What are Addons (LoRA models) and how to use them?

LoRA models (Addons in NovArch) are small Diffusion models that apply tiny changes to standard checkpoint models. They are usually 10 to 100 times smaller than checkpoint models. That makes them very attractive additions to the main model collection.

What are LoRA models?

LoRA (Low-Rank Adaptation) is a training technique for fine-tuning NovArch models.

They are used to modify the style or add a special effect to a checkpoint model.

LoRA offers a good trade-off between file size and training power. 

How to use LoRA?

Click on the Exterior or Interior Addons tab. 

You should see a list of LoRA models installed. 

Click on the one you want to use.

The LoRA phrase will be inserted in the prompt. 

 <lora:ArtArchitectureMC:0.65>

That’s it!

Notes on using LoRA

You may adjust the multiplier to crank up or tune down the effect. Setting the multiplier 0 disables the LoRA model. You can adjust the style effect between 0 and 1.

Please note that using two or more LoRA models together is not recommended with an effect strength more than 0.25.