The Creator

OpenAI's first image model that thinks before it draws

“Eight consistent characters in one prompt is the feature I've been screaming for since DALL-E 2. Storyboards, character sheets, scene consistency across a comic — these all just became practical. The multilingual text rendering is also a game-changer for global content teams who've been manually editing text onto AI images in Photoshop. This ships.”

OpenAI's image model finally thinks before it draws — and text comes out readable

“Text that actually renders correctly in AI images is genuinely transformative for content creation. Mockups, social graphics, ad creatives with overlaid copy — I've been waiting for this for two years. The 8-image consistent character batch is also a game changer for storyboarding and consistent brand imagery.”

OpenAI's gpt-image-2 replaces DALL-E with 4096px output and near-perfect text

“Accurate multilingual typography in generated imagery is something the design community has been waiting years for. If the text quality holds at production scale, this replaces a painful manual step for anyone doing international content. The infographic and slide generation demos alone would justify the upgrade.”

Microsoft's in-house image model — 41% cheaper, faster

“For creative work, 'efficient' is a red flag. I'd rather pay for the full MAI-Image-2 and get better detail. This feels like a model designed for product managers, not designers — useful for mockups and batch jobs, but not for hero images or campaigns.”