demo_inpainting.py

import torch
from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image, make_image_grid
from scheduling_tcd import TCDScheduler 

device = "cuda"
base_model_id = "diffusers/stable-diffusion-xl-1.0-inpainting-0.1"
tcd_lora_id = "h1t/TCD-SDXL-LoRA"

pipe = AutoPipelineForInpainting.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)

pipe.load_lora_weights(tcd_lora_id)
pipe.fuse_lora()

img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"

init_image = load_image(img_url).resize((1024, 1024))
mask_image = load_image(mask_url).resize((1024, 1024))

prompt = "a tiger sitting on a park bench"

image = pipe(
  prompt=prompt,
  image=init_image,
  mask_image=mask_image,
  num_inference_steps=8,
  guidance_scale=0,
  eta=0.3, # A parameter (referred to as `gamma` in the paper) is used to control the stochasticity in every step. A value of 0.3 often yields good results.
  generator=torch.Generator(device=device).manual_seed(0),
).images[0]

grid_image = make_image_grid([init_image, mask_image, image], rows=1, cols=3)