Kenji Hata

Researcher and Member of Technical Staff at OpenAI working on image generation, including 4o image generation/GPT-Image-1, Sora 2, GPT-Image-1.5, o3/o4-mini, and thinking with images. Previously worked on computer vision at Google Research and studied at the Stanford Vision Lab.

Images 2.0 Moves Image Generation From Novelty to Workflow Tool

OpenAI product lead Adele Li and researcher Kenji Hata argue that Images 2.0 marks a shift from novelty image generation to a working visual layer inside ChatGPT. In a podcast discussion with Andrew Mayne, they point to 1.5bn images generated weekly, sharper text rendering, stronger photorealism, broader aspect ratios and more consistent characters as evidence that the model is moving into education, internal communication, marketing assets, software mockups and other practical creative work.

OpenAIMay 14, 202612 min read