2) Once you have a generation that you like, upscale it.
Reminder: You want a three panel image. Preferably with a large panel and two small panels.
3) With your upscaled image, click on the vary region button. Using the square selection tool, select only one panel. Make sure your selection slightly extends past the edges of the panel.
Important: Only select one, or at most, two panels. Do not select the entire image.
4) Edit only the subject of the prompt and change the stylization to low.
For example, if your subject is a brunette woman, you can change the subject to brunette woman at dinner. Do not change any of the remainder of the prompt.
Important: Add --s 50 to the end.
5) This is where the magic happens. It appears that by selecting one panel for inpainting, Midjourney will reference the subject in the other panels.
If you are having issues, try selecting a different panel and re-running the inpainting prompt. Also make sure to use --s 50.
6) To go a step further, upscale one of the inpainted versions and click the vary region button again. This time select every panel besides the one that you like.
This is less stable, but with some re-rolls you can create multiple images of your subject at the location.
7) If you would like to extend the height and width of your panels, I recommend using adobe's Gen Fill for this task.
This last step is optional.
Thank you for reading along! If you enjoyed these posts,
1) Follow me @Mr_AllenT for more AI content and tutorials.
2) Bookmark, like, and repost to share with your friends!
Layering elements in your images is important for creating depth and spatial relationships within a scene.
It makes your images feel complex.
Let's dive in 👇
The key to layering elements is using the tokens foreground, middle ground, and background.
The nearest part of a photo is the foreground, the most distant is the background, and the area between is the middle ground; however, not every image requires all 3.
Let’s continue
Let's start with a foreground and background
This is the most common layering created with Midjourney. It consists of a close up of a subject and a background.
Prompt: Intense video game website landing page, space exploration game, rich and saturated color pallet with blues, oranges, greens, color pallet, geometry, wide angle --ar 4:3
#2 Fashion E-Commerce Website
Prompt: Minimalist fashion website landing page, high quality fashion, soft pastel color pallet, geometry, wide angle --ar 4:3
The aspect ratio is one of the most powerful parameters when crafting a Midjourney prompt.
It plays a critical role in the composition, shape, and aesthetic of the image
Let's look at some examples and discuss🧵👇 (1/10)
--ar 1:1
The default aspect ratio (ar) in Midjourney is 1:1 or "--ar 1:1".
An ar of 1:1 is the classic square image. It is ideal for social media profile pics, icons, and logos.
(2/10)
--ar 16:9
This is the standard "wide-screen' ratio.
iPhone pictures and videos use an aspect ratio of 16:9.
It is typically used for presentations, animations, and videos. It is also Youtube's most common aspect ratio.
(3/10)
Isometric illustrations are a fun way to generate 3D objects. They are created with equal proportions and unique angles to maintain the size and add depth to digital designs.