OpenAI’s new AI image generator is potent and bound to provoke
1 min read
Summary
OpenAI’s new multimodal image generation capabilities, integrated into its GPT-4o AI language model, allow it to follow prompts more accurately and at a better quality than its predecessor DALL-E 3.
Available to ChatGPT Free, Plus, Pro, and Team users, with Enterprise and Education access coming later, the model also responds to chat context for image modification.
While it will undoubtedly provoke debate and controversy over artistic styles and copyright, the new feature enables sophisticated media manipulation capabilities that were once the domain of sci-fi and human creators.
Current users have noted that there is no UI indication of which image generator is active, but the new model is identifiable by phenomenally slow generation that proceeds from top to bottom.
