OpenAI releases Images 2.6, generating images 50% faster across ChatGPT, Codex and the API
The update adds GIF output and gives API developers a choice between a fast model and a higher-detail one.
OpenAI has released Images 2.6, an update to its image generation that is now available in ChatGPT, Codex and the API. The model generates images 50% faster, and in the API developers can pick between GPT-Image-2.6 Flare, which can produce a low-quality image in about six seconds, and Sunburst, aimed at higher detail and better consistency across edits at medium or high quality. Users can now turn images into GIFs, which suits animated mascots, memes and storyboards, and API developers gain image markup, SVG exports and a new complexity parameter for controlling how much planning the model does. OpenAI says people now create about 4 billion images a week across its products, more than half a billion per day. Images 2.6 is rolling out globally today to ChatGPT and Codex users on all subscription tiers across desktop, mobile and web.
Why it matters
For people who use ChatGPT and Codex, image generation now runs at half the previous time, and the update is rolling out to every subscription tier on desktop, mobile and web. The new GIF option lets users turn images into short animations, which fits mascots, memes and storyboards. OpenAI says people already create about 4 billion images a week across its products, so the change reaches a large share of its user base at once.
Matters or hype?
Does this story matter, or is it hype? Vote before you see what everyone else said.
Sources · 1
- OpenAI News ↗ Primary source