fofr / sdxl-reference

Make variations of an image with SDXL

  • Public
  • 357 runs
  • GitHub

If you haven’t yet trained a model on Replicate, we recommend you read one of the following guides.

Pricing

Trainings for this model run on Nvidia L40S GPU hardware, which costs $0.000975 per second.

Create a training

Install the Python library:

pip install replicate

Then, run this to create a training with fofr/sdxl-reference:255c5260 as the base model:

import replicate

training = replicate.trainings.create(
  version="fofr/sdxl-reference:255c5260c64a99de3c76bb349d517e75ef59280d97cae56b1b4118010075d98b",
  input={
    ...
  },
  destination=f"{username}/<destination-model-name>"
)

print(training)

Note that before you can create a training, you’ll need to create a model and use its name as the value for the destination field.