ChatGPT现在可以用OpenAI的图像2.6模型将文本提示和照片转换成动画GIF
ChatGPT现在可以创建动画GIF. 该更新基于OpenAI的新Images 2.6模式，并正在网络，桌面，和移动应用，The Verge Reports上向所有ChatGPT和Codex用户推出。 用户可以从文本提示或上传的照片生成GIF，然后调整动画速度或编辑单个帧。
作为一个例子，OpenAI展示了"你能让猫跳舞的一丝不苟"的提示，产生了几个角色的微小变体，这些变体会将翻页书风格串成GIF. 模型的图像一致性看起来足够强大，可以保持字符识别跨帧，而早期的模型可能已经将其外观从一个帧到另一个帧都改变得太多，使得诡计无法奏效。
GIFs之外，Images 2.6也是为了全面加速图像生成。 对于开发者来说，OpenAI还发布了API模型GPT-Image-2.6"Flare"，用于高效和"Sunburst"，用于高品质的图像生成。 两个模型变体都是第一个带有图像2.5的推出。 OpeneAI 称用户现在每周通过ChatGPT和API生成超过40亿的图像，比9月份多10亿。
AI News Without the Hype – 由人类治愈
订阅THE DECODER免费阅读，每周AI通讯，我们独家的"AI雷达"前沿报告每年6次，全面存档访问，访问我们的评论部分。
现在订阅
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
ChatGPT can now turn text prompts and photos into animated GIFs with OpenAI's Images 2.6 model
ChatGPT can now create animated GIFs. The update is based on OpenAI's new Images 2.6 model and is rolling out to all ChatGPT and Codex users on web, desktop, and mobile apps, The Verge reports. Users can generate a GIF from a text prompt or uploaded photo, then adjust animation speed or edit individual frames.
As an example, OpenAI showed how the prompt "Can you make a gif of a cat dancing?" produces several slight variations of a character that are strung together flipbook-style into a GIF. The model's image consistency appears strong enough to keep the character recognizable across frames, while earlier models would likely have altered its look too much from one frame to the next for the trick to work.
Beyond GIFs, Images 2.6 is also meant to speed up image generation overall. For developers, OpenAI is also releasing the API models GPT-Image-2.6 "Flare" for efficient and "Sunburst" for higher-quality image generation. Both model variants were first introduced with Image 2.5. OpeneAI says users now generate well over four billion images per week via ChatGPT and the API, one billion more than in September.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now
Auto-fetched and translated by AI Atlas. All rights belong to the original author.