Lagos, Nigeria – OpenAI don roll out new image generation feature wey dey integrated directly into its popular chatbot, GPT-4o. Dis feature go allow users to create images from text prompts as e dey chat, making am more accessible without any need for separate tools like Dall-E. Dis update don come as part of OpenAI’s continuous efforts to improve the user experience with AI capabilities.
The new image generator dey allow users to describe images with specific details like colors, aspect ratio, and even apply changes during the conversation. OpenAI don say this new model dey provide more accurate and detailed images, wey fit impress users. ‘Na so we fit create visuals wey align well with wetin our users want,’ as OpenAI don explain for their announcement.
Dis latest update fit users across different levels — Plus, Pro, Team, and Free plans — with Enterprise and Edu users go dey access am soon. The ability to create images directly from ChatGPT means users no go need to switch between different applications to produce AI-generated visuals.
OpenAI don emphasize say this new feature dey designed to provide high-quality images and allow users to make edits fast. ‘This na significant step forward for creative expression, making it easier for businesses and individuals to communicate visually,’ as Allie K. Miller, independent AI consultant, don talk on X.
As users embark on the new image generation journey, it’s important to note say the capability fit come with some challenges. OpenAI don acknowledge the limitations wey still dey exist, like issues with text rendering and image cropping. Dem dey work to fix these problems as users go begin provide feedback.
Furthermore, OpenAI dey put measures in place to address concerns about copyright, especially since some of the artworks fit be from copyrighted sources. Di company don create C2PA metadata for AI-generated images, wey go help users identify the origin of di images. ‘Dis na part of our commitment to responsible AI development,’ OpenAI talk.
In addition to generating standalone images, GPT-4o fit also generate visuals based on uploaded images, helping users maintain a consistent style across different iterations. For instance, users fit create a game character and refine di design seamlessly through conversation, which dey show how dis technology fit enhance creativity and productivity.
OpenAI’s move to combine text and image generation under one platform don reflect a bigger trend in AI, where multi-modal abilities dey become the norm. Dis new capability, as per experts, na game changer for marketing and creative industries.
Users fit expect more updates in di coming weeks as OpenAI dey continuously work to refine the image generation experience. ‘We de committed to evolving this technology based on real-world usage and feedback from our community,’ OpenAI don assure, making am clear say dem get plans to enhance di performance regularly.
As more applications for AI image generation dey emerge, OpenAI don position itself at the forefront of this technological advancement, promising to keep pushing boundaries and delivering value to users.
