OpenAI has released the image generation feature of GPT – 4o and made it freely available to users.

OpenAI has announced the integration of advanced image generation capabilities into the GPT-4o model, enabling users to generate and edit images through natural language instructions. The new feature supports multi-turn conversations to optimize images while maintaining content consistency. It can handle complex instructions involving 10 to 20 objects, far surpassing other models. Additionally, it supports text rendering, style transfer, and context-aware image generation.