OpenAI 发布 Images 2.6 模型，支持 GIF 动画生成与更精准的图像编辑
Introducing Images 2.6
OpenAI 推出 Images 2.6 模型，现已在 ChatGPT、Codex 及 API 中上线。该版本生成速度提升 50%，新增 GIF 动画生成功能，并为 API 开发者提供 Flare 和 Sunburst 两种模型选择，支持 SVG 导出、图像标记及复杂度参数调节，以实现更一致的编辑效果。
新模型通过引入 GIF 动画生成能力和更精细的 API 编辑参数，为开发者和创作者提供了更高效的视觉内容生产工具。
Introducing Images 2.6
Generate images faster and with more control over editing rounds.
Listen to article 3:20
Share
W e’re introducing Images 2.6 in ChatGPT, Codex, and the API, bringing your ideas to life faster. With this, you can bring motion to your images with GIFs — from animating a brand mascot or character to turning a product shot into an eye-catching loop. You can also create polished visuals faster and refine them with greater precision — keeping characters, products, and brand details consistent as you edit.
People around the world now create 4 billion images per week across ChatGPT, Codex, and the API. On average, that’s more than half a billion images created per day.
A montage of animated scenes generated with Images 2.6.
Faster iteration and more professional visuals
Images 2.6 generates images 50% faster than before. In the API, we offer GPT‑Image‑2.6 Flare and Sunburst for developers to choose from. When quality is set to low, Flare can generate images in as little as six seconds. For work that calls for greater detail and precision, GPT‑Image‑2.6 Sunburst brings higher-quality image generation and even greater image consistency across edits when quality is set to medium or high. Flare also improves layout quality for posters, product imagery, and other professional visuals.
Side-by-side image-generation latency comparison using a luxury travel advertisement, with generation timers shown at eight-times playback speed.
Animate your ideas with GIFs
For moments that call for motion, GIFs bring another dimension to your ideas. Marketers and creators can 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.
A chibi office worker reacts to a falling stock-market chart.
Created by OpenArt
Prompt 1: Create a single animation sprite sheet for a seamless looping GIF. A super-cute chibi adult office worker sits at a desk watching a computer monitor with a clearly plunging stock-market line chart. The sequence: hopeful expression, notices the chart falling, eyes widen, face crumples, large cartoon tears stream down both cheeks, then quietly wipes tears while still staring at the falling chart. Oversized round head, tiny body, big expressive eyes, soft rounded features, messy fluffy hair, white shirt and loosened tie. Exactly 6 sequential frames arranged in a precise 3-column by 2-row grid, read left-to-right then top-to-bottom. Every panel has identical dimensions. Fixed front three-quarter camera, same character, same desk, monitor, outfit, and cozy miniature office background. Clear incremental facial and tear motion; sixth frame transitions smoothly toward the first. Polished kawaii chibi 3D toy-like style, warm pastel lighting, funny and sympathetic mood. No captions, no words, no numbers, no logos, no speech bubbles, no panel labels, no borders, no gutters.
Show more
A chibi office worker celebrates a rising stock-market chart.
Created by OpenArt
**Prompt 2:**Create a single animation sprite sheet for a seamless looping GIF. A super-cute chibi adult office worker sits at a desk watching a computer monitor with a clearly soaring stock-market line chart and a large upward arrow. The sequence: notices the chart rising, eyes widen with delight, jumps up cheering, grabs a handful of generic paper banknotes with no readable currency markings, then happily tosses the banknotes into the air like confetti while laughing. Oversized round head, tiny body, big sparkling expressive eyes, soft rounded features, messy fluffy hair, white shirt and loosened tie. Exactly 6 sequential frames arranged in a precise 3-column by 2-row grid, read left-to-right then top-to-bottom. Every panel has identical dimensions. Fixed front three-quarter camera, same character, desk, monitor, outfit, and cozy miniature office background. Clear incremental body, arm, and flying-paper motion; sixth frame transitions smoothly toward the first. Polished kawaii chibi 3D toy-like style, bright celebratory pastel lighting, funny joyful mood. No captions, no words, no numbers, no logos, no real currency symbols, no speech bubbles, no panel labels, no borders, no gutters.
Show more
“GIFs are the native language of social media, and GPT‑Image‑2.6 lets every OpenArt creator speak it fluently from a single prompt.”
—Coco Mao, CEO & Co-founder at OpenArt
And you don’t need a polished design to get started — even a simple sketch can become an expressive, animated character for videos, games, and more.
An animated owl created from the hand-drawn sketch.
From personal reactions to brand mascots and product visuals, GIFs give people and businesses a playful way to communicate. Town, a startup building an AI work assistant, used Images 2.6 in the API to explore how animated characters could bring more personality to everyday interactions at work.
Monty, an animated character in the Town work assistant, appears above the message box as a typing indicator.
More ways to create and edit in the API
A presenter at a laptop in the image-editing demonstration.
00:00
With Images 2.6, developers get more control over how images are created, edited, and carried into the next stage of a project. Image markup, already available in ChatGPT, comes to the API so teams can pinpoint exactly where to make specific changes. SVG exports make designs ready to use across websites, apps, and print.
A new complexity parameter lets developers adjust how much planning the model does to meet a request, with lower settings suited to quick edits. Image quality controls visual detail and fidelity, while complexity guides how much goes into the scene.
“GPT‑Image‑2.6 brings speed and creative control together, helping you generate and edit images while preserving the details that define a character, product, or brand. We’re excited to add it to Figma Weave, giving teams another powerful model for creative production, all within a reusable workflow.”
—Itay Schiff, Creative Director at Figma Weave
For most editing tasks, we recommend low complexity for faster edits, paired with the image quality your workflow requires. For scenes with many elements or constraints, try medium or high complexity effort.
See what early access customers generated using Images 2.6:
Picsart fal Sable Higgsfield
“At Picsart, we see how much creators value being able to generate an image fast. OpenAI’s new 2.6 model brings more accurate results, better character consistency, and faster generations. Paired with Picsart’s advanced editing tools, it gives our users more time to experiment, refine details, and turn one idea into a whole social campaign.”
—Davit Avoyan, Director GTM at Picsart
Pricing and availability
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 GPT‑Image‑2.6 Flare are available in the API. Seepricing details here.(opens in a new window)
Learn more about our safety evaluations and safeguards for Images 2.6 in the system card.
Author
OpenAI
来源：Hacker News-首页 · openai.com