Hello GPT-4o
- steph5837
- Apr 1
- 1 min read
On March 25, 2025, OpenAI hosted a livestream event to announce the launch of GPT-4o, their latest multimodal AI model capable of processing and generating text, images, and audio.
During this event, CEO Sam Altman introduced GPT-4o's native image generation feature, allowing users to create and modify images directly within ChatGPT.
Follow this link and scroll to the replay of the livestream Introducing 4o Image Generation | OpenAI from the launch where Sam and some of his team demonstrate the new release.
What the model can do is awesome! The time taken to produce a multi modal image feels a bit slow – but this will improve!
For a visual overview of GPT-4o's image generation capabilities, you can watch the following video:
تعليقات