OpenAI launches Images 2.6 with GIF creation and API controls

Images 2.6 can turn images into GIFs, and OpenAI says ChatGPT users can make an animated GIF from either a prompt or an image.[1][2] Users can adjust playback speed, edit individual frames and share the result on repeat.[2] The Verge reported that ChatGPT previously could not natively generate a GIF in one step.[3] For teams creating short visual assets, the key change is that GIF generation and frame-level adjustments are now part of the described workflow.[2]

OpenAI says GPT-Image-2.6 Flare can produce an image in as little as six seconds when quality is set to low.[1] It says Flare also improves layout quality for posters, product imagery and other professional visuals.[1] GPT-Image-2.6 Sunburst is positioned for higher-quality generation, with greater consistency across edits at medium or high quality settings.[1] Both models are available in OpenAI’s API.[1]

Image markup, which OpenAI says was previously available in ChatGPT, is now also available in the API.[1] SVG exports are described as ready for use across websites, apps and print.[1] A new complexity parameter lets developers adjust how much planning the model does, and OpenAI recommends low complexity for most editing tasks to make edits faster.[1] OpenAI also says Images 2.6 generates images 50% faster than before.[1]

OpenAI says Images 2.6 is available globally in ChatGPT and Codex across all subscription tiers on desktop, mobile and web.[1] Sunburst and Flare are available through the API.[1] OpenAI says people create four billion images per week across ChatGPT, Codex and the API, averaging more than half a billion creations per day.[1] The Verge reported that the weekly figure rose from three billion images per week reported in September.[3] OpenAI also says startup Town used Images 2.6 through the API to explore animated characters for workplace interactions.[1]