Advertisement: Click here to learn how to Generate Art From Text
SREF is a new feature released by Midjourney that acts like a LoRA style training tool. It allows you to generate images with a certain style aesthetic by simply learning from an image.
It’s cool that you can get consistent results using just one image.
- Use the argument to start your sentence.
--srefFollowed by the URL of one or more images.
- Midjourney will create your image by analysing the image(s) you provide and using the style, aesthetics and design of that image.
- Both V6 and Niji V6 are compatible. Does not work on earlier models.
- You can use more than one image like this
--sref urlA urlB urlC
- You can also change the weights of styles as follows
--sref urlA::2 urlB::3 urlC::5
- You can also change the overall strength of the stylization by using
--sw 100(100 is the default, 0 is off and 1000 is the maximum)
- You can also use this when using image prompts. However, your images must come before
/imagine cat ninja ImagePrompt1 ImagePrompt2 --sref stylePrompt1 stylePrompt2
Midjourney colour grades your image using the colour scheme from the reference image.
Let’s explore this further with a reference image from Mad Max: Fury Road
Let’s create an image using this prompt:
a old 1965 Post-Apocalyptic mustang in a dystopian scene, mustang is heavily modified with armour and weapons to protect it's driver, shot from behind the car overlooking a desert landscape and rocky mountains, camera is placed at a very low angle --ar 239:100 --sref https://s.mj.run/C76XE6JqaTA --stylize 200 --v 6
You can see that the resultant image has the exact same colour grading. The source image has the same aesthetics and style. We did not mention anything about the colour scheme. We will now run the same prompt, but without the colour scheme.
A 1965 Post-Apocalyptic Mustang in a dystopian setting, the car is heavily modified and equipped with weapons and armour to protect its driver. The scene is shot from behind, overlooking a desert and rocky mountains.
You can see these images have different aesthetics and its based on Midjourney’s own interpretation of what it should look like. So using the –sref style reference has immense benefit to the results.
Let’s try from another movie – Tenet
Here is the result with prompt
a african american man in a well dressed suit standing in a secret research facility --ar 239:100 --sref https://film-grab.com/wp-content/uploads/photo-gallery/Tenet_027.jpg?bwg=1614340151 --sw 300 --stylize 200 --v 6
Midjourney is amazing. SREF style reference let’s you replicate the aesthetics of a reference image in the image you are creating with the prompt. It’s a great way to create consistent images with Midjourney.
Original content by wackywonderfulai.art – “A guide to SREF style reference in midjourney”
Read the full article here https://weirdwonderfulai.art/resources/a-guide-to-sref-style-reference-in-midjourney/