Is Copilot the best AI companion out there? Help us find out by answering a couple of quick questions!
Early this month, OpenAI announced Dall-E 3, its 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. 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. However, you can access Dall-E 3 today for free through Microsoft Bing.
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. Bing Image Creator is now powered by Dall-E 3 in the backend, and it is available for everyone. You can access Dall-E 3 powered Bing Image Creator here. The DALL-E 3 model can create stunning images with improved quality and realism, especially for fine details.
Also, you have to remember that Bing Image Creator will have the same restrictions as Dall-E 3. Since OpenAI removed explicit sexual and violent content from the dataset used to train the Dall-E 3 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.
All AI-generated images created by Bing Image Creator now include an invisible, digital watermark that follows the C2PA specification. This watermark will have the time and date it was originally created and confirms the provenance of the image to be AI-generated.