Midjourney's Describe feature helped me master new image prompts. I'll show you how I used it to create new versions of a blended image all the way to this result: [img:Bs4Egr6Yo]

1. Midjourney has a '/blend' feature to upload 2 or more images to blend styles to create a new image. I blended 2 images in a challenge thread to generate the image below. I liked this image and other variations but didn't know how to write a prompt to recreate it: [img:3FqVVH0jy]

2. I used the /describe feature to generate 4 possible prompts for that image: [img:38lTOMuc6]

3. I chose 2 prompts from the /blend options. Option number 1: [img:oAS5euUhU]

4. Option number 4: [img:z-3_R6Jup]

5. I generated variations of the 2nd image. Prompt: "A digital art poster for the artof slender robots, in the style of colorful portraiture, metallic gothic futurism, women artists, illusion of three-dimensionality, serene faces, intense close-ups, hyper-realistic pop"

6. The variations are below: [img:tBjRjfiXW]

7. I liked all 4 images in that result, so I upscaled each one. I repeated this process several times with different results and added new keywords or elements to generate new styles, like this: [img:gOS41KDTj]

8. Or like this: [img:ZhMSEZpDO]

Recap I learned new terms and styles, including: • Dollcore • Pop Art Fusion • Gothic Futurism Overall, I found several uses for this feature and it's a great tool to help you learn how to build better prompts for any images. Reply with results of your /describe output 👇

Thank you for reading. If you found this information useful, follow @HBCoop_ for more content on visual information design and AI. Retweet the 1st tweet below to share this thread: twitter.com/HBCoop_/status/1645119427220783107