OpenAI on Wednesday updated ChatGPT and Codex with the Images 2.6 model, which adds support for GIF creation and faster image generation on both platforms.
Images 2.6 generates photos 50% faster than previous models, the company says. Developers can choose between GPT‑Image‑2.6 Flare and Sunburst for their outputs, depending on the speed or quality they want. Flare, for instance, delivers outputs in as little as six seconds, while Sunburst generates more accurate images when its quality is set to medium or high.
Support for GIFs is the biggest plus from this update for regular users. Just as you do with image-generation prompts, just describe the kind of imagery you’d like to generate, and Images 2.6 does the rest.
The feature can help marketers and creators “animate a brand mascot for a campaign, create reactions and memes for social media, or use animated storyboards to explore character movement before video production,” OpenAI says.
If you already have a character or mascot you’d like to create GIFs from, just upload a rough sketch and pair it with a text prompt. In an X post, the company also mentioned that creators can adjust the GIF’s speed or modify individual frames before sharing it with others. You can also save reference images of characters, pets, or yourself once, and use their names in your prompts instead of uploading images every time.
I tried creating a GIF of a man walking into a door headfirst, and the output didn’t disappoint.
Recommended by Our Editors
ChatGPT vs. Gemini: Don’t Pick a Chatbot Until You Read This
Is That Image, Audio, or Video Made by AI? Google’s AI Detector Will Tell You
ChatGPT Can Now Take Control of Your Chrome Tabs
(Credit: OpenAI/ Jibin Joseph)
Images 2.6 with support for GIFs is now available for ChatGPT and Codex users across all subscription tiers on web, desktop, and mobile. On average, OpenAI platforms currently generate 4 billion images per week, the announcement post added.
Disclosure: Ziff Davis, PCMag’s parent company, filed a lawsuit against OpenAI in April 2025, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.
About Our Expert
Jibin Joseph
Contributor
Experience
Jibin is a tech news writer based out of Ahmedabad, India. Previously, he served as the editor of iGeeksBlog and is a self-proclaimed tech enthusiast who loves breaking down complex information for a broader audience.
- How to Watch the F1 Brazilian Grand Prix Live, Even for Free
- New Moto Watch Fit 27 Packs 12-Day Battery, Polar-Powered Fitness Insights
- iOS 27.3 Lets Apple Start Checking Shared iCloud Links for Harmful Content
- How to Watch Today’s Fenerbahçe vs. Liverpool UCL Game Live For Free
- iPhone 18 Tipped to Arrive Next Year With Bigger Battery, Higher Price
- More from Jibin Joseph
