Stable Diffusion Schedule Type: Explained + Best Settings
- Cole B.
In this article I am going to explain five different stable diffusion schedule types and which one you should choose when generating your images.
Choosing the right schedule type can transform your images to look amazing if done right.
So if you want to start generating better images, you’ll love this guide.
What Are Stable Diffusion Schedule Types?
Stable diffusion schedule types or noise schedulers are methods of adding and removing noise to get your final image.
It is what basically gets an image looking like this:
To this:
But the process is different for removing noise depending on which schedule type you use:
Different Noise Schedulers Explained
In this section, I am going to cover all the noise scheduling methods in WebUi.
This will give you a background of how each one works before I tell you the best ones to use in the next section.
Karras
Karras follows an algorithm that generates noise based on the discretizations of Euclidian distance.
To be honest, I don’t know what that means.
But what matters is that Karras adjusts the noise scheduling depending on the number of steps. It will remove noise at progressively smaller steps at the end of the process.
It is a lot more flexible than other fixed schedulers, making it very reliable.
Exponential
Exponential is exactly the same as we learned it in school.
It removes noise very rapidly at the beginning steps but reduces the amount of noise removed later.
It is best for using a small amount of steps per image.
Uniform
Uniform reduces noise at a consistent amount per image.
It can have some non optimal performance compared to other types due to it not being able to focus on critical steps in the process.
Polyexponential
Polyexponential uses a combination of exponential rates.
This enables the model to be able to adapt to the data distribution better.
SGM Uniform
SGMs estimate a gradient or score based on the noise level data to add and remove noise.
What Is The Best Schedule Type?
TLDR: Karras is the best.
The generally recommended schedule type is Karras. This is because of Its ability to adjust noise removal using its formula makes it the best.
Secondly, I wouldn’t recommend both uniform types as much as the other. Especially just uniform.
Scheduler Comparisons
Below, I made a x/y/z plot of the schedule types from above.
I am going to compare the quality of images created with different sampling steps amounts to see which one has the highest quality:
Prompt: race car on a icy mountain peak, snowy landscape, dramatic lighting, cinematic, establishing shot, extremely high detail, photorealistic
Most of the images look similar but uniform has worst images at lower and higher steps.
Otherwise, the three schedulers in the middle have the best looking images with karras looking the best.
Let Me Know What You Think
There you have it.
Everything you need to know about stable diffusion schedule types.
Let me know if I missed anything or add something you want to see by leaving a comment below.
