better.

The information in each visual page of this infinite visual browser comes from a combination of agentic web search and the image model's own world knowledge. There may be occasional inaccuracies, but it's a useful starting point and usually grounded in real data online. You can expect a similar level of factual accuracy to what you might get using ChatGPT, Gemini, or Claude.

A picture is worth a thousand words, yet most of our screens are filled with text and colored rectangles. We built Flipbook, the infinite visual browser, because we wanted a computing experience full of rich, beautiful visuals made just for you, generated just in time. Instead of sipping an ocean of wisdom through a tiny straw, the Flipbook infinite visual browser finds the most effective way to communicate anything to you — whether that's a single word, an illustration, or a photorealistic rendering.

Right now, Flipbook, the infinite visual browser, is designed for open-ended exploration and learning. As image and video models become more accurate and performant, this infinite visual browser could include more real data, become more interactive, and even take actions or store its own data. We imagine a world where all the tools you use are as rich and visual as the world we live in.