OpenAI unveils DALL-E 3, allows artists to opt out of training

OpenAI has introduced an upgraded version of its text-to-image tool called DALL-E 3. This tool utilizes ChatGPT, OpenAI’s popular AI chatbot, to assist users in generating prompts for image creation. Prompt engineering, the process of crafting the right prompt, has become a specialized profession due to its complexity. With DALL-E 3, subscribers to OpenAI’s premium ChatGPT plans can input a request for an image and refine it through conversations with the chatbot. The integration of ChatGPT allows for more descriptive prompts, even with just a few words. DALL-E 3 also produces higher-quality images that accurately reflect the prompts, particularly with longer prompts. It addresses challenges faced by image-generating models, such as text and human hands. OpenAI has implemented mechanisms to reduce algorithmic bias and improve safety, including rejecting requests for images in the style of living artists or public figures. Additionally, artists now have the option to opt out of having their artwork used to train future generations of OpenAI’s text-to-image models. The launch of DALL-E 3 coincides with the competitive race in generative AI, specifically in image synthesis. OpenAI plans to release DALL-E 3 to premium ChatGPT users in October, followed by research labs and API customers. There is no mention of a free web tool release at this time.

Full article

Leave a Reply