IBL News | New York
OpenAI released an advanced image generator for GPT‑4o this week.
The San Francisco-based research lab announced that this improvement in image generation is now native to GPT-4o, allowing users to refine images through natural conversation.
“GPT‑4o can build upon images and text in chat context, ensuring consistency throughout. For example, if you’re designing a video game character, the character’s appearance remains coherent across multiple iterations as you refine and experiment,” explained the company.
This initial release is available across ChatGPT Plus, Pro, Team, and Free subscription tiers. The free tier’s usage limit is the same as three images per day with DALL-E.
This model is considered a step change from previous models as it uses GPT-4o unimodal, a foundation that can generate data, including text, images, audio, and video.
