'This is next-level': ChatGPT’s new image generator stuns desi internet with its accuracy

OpenAI introduced native image generation in GPT-4o, allowing users to create and edit visuals. Indian users shared reactions online.

OpenAI has unveiled native image generation capabilities in GPT-4o, making it easier for users to create images directly within the AI model. Announced on Tuesday, this new feature allows GPT-4o to generate various types of visuals, including infographics, comic strips, signboards, graphics, menus, memes, and street signs.

Indian users were amazed as OpenAI introduced native image generation in GPT-4o, allowing it to create and edit images. (X/@sama)

The update also enables users to refine and edit generated images through follow-up prompts, offering greater flexibility and customisation. OpenAI has rolled out this functionality for users on Plus, Pro, Team, and Free plans, with Enterprise and Edu plans set to receive access soon. Additionally, API integration is expected in the coming weeks.

GPT-4o no longer reliant on DALL-E

Unlike previous iterations, GPT-4o can generate images using its own inherent knowledge rather than relying on external diffusion models like OpenAI’s own DALL-E. However, users will still have access to DALL-E for image generation if needed.

"Creating and customising images is as simple as chatting using GPT‑4o – just describe what you need, including any specifics like aspect ratio, exact colours using hex codes, or a transparent background,” OpenAI stated in its announcement.

Internet reacts to GPT-4o’s abilities

Users quickly put GPT-4o’s new capabilities to the test, sharing their reactions on social media. Shopify CEO Tobias Lütke took to X to express his amazement after the model successfully described the anatomy of an unknown animal on his son’s t-shirt. “How is this even real?” he remarked.

Indian users also joined the conversation, experimenting with the model’s ability to generate images, transform existing photos into different styles, and create user interfaces based on text prompts alone.

Take a look here at the posts:

OpenAI vs Google in AI image generation

OpenAI’s announcement comes shortly after Google introduced native image generation in its Gemini 2.0 Flash AI model. Initially made available to select testers in December, the feature is now accessible in all regions supported by Google AI Studio.

“Developers can now test this new capability using an experimental version of Gemini 2.0 Flash (gemini-2.0-flash-exp) in Google AI Studio and via the Gemini API,” Google said in a statement.