Updated
Updated · The Verge · Sep 8
OpenAI Launches ChatGPT Images 2.5, Cutting Latency Up to 50% With Sketch
Updated
Updated · The Verge · Sep 8

OpenAI Launches ChatGPT Images 2.5, Cutting Latency Up to 50% With Sketch

3 articles · Updated · The Verge · Sep 8

Summary

  • OpenAI on Tuesday rolled out ChatGPT Images 2.5 and a new Sketch tool that lets users draw a doodle inside ChatGPT and turn it into a detailed AI-generated image.
  • Typing @Sketch opens a drawing window, and users can now also click directly on parts of an image to request edits such as changing eye color.
  • Images 2.5 adds more natural lighting, richer textures and better adherence to editing instructions across multiple turns, while reducing image-generation latency by up to 50% versus Images 2.0.
  • The update is available now across desktop, mobile and web for ChatGPT, ChatGPT Work and Codex users, extending OpenAI's push to make image creation more interactive and iterative.

Insights

Why are some users calling OpenAI's massive new image upgrade flat and generic despite promises of hyper-realistic detail?
If AI metadata can be easily stripped, how will we ever truly distinguish human art from a flawless Sunburst generation?