benchmark/sd_controlnet.py

#!/usr/bin/env python3
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
import requests
import torch
from PIL import Image
from io import BytesIO

url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"

response = requests.get(url)
init_image = Image.open(BytesIO(response.content)).convert("RGB")
init_image = init_image.resize((512, 512))

path = "runwayml/stable-diffusion-v1-5"

run_compile = True  # Set True / False
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    path, controlnet=controlnet, torch_dtype=torch.float16
)

pipe = pipe.to("cuda:0")
pipe.unet.to(memory_format=torch.channels_last)
pipe.controlnet.to(memory_format=torch.channels_last)

if run_compile:
    print("Run torch compile")
    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
    pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)

prompt = "ghibli style, a fantasy landscape with castles"

for _ in range(3):
    image = pipe(prompt=prompt, image=init_image).images[0]