xinsir/controlnet-depth-sdxl-1.0

ControlNet Depth SDXL, support zoe, midias

Example

How to use it

from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
from diffusers import DDIMScheduler, EulerAncestralDiscreteScheduler
from PIL import Image
import torch
import random
import numpy as np
import cv2


from controlnet_aux import MidasDetector, ZoeDetector


processor_zoe = ZoeDetector.from_pretrained('lllyasviel/ControlNet')
processor_midas = MidasDetector.from_pretrained('lllyasviel/ControlNet')


controlnet_conditioning_scale = 1.0  
prompt = "your prompt, the longer the better, you can describe it as detail as possible"
negative_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality'

eulera_scheduler = EulerAncestralDiscreteScheduler.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="scheduler")


controlnet = ControlNetModel.from_pretrained(
    "xinsir/controlnet-depth-sdxl-1.0",
    torch_dtype=torch.float16
)

# when test with other base model, you need to change the vae also.
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)

pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet,
    vae=vae,
    safety_checker=None,
    torch_dtype=torch.float16,
    scheduler=eulera_scheduler,
)

# need to resize the image resolution to 1024 * 1024 or same bucket resolution to get the best performance

img = cv2.imread("your original image path")

if random.random() > 0.5:
    controlnet_img = processor_zoe(img, output_type='cv2')
else:
    controlnet_img = processor_midas(img, output_type='cv2')


height, width, _  = controlnet_img.shape
ratio = np.sqrt(1024. * 1024. / (width * height))
new_width, new_height = int(width * ratio), int(height * ratio)
controlnet_img = cv2.resize(controlnet_img, (new_width, new_height))
controlnet_img = Image.fromarray(controlnet_img)


images = pipe(
    prompt,
    negative_prompt=negative_prompt,
    image=controlnet_img,
    controlnet_conditioning_scale=controlnet_conditioning_scale,
    width=new_width,
    height=new_height,
    num_inference_steps=30,
    ).images

images[0].save(f"your image save path, png format is usually better than jpg or webp in terms of image quality but got much bigger")