Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

90年代申花出租车司机夜晚在车内看文汇报90年代申花出租车司机夜晚在车内看文汇报
0

The AI landscape is rapidly evolving, and the latest contender making waves is GPT-4o, particularly its image editing capabilities. Social media platforms like X and Xiaohongshu are flooded with examples of its stunning creations, leaving users and even industry leaders like the Midjourney CEO impressed.

For years, AI image generation tools have promised to empower users, even those without Photoshop skills. But GPT-4o appears to be delivering on that promise in a way that’s truly capturing the internet’s attention. The last time an AI product generated this much excitement was likely DeepSeek R1.

Here are a few examples showcasing GPT-4o’s capabilities:

  • Scientific Illustrations: GPT-4o can generate detailed and accurate illustrations for academic papers.
  • Satirical Art: It can create humorous and topical images, such as a Miyazaki-style depiction of Trump and Zelensky in frank and honest dialogue.
  • Affordable Commissions: Need a quick illustration? GPT-4o can produce images like a 5-dollar Japanese character on demand.
  • Professional-Looking Posters: GPT-4o can generate well-designed and visually appealing posters for various purposes.
  • 3D Depth Maps: It can create 3D depth maps, demonstrating a strong understanding of spatial relationships and affordance. As one user on Xiaohongshu noted, Although the image still has some flaws, the improvement in spatial ability and affordance prediction is too great.
  • Style Transfers: Users can easily transform portraits into various artistic styles, such as Disney, Ghibli, Snoopy, or Stardew Valley.

What’s particularly impressive is that GPT-4o often achieves these results on the first try, minimizing the need for iterative modifications.

Furthermore, GPT-4o’s capabilities extend beyond still images. Its AI video generation capabilities have been used to create a Miyazaki-style version of Interstellar.

Conclusion

GPT-4o’s image editing capabilities are a significant leap forward in AI-powered creativity. Its ability to generate diverse and high-quality images with minimal user input has captured the imagination of the internet and even impressed industry leaders. As AI technology continues to advance, tools like GPT-4o are poised to transform the way we create and interact with visual content.

References

  • 机器之心. (2024, March 27). GPT-4o的P图全家桶有多强?连Midjourney CEO都坐不住了. Retrieved from [Original article URL]


>>> Read more <<<

Views: 0

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注