ChatGPT 上线 GIF 生成功能，随 OpenAI 图像模型 Images 2.6 推出
ChatGPT will now make you animated GIFs
- 1ChatGPT 随新图像模型 Images 2.6 上线 GIF 生成，可用提示词或上传照片一步完成
- 2用户可调整 GIF 动画速度、逐帧编辑并分享，此前 ChatGPT 无法一步原生生成 GIF
- 3OpenAI 称用户每周经 ChatGPT 和 API 生成超 40 亿张图像，高于 9 月报告的 30 亿
- 4Images 2.6 已向所有 ChatGPT 和 Codex 用户推送，API 另上线 Flare 与 Sunburst
OpenAI 把动图生成并入 ChatGPT 一步流程，图像生成正被做成高频的日常对话能力。
- 影响：做社交与营销素材的团队可少接一道专门的拼接工具；每周 40 亿张的生成量说明图像已是 ChatGPT 的高负载场景；API 新模型为自建图文流程提供了更快档位。
- 参考：可考虑让内容团队拿真实素材试 GIF 生成并对比现有工具的耗时；已在业务中用图像 API 的，值得评估 Flare 与 Sunburst 的速度和质量是否值得迁移。
- 依据：GIF 能力、更快的生成速度和周产量 40 亿张等数字均来自 OpenAI 官方口径，暂无独立验证；演示效果出自公司分享的示例。
Emma Roth
is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO.
ChatGPT can now create GIFs using a prompt or a photo uploaded to the AI chatbot. The update, which is rolling out alongside OpenAI’s new Images 2.6 model, allows you to adjust the GIF’s animation speed, edit individual frames, and share it with others.
Before this change, ChatGPT couldn’t natively generate GIFs in a single step. An example shared by the company shows how ChatGPT can generate a GIF in response to the prompt, “can you make a gif of a cat dancing?,” while also providing you with the option to change the playback speed and view it frame-by-frame.
Along with support for GIF-making, OpenAI says the Images 2.6 update also enables faster image generation in ChatGPT. The company says users now generate over 4 billion images per week across ChatGPT and its API, a jump from the 3 billion per week it reported in September.
Images 2.6 is rolling out to all ChatGPT and Codex users across web, desktop, and mobile apps. OpenAI is also launching GPT-Image-2.6 Flare and Sunburst in its API for faster and higher-quality image generation.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
- Emma Roth
来源：The Verge · AI · theverge.com