Midjourney: ↩️ What is Omni-Reference?
- Omni-reference can be best thought of as a system of saying “put THIS in my image”.
- It can work for characters, objects, vehicles, or non-human creatures
- Omni-reference works with personalization, stylization, style references, and moodboards
How to use Omni-Reference
- On web: Drag a image into the prompt bar. Drop it into the bin that says 'omni-reference'. There's a slider icon to control strength.
-On discord: Type --oref url where url goes to an image url and use --ow to controls strength.
About Omni-Reference Weighing
- There's a ‘omni-weight’ parameter called –-ow (with a slider on the web ui) that controls how strictly it adheres to your image reference. This parameter goes from 0 to 100 to 1000 (100 is default)
- If you want to change the style of the image (such as photo to anime) you should lower the weight (ie: -–ow 25)
- If you want to make a characters face is extremely visible (or that their clothes are preserved) you should try something higher like –-ow 400
- Both -–stylize and -–exp also compete for influence over the image with omni-reference so if you have a high stylize or exp value you probably want touse a higher corresponding omni-weight value
Example: /imagine a person –stylize 1000 –-ow 1000 --exp 100 –-oref person.png
- Please note: If you aren't using extremely high stylize and exp you should probably never want go over 'moderate' values of ow like --ow 400 or things may actually be worse
More about using Omni-reference
- If you want a character to hold a sword in an image please make sure you say that in your prompt a character holding a sword –-oref sword.png
- If you want to style transfer a character and have a low omni-weight please make sure to over-specify the parts of your character you want to preserve
Example: /imagine a anime woman with blonde hair and red suspenders --oref url –-ow 25
- It’s somewhat untested but if you have two characters (or object/character/etc) in your omni-reference image (either in the same image or just in two images side by side) and you refer to them both in your prompt can often get those two characters in your resulting image too
We know this is all a bit experimental. Honestly, there’s SO MANY ways to use this feature. It’s hard for us to know what works well, what doesn’t work well, and what people want to use or improve most. Let us know what you think!
Thanks everyone and have fun! <3
Fri May 02 2025 07:11:03 GMT+0800 (China Standard Time)
