OpenAI introduced Images 2.6 on Wednesday, November 4, bringing faster image generation, animated GIF creation and finer editing controls to ChatGPT, Codex and the API. Here is a plain-language look at what the company announced in its launch post.

Faster, with more consistent edits

According to OpenAI, Images 2.6 generates images 50% faster than before. In the API, developers can choose between two models: GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. OpenAI says Flare, set to low quality, can produce an image in as little as six seconds and also improves layout quality for posters, product imagery and other professional visuals. Sunburst is aimed at work needing greater detail and precision, bringing higher-quality generation and more consistency across edits when quality is set to medium or high.

The pitch is consistency: keeping characters, products and brand details the same as you refine an image over multiple rounds of editing, rather than starting from scratch each time.

Animated GIFs

The headline feature is GIF creation. OpenAI says people can “bring motion to your images with GIFs,” whether animating a brand mascot, turning a product shot into a loop, or making reactions and memes for social media. The company also suggests creators could use animated storyboards to explore character movement before video production. Even a simple sketch can become an animated character, OpenAI says.

In the launch post, partner OpenArt’s CEO Coco Mao described GIFs as “the native language of social media.” The examples in the post use prompts that ask for a six-frame sprite sheet arranged in a grid, which then loops as a GIF.

New tools for developers

For developers, OpenAI lists several additions in the API:

  • Image markup: already available in ChatGPT, it now comes to the API so teams can point to exactly where a change should happen.
  • SVG exports: designs can be exported as SVG, which works across websites, apps and print.
  • A complexity parameter: it lets developers adjust how much planning the model does. OpenAI recommends low complexity for faster edits and medium or high for scenes with many elements or constraints.
  • Quality controls: image quality governs visual detail and fidelity, while complexity guides how much goes into the scene.

Figma and a startup called Town are named in the post as early users. Figma Weave’s Creative Director Itay Schiff said the company is adding the model to Figma Weave.

The scale of AI imagery

OpenAI says people now create 4 billion images per week across ChatGPT, Codex and the API, which it describes as more than half a billion images per day. These are the company’s own figures and have not been independently verified.

Availability and pricing

Images 2.6 is available globally today in ChatGPT and Codex across all subscription tiers, on desktop, mobile and web. GPT-Image-2.6 Sunburst and Flare are available in the API, and OpenAI points to its pricing page for details. The company also published a system card covering its safety evaluations and safeguards for the release.

What it means for everyday users

For most people, the change will feel like speed and polish. Quick drafts arrive sooner, and edits are less likely to alter parts of an image you wanted to keep. For small businesses and creators, animated GIFs and SVG export may reduce the number of tools needed for simple marketing visuals. As always with AI-generated content, it is worth reviewing the results carefully before publishing, checking details, text and brand elements, and following each platform’s rules for labeling AI imagery.

What to watch next

  • How developers use the new complexity and markup controls in real products.
  • Whether competitors respond with similar animation features.
  • Independent testing of the speed and consistency claims.

The bottom line

Images 2.6 is an incremental but practical step: faster outputs, tighter edits and a new way to bring still images to life with GIFs.

Image: Mix of paints (Unsplash) by Mike Petrucci mikepetrucci via Wikimedia Commons, CC0 1.0