Read the affiliate disclosure page to find out how can you help MSPoweruser effortlessly and without spending any money. Read more
Yesterday, OpenAI announced Dall-E 3, the latest version of text-to-image model that delivers much more accurate output than Dall-E 2. Dall-E 3 understands significantly more nuance and detail allowing users to easily create images they imagine. OpenAI mentioned that DALL-E 3 is now in research preview and will be available to ChatGPT Plus and Enterprise customers in October via the API, and in Labs later this fall.
According to Mikhail Parakhin from Microsoft, Bing Image Creator is already using DALL-E 3 model in the backend for some users. If you are lucky, you will be able to try out Dall-E 3 model already through Bing Image Creator.
This news is not surprising given the fact that OpenAI works closely with Microsoft product teams when developing their models. In fact, Mikhail Parakhin’s name is credited in the official OpenAI DALL-E 3 page.
Bing Image Creator allows you to create an image that doesn’t exist. You can just type in a description of something, any additional context like location or activity, and an art style, and Bing Image Creator will make it for you. Since OpenAI removed explicit sexual and violent content from the dataset used to train the model, you won’t be able to create images that are explicit and violent. Also, DALL·E 3 has mitigations to decline requests that ask for a public figure by name. Finally, DALL·E 3 will decline requests that ask for an image in the style of a living artist.
You can try out Bing Image Creator here.