OpenAI Introduces Image Generation via GPT-4o in ChatGPT

OpenAI CEO Sam Altman announced a major update to ChatGPT, which now allows the system to create and edit images using the GPT-4o model. Previously, this feature was only available for text, and a separate DALL-E 3 model was responsible for generating images.

However, the updated feature works much better and is more accurate. OpenAI representative Taya Christianson clarified that the limits for free users will remain the same as DALL-E, i.e. three images per day. DALL-E can still be accessed through the ChatGPT user interface.

The system also now uses a non-standard generation method. Images are created sequentially, from left to right and top to bottom, rather than as a whole, as is the case in DALL-E. According to Goh, this explains 4o Image Generation’s superiority in handling text and complex scenes.

The system also now uses a non-standard generation method. Images are created sequentially, from left to right and top to bottom, rather than as a whole, as is the case in DALL-E. According to Goh, this explains 4o Image Generation’s superiority in handling text and complex scenes.

This update marks an important step towards multimodal AI capabilities, where a single model can work on text, images, and other types of data simultaneously.