OpenAI 发布了 Images 2.6 模型，这次更新最实用的改动是把原生的 GIF 动图生成和编辑直接整合进了 ChatGPT 和 Codex。
This is a AI post classified by AGK Intelligence as AI image (a launch), kept by the AI Radar because it carries real work, not commentary.
OpenAI 发布了 Images 2.6 模型，这次更新最实用的改动是把原生的 GIF 动图生成和编辑直接整合进了 ChatGPT 和 Codex。 以前想在对话框里做张动图，往往得靠代码解释器写脚本把多张图拼起来，过程比较折腾。现在直接输入文字提示词或者传一张参考图，就能直接生成循环动图。生成之后不仅能直接调节播放速度，还支持逐帧查看和单帧局部修改。如果哪一帧画面崩了，直接单独修那一帧就行，不用整张图重新抽卡，这也说明模型在连续帧的角色和画面一致性上稳定了不少。 除了动图能力，常规静态图的生成速度也比上代更快。在开发者 API 这边，OpenAI 同步更新了两个分支型号，其中 GPT Image 2.6 Flare 主打低延迟和高吞吐，适合对响应速度敏感的场景，而 GPT Image 2.6 Sunburst 则偏向更高精度的画质表现。 顺便提一句，官方透露现在每周通过 ChatGPT 和 API 生成的图片数量已经超过 40 亿张，距离 9 月份的 30 亿张又涨了一大截。目前新模型和动图功能已经开始向网页端、桌面端和移动端的全量用户推送，日常做点表情包或者演示素材会顺手很多。 https://x.com/ChatGPT/status/2118126207602704513?a=U5xqpZAJspVjzReZEmQ&s=20
Posted by KC (8.8k followers) 1 days ago · 25 likes · 3.6k views · view the original post on X. Kept by the AI Radar as AI image.
More AI work like this
- The machine with the most memory made my AI picture slowest. 7.3 s on a DGX Spark, 1.7 s… — @niklaslenz_ai
- @OpenAI's GPT Images 2.6 just dropped, and it's the most fun model for a specific reason. — @ImagineArt_X
- I wasn't able to train a pixel art model from scratch (at least not without spending… — @Angaisb_
- From ad creatives to lookbooks and storyboards, bring your ideas to life with GPT Image… — @PixVerse
- the new gpt gif creator is dope af, so many ppl gonna catch this one — @thekitze
- Turn any image into a 3D relief you can print. — @MeshyAI
- Grok interpretation of minimalist clothes 😂 — @carolletta
- Turn any image into a 3D relief you can print. — @MeshyAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.