LoRA (low-rank adaptation)
Related tutorialA LoRA (low-rank adaptation) is a small, lightweight file that adjusts a base image model so it reliably reproduces one subject, character or style. Instead of retraining the full model, which needs huge datasets and compute, a LoRA learns from a handful of reference images and stores only the changes, making it fast to train and easy to share.
In tendre.AI, you train a character's LoRA from 10 to 15 varied photos (Characters > Create a character > LoRA training), on our servers in about 55 minutes or free on your own graphics card. When you connect the character in Create an image and pick its LoRA, its @ in the scene sends the trigger word. You can also import a Krea 2 LoRA you already have, on the character's profile; LoRAs made for other engines, such as SDXL or FLUX, are refused. Video has its own LoRA (LTX 2.5), trained online.