de

app.py

@@ -9,6 +9,7 @@ import cv2
 import gradio as gr
 from torchvision import transforms 
 from controlnet_aux import OpenposeDetector
+import random
 
 ratios_map =  {
     0.5:{"width":704,"height":1408},
@@ -106,139 +107,139 @@ def process(input_image, prompt, negative_prompt, num_steps, controlnet_conditio
     return [pose_image,images[0]]
 
 
-# @spaces.GPU
-# def predict_image(cond_image, prompt, negative_prompt, controlnet_conditioning_scale):
-#   print("predict position map")
-#   global pipe
-#   generator = torch.Generator()
-#   generator.manual_seed(random.randint(0, 2147483647))
-#   image = pipe(
-#       prompt,
-#       negative_prompt=negative_prompt,
-#       image = cond_image,
-#       width=1024,
-#       height=1024,
-#       guidance_scale=8,
-#       num_inference_steps=20,
-#       generator=generator,
-#       guess_mode = True,
-#       controlnet_conditioning_scale = controlnet_conditioning_scale
-#   ).images[0]
+@spaces.GPU
+def predict_image(cond_image, prompt, negative_prompt, controlnet_conditioning_scale):
+  print("predict position map")
+  global pipe
+  generator = torch.Generator()
+  generator.manual_seed(random.randint(0, 2147483647))
+  image = pipe(
+      prompt,
+      negative_prompt=negative_prompt,
+      image = cond_image,
+      width=1024,
+      height=1024,
+      guidance_scale=8,
+      num_inference_steps=20,
+      generator=generator,
+      guess_mode = True,
+      controlnet_conditioning_scale = controlnet_conditioning_scale
+  ).images[0]
   
-#   return image
-
-
-# def convert_pil_to_opencv(pil_image):
-#   return np.array(pil_image)
-
-# def inv_func(y,
-#   c = -712.380100,
-#   a = 137.375240,
-#   b = 192.435866):
-#   return (np.exp((y - c) / a) - np.exp(-c/a)) / 964.8468371292845
-
-# def create_point_cloud(img1, img2):
-#   if img1.shape != img2.shape:
-#     raise ValueError("Both images must have the same dimensions.")
-
-#   h, w, _ = img1.shape
-#   points = []
-#   colors = []
-#   for y in range(h):
-#     for x in range(w):
-#       # ピクセル位置 (x, y) のRGBをXYZとして取得
-#       r, g, b = img1[y, x]
-#       r = inv_func(r) * 0.9
-#       g = inv_func(g) / 1.7 * 0.6
-#       b = inv_func(b)
-#       r *= 150
-#       g *= 150
-#       b *= 150
-#       points.append([g, b, r])  # X, Y, Z
-#       # 対応するピクセル位置の画像2の色を取得
-#       colors.append(img2[y, x] / 255.0)  # 色は0〜1にスケール
-
-#   return np.array(points), np.array(colors)
-
-# def point_cloud_to_glb(points, colors):
-#   # Open3Dでポイントクラウドを作成
-#   pc = o3d.geometry.PointCloud()
-#   pc.points = o3d.utility.Vector3dVector(points)
-#   pc.colors = o3d.utility.Vector3dVector(colors)
+  return image
+
+
+def convert_pil_to_opencv(pil_image):
+  return np.array(pil_image)
+
+def inv_func(y,
+  c = -712.380100,
+  a = 137.375240,
+  b = 192.435866):
+  return (np.exp((y - c) / a) - np.exp(-c/a)) / 964.8468371292845
+
+def create_point_cloud(img1, img2):
+  if img1.shape != img2.shape:
+    raise ValueError("Both images must have the same dimensions.")
+
+  h, w, _ = img1.shape
+  points = []
+  colors = []
+  for y in range(h):
+    for x in range(w):
+      # ピクセル位置 (x, y) のRGBをXYZとして取得
+      r, g, b = img1[y, x]
+      r = inv_func(r) * 0.9
+      g = inv_func(g) / 1.7 * 0.6
+      b = inv_func(b)
+      r *= 150
+      g *= 150
+      b *= 150
+      points.append([g, b, r])  # X, Y, Z
+      # 対応するピクセル位置の画像2の色を取得
+      colors.append(img2[y, x] / 255.0)  # 色は0〜1にスケール
+
+  return np.array(points), np.array(colors)
+
+def point_cloud_to_glb(points, colors):
+  # Open3Dでポイントクラウドを作成
+  pc = o3d.geometry.PointCloud()
+  pc.points = o3d.utility.Vector3dVector(points)
+  pc.colors = o3d.utility.Vector3dVector(colors)
   
-#   # 一時的にPLY形式で保存
-#   temp_ply_file = "temp_output.ply"
-#   o3d.io.write_point_cloud(temp_ply_file, pc)
+  # 一時的にPLY形式で保存
+  temp_ply_file = "temp_output.ply"
+  o3d.io.write_point_cloud(temp_ply_file, pc)
   
