OpenAI releases Images 2.6 with GIF animation
OpenAI has released Images 2.6 across ChatGPT, Codex and its API, adding GIF animation and SVG export, cutting generation time by half, and giving developers two model tiers to choose between.
OpenAI announced Images 2.6 on its website. It follows Images 2.5, which we covered earlier. The update is available globally today in ChatGPT and Codex on all subscription tiers, on desktop, mobile and web.
OpenAI says Images 2.6 generates images 50% faster than the previous version. The API offers two models:
- GPT-Image-2.6 Flare is the faster option. With quality set to low, it can return an image in as little as six seconds. OpenAI also says it improves layout quality for posters and product imagery.
- GPT-Image-2.6 Sunburst is meant for detailed work. OpenAI says it delivers higher-quality output and better consistency across edits when quality is set to medium or high.
The main new feature is GIF output. OpenAI suggests uses such as animated brand mascots, memes and storyboards made before video production, and says even a simple sketch can be turned into an animated character. It named Town, a startup building an AI work assistant, as an early API user that tried animated characters.
Developers also get several new controls:
- Image markup, already in ChatGPT, now comes to the API so users can mark the exact area they want changed.
- SVG export produces files ready for websites, apps and print.
- A complexity parameter sets how much planning the model does before generating. It works separately from the existing quality setting. OpenAI recommends low complexity for most edits and medium or high for scenes with many elements or constraints.
OpenAI says users create 4 billion images per week across ChatGPT, Codex and the API.
The post links to pricing and a system card but does not include prices or benchmark results.