Concepts / Low-Rank Adaptations (LoRAs)

Modified on Thu, 04 Jan 2024 at 07:02 AM

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.

Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select atleast one of the reasons

Feedback sent

We appreciate your effort and will try to fix the article