ChatGPT Images 2.6 Brings GIFs and Faster AI Art
OpenAI's ChatGPT Images 2.6 adds animated GIF creation, reusable reference images, and 50% faster generation, with new Flare and Sunburst models for developers.
OpenAI has released ChatGPT Images 2.6, a new version of its image tool that can turn a text prompt or a photo into an animated GIF. The update is available now in ChatGPT and Codex across all subscription tiers, on the web, desktop, and mobile. It also brings two new models for developers through the API.
GIFs arrive in ChatGPT
The headline feature is animation. You can describe a short clip in words, or upload a photo, and ChatGPT returns a looping GIF instead of a still image. You can adjust the playback speed and edit individual frames before you share it. OpenAI's examples include turning a simple sketch into an animated character and building a flipbook-style loop from variations of one character. The GIF feature is rolling out gradually, so it may not appear in every account right away.
Reference images you save once
Images 2.6 also adds reusable reference images. You can save a character, product, or style once and use it again across new generations, instead of uploading the same image as input every time. That makes it easier to keep a mascot or a product looking the same across many images.
50% faster, with two new API models
OpenAI says image generation is now 50% faster than before. For developers, the API gets two new models: GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. Flare is the fast option. At the low-quality setting it can produce an image in as little as six seconds, and OpenAI says it improves layouts for posters and product imagery. Sunburst is the quality option, built for higher-quality generation and stronger consistency across edits at medium or high quality. The API also adds markup-guided editing and SVG export, so developers can export clean vector graphics from their images. The scale behind the release is large. OpenAI says ChatGPT and the API now generate more than 4 billion images each week, up from 3 billion in September. API pricing for the new models is set at 8 dollars per million input tokens and 30 dollars per million output tokens.
Who gets it, and the catch
Images 2.6 is available globally in ChatGPT and Codex across all subscription tiers. The GIF feature is the part rolling out in stages, so some users will need to wait a few days. The usual caveats apply. A moving image spreads faster than a still one, and a convincing GIF of a real person can mislead. OpenAI's system card for Images 2.6 describes extra safeguards for GIF creation, but users should still treat AI-made animations of real people with care.
Why it matters
GIFs are the internet's short-form visual language, used for reactions, memes, and product demos. Putting animation inside ChatGPT means anyone can make a looping visual without opening an animation editor, and that will show up quickly in chats, social posts, and marketing. For developers, the Flare and Sunburst split is the more useful change. Speed and consistency are now separate choices, so a team can pick fast drafts for testing and the steadier model for finished work. With more than 4 billion images a week already flowing through OpenAI's tools, small speed and quality gains add up fast.
Sources
- OpenAI - https://community.openai.com/t/images-upgraded-introducing-chatgpt-images-2-6/1412901/1 - Gadgets 360 - https://www.gadgets360.com/ai/news/openai-images-2-6-update-gif-creation-chatgpt-new-api-models-12287035 - ETV Bharat - https://www.etvbharat.com/en/technology/openai-introduces-images-2-6-in-chatgpt-codex-api-for-animated-gifs-reference-image-retention-enn26110501358