lucataco / sdxl-lcm-zeke

A fine-tuned SDXL-LCM LoRA based on the photos of Zeke

  • Public
  • 553 runs

Input

Output

Run time and cost

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 15 seconds.

Readme

This is a fine-tuned SDXL-LCM LoRA based on 6 photos of Zeke

To recreate:

  1. Upload zipped photos using this model and get back a URL

  2. Use the following Python code to run this training. Switch out the input_images for the URL in step 1, and replace the model name “lucataco/sdxl-lcm-zeke” to use your own existing replicate model or create one

export REPLICATE_API_TOKEN=r8_****
import replicate
training = replicate.trainings.create(
  version="lucataco/sdxl-lcm:fbbd475b1084de80c47c35bfe4ae64b964294aa7e237e6537eed938cfd24903d",
  input={
        "input_images": "https://replicate.delivery/pbxt/JosiwEGYXZHg0wXzMHcHJPTUMwoN4BsRIB9TOII73u8vbEqr/zeke.zip",
        "use_face_detection_instead": True
  },
  destination="lucataco/sdxl-lcm-zeke"
)