Ambrosiussen / controlnet_aux

ControlNet auxiliary models

This is a PyPi installable package of lllyasviel's ControlNet Annotators

The code is copy-pasted from the respective folders in https://github.com/lllyasviel/ControlNet/tree/main/annotator and connected to the 🤗 Hub.

All credit & copyright goes to https://github.com/lllyasviel .

Install

pip install controlnet-aux==0.0.3

Usage

from PIL import Image
import requests
from io import BytesIO
from controlnet_aux import HEDdetector, MidasDetector, MLSDdetector, OpenposeDetector, PidiNetDetector, NormalBaeDetector, LineartDetector, LineartAnimeDetector, CannyDetector, ContentShuffleDetector, ZoeDetector, MediapipeFaceDetector

# load image
url = "https://huggingface.co/lllyasviel/sd-controlnet-openpose/resolve/main/images/pose.png"

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

# load checkpoints
hed = HEDdetector.from_pretrained("lllyasviel/Annotators")
midas = MidasDetector.from_pretrained("lllyasviel/Annotators")
mlsd = MLSDdetector.from_pretrained("lllyasviel/Annotators")
open_pose = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
pidi = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
normal_bae = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
lineart = LineartDetector.from_pretrained("lllyasviel/Annotators")
lineart_anime = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators")
zoe = ZoeDetector.from_pretrained("lllyasviel/Annotators")

# instantiate
canny = CannyDetector()
content = ContentShuffleDetector()
face_detector = MediapipeFaceDetector()


# process
processed_image_hed = hed(img)
processed_image_midas = midas(img)
processed_image_mlsd = mlsd(img)
processed_image_open_pose = open_pose(img, hand_and_face=True)
processed_image_pidi = pidi(img, safe=True)
processed_image_normal_bae = normal_bae(img)
processed_image_lineart = lineart(img, coarse=True)
processed_image_lineart_anime = lineart_anime(img)
processed_image_zoe = zoe(img)

processed_image_canny = canny(img)
processed_image_content = content(img)
processed_image_mediapipe_face = face_detector(img)