OpenAI upgrades ChatGPT's image generation, Sam Altman says ...
OpenAI has upgraded ChatGPT’s image-generation capabilities, allowing users to create more precise visuals, accurately render text, and follow complex prompts. OpenAI CEO Sam Altman announced the development on X, calling it an “incredible technology” and a step forward in creative freedom.
OpenAI on Tuesday rolled out an upgraded image-generation feature in ChatGPT, enabling users to generate images with greater precision, including the ability to render text accurately and follow complex prompts. Unlike previous iterations, the tool can maintain consistency across multiple image generations, making it particularly useful for applications such as game design and storytelling.
Enhanced Image-Generation Feature
OpenAI CEO Sam Altman announced the development, emphasizing its potential for unlocking creative freedom. He stated that the tool is designed to prevent the creation of offensive content unless intentionally desired by the user. Altman expressed excitement about the tool's potential for creativity and innovation.
In a blog post, OpenAI highlighted the model’s ability to analyze and incorporate user-uploaded images into new creations. The model can handle complex scenes with 10-20 objects, surpassing the 5-8 object limit of rival systems, and it integrates user-uploaded images to inspire or refine outputs.
Customization and Safety Measures
Trained on a vast dataset of online images and text, GPT-4o offers "surprising visual fluency," capable of maintaining consistency across iterative designs, like a video game character, through natural conversation. It also supports customization, allowing users to specify details such as hex-code colors, aspect ratios, or transparent backgrounds. However, its detailed rendering means images may take up to a minute to generate.
The upgraded image-generation feature has started rolling out for Plus, Pro, Team, and Free-tier ChatGPT users, with Enterprise and educational access expected soon. Developers will also gain access to the API in the coming weeks, expanding the tool’s reach across different applications.
Rollout and Accessibility
OpenAI outlined its approach to safety, ensuring that all AI-generated images would be embedded with metadata to identify them as coming from GPT‑4o. The company has implemented safeguards to prevent the creation of harmful or misleading content, including restrictions on deepfake imagery and graphic violence.
OpenAI's advancements in image generation technology mark a significant step forward in AI capabilities, providing users with powerful tools for creative expression and innovation.
