OpenAI rolls out advanced AI image generation to ChatGPT with GPT-4o

OpenAI is integrating advanced AI image generation capabilities into ChatGPT, leveraging the strengths of GPT-4o. This integration allows for precise rendering of text within images, complex prompt handling with up to 20 objects, and image creation based on uploaded references. The system utilizes GPT-4o’s knowledge base and chat context to transform images or use them as inspiration, enabling users to refine images through conversation while maintaining a consistent style.

All generated images are tagged with C2PA metadata for transparency, identifying them as products of GPT-4o. While OpenAI acknowledges existing limitations, they plan to address these through future model improvements. The image generation feature is available to Plus, Pro, Team, and Free users in ChatGPT, with Enterprise and Edu access coming soon. Additionally, it’s also available to use in Sora, and developers will soon have API access to GPT-4o’s image generation capabilities.