Another image generator? Don’t we have enough to choose from between Midjourney, OpenAI’s Dall-E 2, and Stability AI’s Stable Diffusion? Well, Ideogram has a major selling point, as it may have finally solved a problem plaguing most other popular AI image generators to date: reliable text generation within the image, such as lettering on signs and for company logos.
The company offers a number of preset image generation styles on its web app at ideogram.ai, including one labeled “typography,” which renders lettering in different colors, fonts, sizes and styling. Other preset styles include 3D rendering, cinematic, painting, fashion, product, illustration, conceptual art, ukiyo-e and others. You can select multiple styles at once and apply them all.
Ideogram is already available for signup in beta. And its Discord server and web app are already filled with examples of people generating lettering and images with lettering that are impressive compared to the current state-of-the-art (though not always entirely accurate) options.
However, Ideogram also lacks some of the other features available on rival image generators like zoom out/outpainting, and its results were less consistent in our tests. It even had difficulty rendering its own name, “Ideogram,” and was better at rendering more common words.
The company took the occasion of its launch and beta release to subtly highlight this feature with a post on X (formerly Twitter) including its mission statement, “help people become more creative,” generated using its tool.
Other investors in Ideogram include AIX Ventures, Golden Ventures, Two Small Fish Ventures, and industry experts Ryan Dahl, Anjney Midha, Raquel Urtasun, Jeff Dean, Sarah Guo, Pieter Abbeel, Mahyar Salek, Soleio, Tom Preston-Werner and Andrej Karpathy.
While it’s still early days for Ideogram, differentiating by offering a reliable typographic generator is a smart move and may help it appeal to graphic designers or those who would otherwise have to hire them to create imagery with eye-catching text baked in.
And other AI image generators are continuing to add new features, too. Just this week, Midjourney launched its new “vary region” feature to add, remove, and subtract portions of generated imagery.