Midjourney offers a /describe command on its platform that allows you to convert an image to text. Essentially, the /describe command can be used to generate text-rich prompts based on an existing image. The feature uses AI to reverse-engineer an image you upload, and when Midjourney processes the image, you’ll see a set of descriptions based on the image you shared.

The Describe tool uses inspirational and evocative words to create prompts based on the content it can view and extract from the uploaded image, including the aspect ratio of the original image. You can use all or some of the suggested prompts that are generated to create new AI images with the aspect ratio intact.

Midjourney says that while the tool attempts to extract as much information from an image as possible, subsequent prompts may not be able to recreate an uploaded image in exactly the same way. There may be minimal or drastic changes to the generated images if the AI was unable to add details about certain elements in the suggested prompts. You can further edit any of the suggested prompts to make the AI-generated images look similar to your original image.

The Describe tool on Midjourney has been available since the release of version 5.0, so it is accessible when you open Midjourney on Discord, even on newer Midjourney models. To use the Describe tool, open one of Midjourney’s servers or the Midjourney Bot on your server or Discord DM. Once it’s open, click on the text box at the bottom.