app.py

import gradio
import cv2
import numpy as np

#num_inference_steps_slider_component_v1 = 121 
#num_inference_steps_slider_component_v2  = 3

def inference(img, v1  = "121" , v2 = 9 ):
  #out = cv2.erode(img,(15,15))
  #out = cv2.dilate(out,(55,55))
  # https://scikit-image.org/docs/dev/api/skimage.morphology.html#skimage.morphology.remove_small_objects  
  # my_result = cv2.remove_small_objects(binarized.astype(bool), min_size=2, connectivity=2).astype(int)

  #img_bw = 255*(cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) > 5).astype('uint8')
  #se1 = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
  #se2 = cv2.getStructuringElement(cv2.MORPH_RECT, (2,2))
  #mask = cv2.morphologyEx(img_bw, cv2.MORPH_CLOSE, se1)
  #mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, se2)
  #mask = np.dstack([mask, mask, mask]) / 255
  #out = img * mask

  gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY ) # grayscale
  #out = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,133,9)
  #out = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,333,3)
  out = cv2.GaussianBlur( gray ,(5,5),0)
  #  v1 121 , v2 1
  #out = cv2.adaptiveThreshold( out ,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, int( float(v1) ) , int( float(v2) ) )
  #out = cv2.adaptiveThreshold( out ,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 77 , int ( v2 ) )
  out = cv2.adaptiveThreshold( out ,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 233 , 1 )
  #out = blur = cv.GaussianBlur(img,(5,5),0)
  #out =  cv2.threshold(out,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)

    
  #kernel = cv2.getStructuringElement(cv2.MORPH_RECT, kernelSize)
  #opening = cv2.morphologyEx(gray, cv2.MORPH_OPEN, kernel)

  return out

num_inference_steps_slider_component_v1 = gradio.Slider(
label="Number of inference steps",
info="The number of denoising steps. More denoising steps "
"usually lead to a higher quality image at the",
minimum=1,
maximum=500,
step=1,
value=121,
)

num_inference_steps_slider_component_v2 = gradio.Slider(
label="Number of inference steps",
info="The number of denoising steps. More denoising steps "
"usually lead to a higher quality image at the",
minimum=1,
maximum=100,
step=1,
value=3,
)

# For information on Interfaces, head to https://gradio.app/docs/
# For user guides, head to https://gradio.app/guides/
# For Spaces usage, head to https://huggingface.co/docs/hub/spaces
iface = gradio.Interface(
  fn=inference,
  inputs=['image',num_inference_steps_slider_component_v1,num_inference_steps_slider_component_v2],
  outputs='image',
  title='Noise Removal', 
  description='Remove Noise with OpenCV and Adaptial Gaussian!',
  examples=[["detail_with_lines_and_noise.jpg", "lama.webp", "dT4KW.png"]]
)
  #examples=["detail_with_lines_and_noise.jpg", "lama.webp", "dT4KW.png"])  
  #examples=["detail_with_lines_and_noise.jpg", "lama.webp", "test_lines.jpg","llama.jpg", "dT4KW.png"])  

iface.launch()