OpenAI has enhanced ChatGPT with a new image generation feature powered by its multimodal model, GPT-4o. Initially available to ChatGPT Plus, Pro, Team, and free users, this functionality allows users to generate and modify images using natural language prompts. CEO Sam Altman emphasized the significance of the launch, especially in light of competition from Google Gemini. The model is designed for versatility, catering to creative tasks such as video game character design and producing work-related visuals, all while maintaining contextual awareness.
OpenAI is launching image generation directly within ChatGPT, allowing users to create or edit visuals using natural language prompts.
The feature, which leverages the multimodal capabilities of GPT-4o, provides enhanced user experience through better context understanding and visual consistency.
Collection
[
|
...
]