-#   # PLYをGLBに変換
-#   mesh = trimesh.load(temp_ply_file)
-#   glb_file = "output.glb"
-#   mesh.export(glb_file)
+  # PLYをGLBに変換
+  mesh = trimesh.load(temp_ply_file)
+  glb_file = "output.glb"
+  mesh.export(glb_file)
 
-#   return glb_file
+  return glb_file
 
-# def visualize_3d(image1, image2):
-#   print("Processing...")
-#   # PIL画像をOpenCV形式に変換
-#   img1 = convert_pil_to_opencv(image1)
-#   img2 = convert_pil_to_opencv(image2)
+def visualize_3d(image1, image2):
+  print("Processing...")
+  # PIL画像をOpenCV形式に変換
+  img1 = convert_pil_to_opencv(image1)
+  img2 = convert_pil_to_opencv(image2)
 
-#   # ポイントクラウド生成
-#   points, colors = create_point_cloud(img1, img2)
+  # ポイントクラウド生成
+  points, colors = create_point_cloud(img1, img2)
 
-#   # GLB形式に変換
-#   glb_file = point_cloud_to_glb(points, colors)
+  # GLB形式に変換
+  glb_file = point_cloud_to_glb(points, colors)
 
-#   return glb_file
+  return glb_file
 
-# def scale_image(original_image):
-#   aspect_ratio = original_image.width / original_image.height
+def scale_image(original_image):
+  aspect_ratio = original_image.width / original_image.height
 
-#   if original_image.width > original_image.height:
-#     new_width = 1024
-#     new_height = round(new_width / aspect_ratio)
-#   else:
-#     new_height = 1024
-#     new_width = round(new_height * aspect_ratio)
+  if original_image.width > original_image.height:
+    new_width = 1024
+    new_height = round(new_width / aspect_ratio)
+  else:
+    new_height = 1024
+    new_width = round(new_height * aspect_ratio)
 
-#   resized_original = original_image.resize((new_width, new_height), Image.LANCZOS)
+  resized_original = original_image.resize((new_width, new_height), Image.LANCZOS)
 
-#   return resized_original
+  return resized_original
 
-# def get_edge_mode_color(img, edge_width=10):
-#   # 外周の10ピクセル領域を取得
-#   left = img.crop((0, 0, edge_width, img.height))  # 左端
-#   right = img.crop((img.width - edge_width, 0, img.width, img.height))  # 右端
-#   top = img.crop((0, 0, img.width, edge_width))  # 上端
-#   bottom = img.crop((0, img.height - edge_width, img.width, img.height))  # 下端
+def get_edge_mode_color(img, edge_width=10):
+  # 外周の10ピクセル領域を取得
+  left = img.crop((0, 0, edge_width, img.height))  # 左端
+  right = img.crop((img.width - edge_width, 0, img.width, img.height))  # 右端
+  top = img.crop((0, 0, img.width, edge_width))  # 上端
+  bottom = img.crop((0, img.height - edge_width, img.width, img.height))  # 下端
 
-#   # 各領域のピクセルデータを取得して結合
-#   colors = list(left.getdata()) + list(right.getdata()) + list(top.getdata()) + list(bottom.getdata())
+  # 各領域のピクセルデータを取得して結合
+  colors = list(left.getdata()) + list(right.getdata()) + list(top.getdata()) + list(bottom.getdata())
 
-#   # 最頻値（mode）を計算
-#   mode_color = Counter(colors).most_common(1)[0][0]  # 最も頻繁に出現する色を取得
+  # 最頻値（mode）を計算
+  mode_color = Counter(colors).most_common(1)[0][0]  # 最も頻繁に出現する色を取得
 
-#   return mode_color
+  return mode_color
 
-# def paste_image(resized_img):
-#   # 外周10pxの最頻値を背景色に設定
-#   mode_color = get_edge_mode_color(resized_img, edge_width=10)
-#   mode_background = Image.new("RGBA", (1024, 1024), mode_color)
-#   mode_background = mode_background.convert('RGB')
+def paste_image(resized_img):
+  # 外周10pxの最頻値を背景色に設定
+  mode_color = get_edge_mode_color(resized_img, edge_width=10)
+  mode_background = Image.new("RGBA", (1024, 1024), mode_color)
+  mode_background = mode_background.convert('RGB')
 
-#   x = (1024 - resized_img.width) // 2
-#   y = (1024 - resized_img.height) // 2
-#   mode_background.paste(resized_img, (x, y))
+  x = (1024 - resized_img.width) // 2
+  y = (1024 - resized_img.height) // 2
+  mode_background.paste(resized_img, (x, y))
 
-#   return mode_background
+  return mode_background
 
-# def outpaint_image(image):
-#   if type(image) == type(None):
-#     return None
-#   resized_img = scale_image(image)
-#   image = paste_image(resized_img)
+def outpaint_image(image):
+  if type(image) == type(None):
+    return None
+  resized_img = scale_image(image)
+  image = paste_image(resized_img)
   
-#   return image
+  return image
     
 block = gr.Blocks().queue()