OpenAI Launches DALL-E 3 With ChatGPT Integration and Artist Opt-Outs
OpenAI introduces DALL-E 3, an upgraded image generator that uses ChatGPT to simplify prompting and produces higher-quality visuals. The new model also allows artists to opt out of training data and blocks requests mimicking living creators.
OpenAI unveils DALL-E 3, an upgraded text-to-image tool that integrates directly with ChatGPT to simplify the prompting process. Instead of struggling to write complex instructions, users simply type a basic request and the chatbot expands it into a highly descriptive prompt. This new feature is available to ChatGPT Plus, ChatGPT Enterprise, and Bing Chat users, allowing them to generate and refine images seamlessly within their conversations.
The latest model delivers significant improvements in image quality and accuracy, particularly when handling longer, more detailed prompts. DALL-E 3 also overcomes common historical limitations of AI image generators by rendering difficult elements like text and human hands much more effectively. These enhancements position OpenAI to better compete with rivals like Midjourney and Stability AI in the rapidly evolving generative AI market.
In response to ongoing copyright controversies, OpenAI introduces new safety and privacy mechanisms with this release. DALL-E 3 actively refuses prompts that ask for images in the style of living artists or that depict public figures. Furthermore, creators now have the ability to opt out of having their artwork used to train future OpenAI models, a direct response to pending lawsuits regarding the use of copyrighted material in AI training.