Midjourney finally rolls out “inpainting”


Midjourney is currently testing a long-awaited feature: You can now edit individual regions of an image via a prompt, a feature typically known as “inpainting”.

Midjourney calls its variant of “inpainting”, i.e., painting over parts of an image, “Vary Region”. This option appears on upscaled images and is next to the existing Remix functions “Vary Strong” and “Vary Subtle”. You need to make sure that Remix Mode is enabled in the settings (prompt “/settings”). Otherwise, the button will not show up.

If you press “Vary Region”, a new interface will appear. Here, you can select an area in the upscaled image and edit it with text prompts. For example, you could use a prompt to make a portrait photo with a sad expression smile.

Sad red-bearded guy. | Image: Midjourney prompted by THE DECODER
The inpainting interface appears when you click Vary (Region). In the example, I replaced “sad” with “happy” in the prompt. | Image: THE DECODER
The result is a happy red-bearded guy. | Image: Midjourney prompted by THE DECODER

Of course, you can go on by upscaling the newly created image and further customizing the prompt. For example, you can add a hat to the portrait image.



Now you know the reason for the sudden change of heart: the red-bearded man has learned that he is allowed to wear this beautiful hat. A reason for joy. | Image: Midjourney prompted by THE DECODER

Inpainting isn’t a silver bullet for image editing

According to Midjourney, inpainting works best with relatively large areas of the image, 20 to 50 percent of the image, and when the prompt is only slightly adjusted. Replacing a small detail in the background is likely to be more difficult.

Also, inpainting works more reliably when the prompt change blends well with and complements the original image, as in the example above. The more basic and outlandish the image change, the more difficult it is for the system to implement.

A hat is easy to put on the red-bearded guy via inpainting, a cat on his head is more difficult. | Image: Midjourney prompted by THE DECODER

According to Midjourney, inpainting is not a “magic fix” and often the “vary subtle” feature would work better. This feature generates new images based on the original image and a customized prompt, rather than just changing an area. In the cat example, however, this didn’t help.

The same cat prompt executed with Vary Subtle instead of inpainting. The result is hardly better. | Image: Midjourney prompted by THE DECODER

For major changes in the image, such as the cat on the red-bearded man’s head, re-creation may be the way to go. In this case, Midjourney will create a new composition from scratch that better fits the prompt. Of course, you will lose the look of the original creation.

New cat image that does not have serious image flaws like the previous variations with inpainting. | Image: Midjourney prompted by THE DECODER

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top