OpenAI总裁格雷格·布罗克曼早在2024年5月就预告过GPT-4o的原生图像能力，但出于未公开的原因，该公司直到现在才发布该功能。此前，谷歌AI Studio的Gemini 2 Flash实验模型已经推出了类似功能。

OpenAI近期揭晓了一项重大更新——GPT-4o模型新增了原生图像生成功能，这一革新使得用户能够在ChatGPT及Sora平台上，仅凭自然语言指令，轻松实现图像的创建与编辑。更令人兴奋的是，该功能支持多轮迭代优化，为用户提供了前所未有的创作灵活性。

Because the image generator is accessible in ChatGPT, users can also refine images through a multi-turn conversation. This ...

OpenAI is integrating new image generation capabilities directly into ChatGPT starting today — this feature is dubbed “Images ...

OpenAI has integrated AI image generation directly into ChatGPT, powered by the GPT-4o model, allowing free and paid users to ...

OpenAI has launched the first major upgrade to ChatGPT's image generation capabilities in over a year, driven by the ...

OpenAI launched GPT-4o image generation this week, bringing more advanced image generation capabilities to ChatGPT and Sora.

OpenAI certainly covered quite a bit of ground in just about 15~ minutes. Sam Altman and the team debuted native image ...

The tech world is buzzing with exciting developments and innovations every day, let's find out what's new has been introduced ...

OpenAI CEO Sam Altman announces GPT-4o, a major upgrade for ChatGPT that enables high-precision image generation with enhanced accuracy and context. Now available across all subscription tiers ...

During a live-streamed event on Tuesday, the San Francisco-based company showed how ChatGPT users would be able to refine ...

As AI-generated images become more precise and accessible, GPT-4o represents a significant step forward in the space.