Low-Rank Adaptations (LoRAs)

Low-Rank Adaptations, commonly referred to as LoRAs, are lightweight models that are used in conjucntion with base models.

Using LoRAs

• LoRAs are best used when trying to fine-tune results in order to achieve a certain style.
• To use a LoRA, open the LoRA menu item in the options panel, select the LoRAs you want to apply and select a desired weight. The weight of the LoRA determines the impact the LoRA will have on the final generation. Typically, most LoRAs perform best at a weight of .75-1.
• Some LoRAs may be supplied with a "trigger" word in the prompt that they have been explicitly trained on, while others may simply apply their effect without being triggered.