lucataco / realvisxl2-lora-training

POC to train Realvisxl2 LoRAs

  • Public
  • 261 runs
  • GitHub
  • License

Input

Output

Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 10 minutes.

Readme

About

This is a hacked together, proof of concept model to train your own RealvisXL-v2.0 LoRAs. At this time, it does not support the standard Replicate training method (replicate.trainings.create).

All you need are your training images in a zip file and select “use_face_detection_instead” if training faces

Run inference on RealvisXL LoRAs here