AI News

OpenAI Introduces Native Image Generation in GPT-4o

OpenAI Introduces Native Image Generation in GPT-4o

U.S.-based artificial intelligence research organization, OpenAI, has once again grabbed headlines by introducing a native image generation tool in GPT-4o. According to the announcement, the firm is calling it a “most advanced image generator” in GPT‑4o. 

“GPT‑4o image generation excels at accurately rendering text, precisely following prompts, and leveraging 4o’s inherent knowledge base and chat context, including transforming uploaded images or using them as visual inspiration. These capabilities make it easier to create exactly the image you envision, helping you communicate more effectively through visuals and advancing image generation into a practical tool with precision and power,” the OpenAI team stated in the blog post. 

Community Praises OpenAI’s New Image Generation Feature

The new model allows users to create diverse visuals through natural language prompts, including infographics, comic strips, memes, user interfaces, street signs, and ad copies. 

Unlike previous versions, GPT-4o no longer relies on external diffusion models like OpenAI’s DALL-E. Instead, it generates images directly using its native knowledge, which enhances speed and customization. Also, users can optimize these images with follow-up prompts. By doing this, they can adjust important parameters. For instance, they can adjust aspect ratios, hex color codes, and background transparency.

The good news is that OpenAI has rolled out this feature to users across Plus, Pro, Team, and Free plans. They are also planning to release access for Enterprise and Edu plans. API access is expected within weeks, which will open doors for developers to integrate this capability into their applications.

Early adopters have been quick to showcase GPT-4o’s prowess. Tobias Lütke, CEO of Shopify, posted on X how the model identified and described an unknown animal printed on his son’s t-shirt, leaving him stunned. Similarly, Grant Slatton, A founding engineer at Row Zero, highlighted how GPT-4o transformed a regular photo into a stunning ‘Studio Ghibli’, which is a style of anime image. Such incredible capabilities of OpenAI’s new image generation tool have amused the online community. 

Source: https://openai.com/index/introducing-4o-image-generation/

Latest Stories:

DeepSeek’s New V3 Update Outperforms OpenAI and Anthropic

Google AI Mode Expands to More Users After Initial Glitch

Rajpalsinh Parmar
Rajpalsinh has been decoding the AI universe for three years, turning tech jargon into tales of wonder and possibility. With a knack for making the abstract tangible, he brings AI's potential to life for everyone.

Leave a reply

Your email address will not be published. Required fields are marked *

More in:AI News