At all those web sites for using AI to create images or videos, one term appears often: "LoRa" = Low-Rank Adaptation. It turns out that these are extensions of the original model which add to the original model without that model having to be re-trained. Hereby a lot of computing time is saved.
Here is the explanation of LoRa from one of its inventors at Microsoft, Edward Hu:
No comments:
Post a Comment