How to Create Amazing AI Images Using DALL-E 3 in U-M GPT

Thanks to the latest upgrades to U-M’s AI services platform, all U-M students, faculty, and staff have been provided with no-cost access to OpenAI’s DALL-E 3, a fantastic text-to-image generating tool. DALL-E 3 is now integrated into U-M GPT – users can go to, select the tool they want to use from the dropdown and start creating.  

DALL-E 3 uses generative AI to help you craft high-quality images by simply entering a detailed text description or “prompt” into the tool. You can type a prompt like “A robot walking a dog in the style of Vincent Van Gogh” or “Design a photorealistic image of a rainbow over a large city,” and it will create a custom image for you. (Below, you can see the images that those actual prompts created when entered into U-M GPT’s DALL-E 3.)

If the image is not exactly what you were looking for, you can tweak the language of your prompt to adjust the image. Users can create very simple or extremely complex prompts for DALL-E 3. Part of the fun is experimenting with different wording to see how it changes the final image.

If you are interested in exploring image creation with U-M GPT’s DALL-E 3, we have gathered a few resources to help you craft the perfect prompts for your images:

These are just a few examples of resources that can help you create stellar images using DALL-E 3. You can learn even more by just trying the tool out and playing around with your prompts. You can find DALL-E 3 now integrated into U-M GPT, and you can learn more about U-M’s various AI services on the U-M Generative AI homepage.