







ChatGPT Image 2.0全新发布,能力大大提高,特别是解决了以前图片生成文字经常有错误的问题,现在可以在生成的图片里加入非常复杂的文字细节。上面帖的这几张图也是用它生成的。
不用多说了,下面是官方发布视频的英文原稿和中文翻译。
链接:
https://openai.com/index/introducing-chatgpt-images-2-0/
Today, we are launching Images 2.0.
If you think of DALL·E as cave drawings and Images 1 as ancient art, then Images 2.0 is the Renaissance.
Images 2.0 is the smartest image generation model ever built, with the ability to generate complex, polished, and production-ready visuals with accurate text and structured design.
You see, this model isn’t just generating images — it’s thinking.
That’s right. Images 2.0 is thinking and researching, and it can even search the web to generate images with the most accurate information available.
And with that information, the model is able to generate infographics that explain complex systems and images that solve math problems with proofs.
And with new multilingual capabilities, you can create visuals in multiple languages for the entire world.
And now, for the first time in image generation, you can create multiple distinct images at once.
So you can generate entire magazines with structure, typography, and photorealistic photos, full renovation plans for every room in your house, or manga comics with recurring characters and evolving storylines.
And you can now generate images with 2K resolution across multiple aspect ratios with extraordinary micro-details.
You see, we are no longer generating images to marvel at.
With Images 2.0, we are generating images to discover and navigate, to invent and build, to dream and explore the world, and bring ideas to life.
今天,我们正式发布 Images 2.0。
如果说 DALL·E 是洞穴壁画,Images 1 是古代艺术,那么 Images 2.0 就是文艺复兴。
Images 2.0 是迄今为止最强大的图像生成模型,能够生成复杂、精致、可直接用于生产的视觉内容,并具备准确的文字呈现和结构化设计能力。
你看,这个模型不仅仅是在生成图像——它在“思考”。
没错。Images 2.0 会思考、会研究,甚至可以通过联网搜索来获取最准确的信息,从而生成图像。
借助这些信息,模型可以生成用于解释复杂系统的信息图,甚至还能生成带有推导过程的数学解题图像。
同时,凭借全新的多语言能力,你可以为全球用户创建多语言视觉内容。
而现在,图像生成首次实现了同时创建多张彼此不同的图像。
这意味着你可以生成完整的杂志(包含结构、排版和逼真的照片)、为房屋每个房间设计完整的翻新方案,或创作具有连贯角色和持续剧情的漫画作品。
此外,你现在还可以以 2K 分辨率、支持多种宽高比,生成具有极致微观细节的图像。
你会发现,我们已经不再只是生成让人惊叹的图像。
借助 Images 2.0,我们是在用图像去探索与导航、去发明与构建、去梦想与发现世界,并将想法变为现实。
如果觉得文章有帮助,欢迎分享转发,也欢迎关注我的公众号“搬砖的小明”,及时获取更新