Image models

Midjourney adds an Edit Model for V8 that replaces Omni Reference

Midjourney's Edit Model edits images with instructions, uses up to four image references, and supports inpainting and outpainting in V8.2.

On August 27, 2026, Midjourney began letting everyone test its first V8.2 image edit model, a month after V8.2 became the default model on July 24.

What it does

  • Edit images with written instructions.
  • Generate images using other images as references, replacing Omni Reference, with up to four references at once.
  • Change specific areas (inpainting) or expand the canvas (outpainting).
  • Work with personalization, moodboards and style references. Midjourney notes that moodboards and style references may work best with extra prompt direction in this version.

How to use it

Drag images into the prompt bar under “attach to prompt”, click “edit” in the lower right of the lightbox, or use the “edit” tab on the left and upload an image. On Discord, type --edit followed by the image URL.

Midjourney says there are many edge cases and asks users to report images that do not work well.

Source: Midjourney updates. We summarise in our own words; check the source for the full details.

Related

More AI news

stay in the loop

New guides, prompts and AI model news by email