OpenAI just announced that ChatGPT Plus and Enterprise will soon get the ability to create images through its image generator DALL-E 3.
OpenAI touts the safety precautions and copyright precautions: “DALL·E 3 has mitigations to decline requests that ask for a public figure by name. We improved safety performance in risk areas like generation of public figures and harmful biases related to visual over/under-representation, in partnership with red teamers—domain experts who stress-test the model—to help inform our risk assessment and mitigation efforts in areas like propaganda and misinformation.”
“DALL·E 3 is designed to decline requests that ask for an image in the style of a living artist. Creators can now also opt their images out from training of our future image generation models.”
Greater control over the image
Also, OpenAI says that DALL-E 3 increases the level of text control over the image: “Modern text-to-image systems have a tendency to ignore words or descriptions, forcing users to learn prompt engineering. DALL·E 3 represents a leap forward in our ability to generate images that exactly adhere to the text you provide.”