Skip to content
Main Site News Console

Introducing Images 2.6

· OpenAI Translated
OpenAILLM

OpenAI Introduces Images 2.6

November 4, 2026

Faster generation, greater control across multi-turn edits.

We are officially launching Images 2.6 across ChatGPT, Codex, and the API, turning your ideas into reality faster than ever. With this release, you can bring images to life through GIFs—whether by animating brand mascots and characters or transforming static product shots into eye-catching looping animations. You can also generate polished visual assets more efficiently and fine-tune details with exceptional precision—consistently preserving character, product, and brand details across multi-turn edits.

Users worldwide now generate 4 billion images every week across ChatGPT, Codex, and the API. On average, that’s more than 500 million images generated daily.

A compilation of animated scenes generated by Images 2.6.

Video 1

Image 1: Images 2.6 — GIF compilation poster

Faster Iteration and More Professional Visuals

Images 2.6 generates images 50% faster than previous versions. In the API, we offer developers two model variants: GPT‑Image‑2.6 Flare and Sunburst. When quality is set to low, Flare can generate images in as fast as 6 seconds. For scenarios demanding high detail and precision, GPT‑Image‑2.6 Sunburst delivers superior image rendering when quality is set to medium or high, alongside better consistency across multi-turn edits. In addition, Flare significantly improves layout and composition quality for posters, product visuals, and other professional design assets.

A side-by-side latency comparison of image generation using a luxury travel ad, with generation timers shown at 8x speed.

Image 2: Luxury Travel — Comparison update poster

Bringing Ideas to Life with GIFs

When motion is needed, GIFs add an entirely new dimension to creativity. Marketers and creators can activate brand mascots for campaigns, craft engaging memes and reaction GIFs for social media, or explore character blocking and movement with animated storyboards before shooting begins.

A chibi office worker reacting to a plunging stock chart.

Image 3: Images 2.6 — OpenArt stock market drop animation poster

Created by OpenArt

Prompt 1: A single animation sprite sheet designed for a seamlessly looping GIF. A super cute chibi adult office worker sits at a desk, staring at a monitor displaying a clearly plunging stock market line graph. Sequence of action: starts with a hopeful expression, notices the declining chart, eyes widen in shock, face falls into despair, large cartoon tears stream down cheeks, and finishes wiping away tears while continuing to stare grimly at the falling chart. Big round head, small body, expressive large eyes, soft rounded facial features, messy fluffy hair, white dress shirt, and a loosened tie. 6 sequential frames neatly arranged in a precise 3-column by 2-row grid, read from left to right, top to bottom. Each frame is identical in size. Locked-off front three-quarter camera angle, identical character, desk, monitor, outfit, and cozy miniature office background throughout. Clear progression of facial expressions and tear animation; the sixth frame transitions smoothly back into the first. Polished cute chibi 3D toy aesthetic, warm soft lighting, comedic yet sympathetic tone. No text, subtitles, numbers, logos, speech bubbles, frame borders, or margins.

A chibi office worker celebrating a surging stock chart.

Image 4: Images 2.6 — OpenArt stock market surge animation poster

Created by OpenArt

Prompt 2: A single animation sprite sheet designed for a seamlessly looping GIF. A super cute chibi adult office worker sits at a desk, staring at a monitor showing a soaring stock market line graph and a massive upward arrow. Sequence of action: notices the chart rising, eyes widen in delight, leaps up cheering, grabs a handful of generic, non-descript play banknotes, then laughs joyfully while throwing the bills into the air like confetti. Big round head, small body, bright expressive eyes, soft rounded facial features, messy fluffy hair, white dress shirt, and a loosened tie. 6 sequential frames neatly arranged in a precise 3-column by 2-row grid, read from left to right, top to bottom. Each frame is identical in size. Locked-off front three-quarter camera angle, identical character, desk, monitor, outfit, and cozy miniature office background throughout. Clear progression of body motion, arms, and flying banknotes; the sixth frame transitions smoothly back into the first. Polished cute chibi 3D toy aesthetic, bright celebratory soft lighting, comedic and joyful tone. No text, subtitles, numbers, logos, real currency symbols, speech bubbles, frame borders, or margins.

“GIFs are the native language of social media, and GPT‑Image‑2.6 empowers every OpenArt creator to speak it fluently with just a single prompt.”

— Coco Mao, Co-founder and CEO of OpenArt

And complex initial designs aren’t required—even rough hand-drawn sketches can be transformed into expressive, animated characters ready for video, gaming, and beyond.

Image 5: An owl drawn with pen on lined paper.

An owl animation generated from the hand-drawn sketch.

Image 6: Owl animation — poster

From personal reactions to animated brand mascots and product demos, GIFs offer a vibrant, playful medium for both individuals and enterprises. Town, a startup building an AI workplace assistant, integrated Images 2.6 via the API to explore how animated characters can bring more personality and energy to daily workplace collaboration.

Monty, an animated character in Town’s workplace assistant, appears above the message box as a “typing” indicator.

Image 7: Town — Monty typing animation poster