pnickolas1 / sdxl-dreambooth-loras-dev

  • Public
  • 2.7K runs
  • SDXL fine-tune

Run time and cost

This model costs approximately $0.025 to run on Replicate, or 40 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 26 seconds.

Readme

def train_replicate_sdxl_loras(): training = replicate.trainings.create( version=”stability-ai/sdxl:d830ba5dabf8090ec0db6c10fc862c6eb1c929e1a194a5411852d25fd954ac82”, input={ “input_images”: path_to_zip_training_images, “use_face_detection_instead”: True, “instance_prompt”: “A photo {name} {description}”.format(name=”TOK”, description=”man”), “class_prompt”: “a photo of a man”, }, destination=”pnickolas1/sdxl-dreambooth-loras-dev”, ) print(training)