Ideogram 0.1 is open to everyone for free — August 29, 2023

Today, we're opening Ideogram to everyone on the planet! Ideogram enables you to turn your creative ideas into delightful images, in a matter of seconds. It's free and has no limits, and it can render text! Sign up at https://ideogram.ai and start creating images from text, and get inspired by the creativity of others.

Ideogram (pronounced eye-diogram) is on a mission to help people become more creative through generative AI. We believe everyone has an innate desire to create and share their creations with each other. Our goal is to make creative expression universally accessible and fun. To this end, we invite dreamers from all backgrounds to join and collectively shape a more creative future. Please share your valuable feedback with us by liking your favorite images.

One week ago, on Tuesday, August 22, we announced the formation of Ideogram. We're humbled to see an incredible amount of enthusiasm and excitement from our growing community. In just one week, we've amassed more than 90,000 users, who have generated more than 3 million images. Our users are enjoying the product and are communicating with each other through generating typographic images. We're committed to improving the quality of Ideogram and making it easy, fun, safe, and inclusive for everyone.

Ideogram 0.1 is a new foundation AI model that turns text into images. It is built from scratch by the Ideogram team, and it solves one of the major flaws of existing generative AI tools: it can finally render coherent text inside images. It supports many fonts and text styles and produces beautiful typography that would otherwise be extremely time-consuming to make. Our text rendering feature paves the way for many creative applications, as our users have already made thousands of logos, posters, graphic designs, and images that convey interesting and fun messages.

One of the key features of Ideogram is that it supports a diverse set of image style tags, including: Illustration, Typography, Poster, Photo, 3D Render, Architecture, Fashion, Product, Painting, Vibrant, Portrait Photography, Cinematic, Dark Fantasy, Wildlife Photography, Anime, and Graffiti. These style tags can be combined in interesting ways to help users produce the type of content that they want, and our state-of-the-art AI technology ensures that these style tags are reflected accurately in the generated images.

Our engineering team includes AI experts who made significant contributions to generative AI, including the development of Denoising Diffusion Models for image, audio, 3D, and video generation at Google Brain. We developed the technology breakthrough that enabled the recent wave of generative media products. We're just getting started and we'll release more advanced generative media models in the future.

If you're excited about our mission of using generative AI to help people become more creative, then we'd love to hear from you. We are hiring for several key roles in engineering, research, design, and operation in Toronto. You can apply here.