OpenAI’s Images 2.6 adds GIF animation and faster picture generation
ChatGPT and the API can now turn prompts or photos into looping GIFs; OpenAI says stills are about 50% faster, with Flare and Sunburst API options.
OpenAI on Wednesday released Images 2.6, an update to the image generator inside ChatGPT, Codex and its developer API. The company says the model creates still pictures about 50% faster than before and can turn prompts, sketches or photos into short looping GIFs—repeating animations often used in chats and social posts.
In ChatGPT and Codex, users can animate a brand mascot, character or product shot, set playback speed, and keep editing so characters, products and brand details stay consistent across frames. OpenAI said people now create about 4 billion images a week across ChatGPT, Codex and the API—more than half a billion a day on average.
In the API, developers choose GPT-Image-2.6 Flare or Sunburst. OpenAI says Flare prioritizes speed: when quality is set to low, Flare images can appear in as little as six seconds, and it also improves layout for posters and product imagery. Sunburst targets higher detail and stronger consistency across edits when quality is set to medium or high.
New developer controls include image markup—already in ChatGPT—to pinpoint where an edit should land; SVG export for websites, apps and print; a complexity setting that changes how much planning the model does (OpenAI recommends low complexity for most quick edits); and separate image-quality controls for visual detail. Images 2.6 is available globally today in ChatGPT and Codex on all subscription tiers on desktop, mobile and web. Flare and Sunburst are available in the API; OpenAI posts API pricing separately.
Source: OpenAI: Introducing Images 2.6