pintor-de-anime

from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
from diffusers import DDIMScheduler, EulerAncestralDiscreteScheduler
from controlnet_aux import PidiNetDetector, HEDdetector
from diffusers.utils import load_image
from huggingface_hub import HfApi
from pathlib import Path
from PIL import Image
import torch
import numpy as np
import cv2
import os

def nms(x, t, s):
    x = cv2.GaussianBlur(x.astype(np.float32), (0, 0), s)
    f1 = np.array([[0, 0, 0], [1, 1, 1], [0, 0, 0]], dtype=np.uint8)
    f2 = np.array([[0, 1, 0], [0, 1, 0], [0, 1, 0]], dtype=np.uint8)
    f3 = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]], dtype=np.uint8)
    f4 = np.array([[0, 0, 1], [0, 1, 0], [1, 0, 0]], dtype=np.uint8)
    y = np.zeros_like(x)
    for f in [f1, f2, f3, f4]:
        np.putmask(y, cv2.dilate(x, kernel=f) == x, x)
    z = np.zeros_like(y, dtype=np.uint8)
    z[y > t] = 255
    return z

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("gsdf/CounterfeitXL", subfolder="scheduler")
controlnet = ControlNetModel.from_pretrained("xinsir/anime-painter", torch_dtype=torch.float16)
vae = AutoencoderKL.from_pretrained("gsdf/CounterfeitXL", subfolder="vae", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "gsdf/CounterfeitXL",
    controlnet=controlnet,
    vae=vae,
    safety_checker=None,
    torch_dtype=torch.float16,
    scheduler=eulera_scheduler,
)

if random.random() > 0.5:
    image_path = Image.open("your image path, the image can be real or anime, HED detector will extract its edge boundery")
    processor = HEDdetector.from_pretrained('lllyasviel/Annotators')
    controlnet_img = processor(image_path, scribble=False)
    controlnet_img.save("a hed detect path for an image")
    controlnet_img = np.array(controlnet_img)
    controlnet_img = nms(controlnet_img, 127, 3)
    controlnet_img = cv2.GaussianBlur(controlnet_img, (0, 0), 3)
    random_val = int(round(random.uniform(0.01, 0.10), 2) * 255)
    controlnet_img[controlnet_img > random_val] = 255
    controlnet_img = Image.fromarray(controlnet_img)
else:
    control_path = "the sketch image you draw with some tools, like drawing board, the path you save it"
    controlnet_img = Image.open(control_path)
    width, height  = controlnet_img.size
    ratio = np.sqrt(1024. * 1024. / (width * height))
    new_width, new_height = int(width * ratio), int(height * ratio)
    controlnet_img = controlnet_img.resize((new_width, new_height))

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")