Model Information
![Contrast Controller [SDXL] - Image 1](/_next/image?url=https%3A%2F%2Fcdn.prompthero.com%2Ff8u8jp2buvktgqppnbo1tgqxsi10-Contrast%20Controller%20%5BSDXL%5D.jpeg&w=1920&q=75)
![Contrast Controller [SDXL] - Image 2](/_next/image?url=https%3A%2F%2Fcdn.prompthero.com%2Fxh0uqua2p1hn4go6c66ae81wz3ll-Contrast%20Controller%20%5BSDXL%5D.jpeg&w=1920&q=75)
![Contrast Controller [SDXL] - Image 3](/_next/image?url=https%3A%2F%2Fcdn.prompthero.com%2Fu9ryzzeasx9s02bj95ucgiln1rjz-Contrast%20Controller%20%5BSDXL%5D.jpeg&w=1920&q=75)
![Contrast Controller [SDXL] - Image 4](/_next/image?url=https%3A%2F%2Fcdn.prompthero.com%2Fye2gufy5qr2zo48709z24522tr8g-Contrast%20Controller%20%5BSDXL%5D.jpeg&w=1920&q=75)
![Contrast Controller [SDXL] - Image 5](/_next/image?url=https%3A%2F%2Fcdn.prompthero.com%2Fub2m1wfjt7xkl3nmy94fmrqqimmk-Contrast%20Controller%20%5BSDXL%5D.jpeg&w=1920&q=75)
Description
Contrast Controller
Can you control contrast in SDXL just like using a slider on your monitor? Now you can. And it's simple, it's a LoRA, and can do more than just controling contrast.
What does this LoRA do?
Short answer: It can amplify (strength >0) or reduce (strength <0) the contrast/saturation of your base model.
Answer for advance users:
It can control the "strength" of the U-net output. So you no longer have to choose between "creativity/low CFG scale" and "high contrast". Now you can have both. (Sounds like FreeU, RescaleCFG and DynamicCFG-Fix etc., but much more simple in this case).
You can increase base model contrast so you can lower CFG scale, and get more creative result and details.
Or vice versa, reduce base model contrast so you can use higher CFG to get a stable and clean result, without oversaturation.
Most importantly, this LoRA has ZERO side effects on style.
WTF is this 400KiB LoRA file. Is the file broken?
No. It is a fully functional LoRA. And probably the smallest LoRA. I even tried a 30KiB version, and did not feel any difference. But my inner heart told me not to go too crazy.
How to use it?
Just apply it as normal LoRA.
Recommended strength is -0.5~0.5.
You don't have to set the patch strength for text encoder. This LoRA does not patch it.
Also recommend adjusting your CFG scales.
Supported models?
Guaranteed: Models that are close to Illustrious v0.1, including NoobAI.
Surprisingly, seems it works well on all SDXL model.
What's the training data?
This LoRA is "calculated/calibrated" from SDXL and Illustrious v0.1. No training process.
Sounds like some kind of black magic.
Yes, it is. But it works well.
Share merges using this LoRA is allowed. However, you must credit the creator and provide a link to this page. It is easy for me to know whether a model merged my LoRA, because the weight pattern will become very unique after this LoRA applied. A normally trained model will never have such kind of pattern.
Feedback in comment section is welcome.
Have fun.
Contrast Controller [SDXL]
illus01 v1
Model Details
- Type
- Model Addon
- Subtype
- LoRA
- Created
- Updated
- June 7, 2026