app.py

app.py

@@ -12,8 +12,6 @@ from utils.image_utils import resize_image_aspect_ratio, base_generation
 from utils.prompt_utils import execute_prompt, remove_color, remove_duplicates
 from utils.tagger import modelLoad, analysis
 
-
-
 path = os.getcwd()
 cn_dir = f"{path}/controlnet"
 tagger_dir = f"{path}/tagger"
@@ -99,7 +97,7 @@ class Img2Img:
                 with gr.Column():
                     self.input_image_path = gr.Image(label="input_image", type='filepath')
                     self.prompt = gr.Textbox(label="prompt", lines=3)
-                    self.negative_prompt = gr.Textbox(label="negative_prompt", lines=3, value="lowres, error, extra digit, fewer digits, cropped, worst quality,low quality, normal quality, jpeg artifacts, blurry")
+                    self.negative_prompt = gr.Textbox(label="negative_prompt", lines=3, value="sketch, lowres, error, extra digit, fewer digits, cropped, worst quality,low quality, normal quality, jpeg artifacts, blurry")
                     prompt_analysis_button = gr.Button("prompt_analysis")
                     self.controlnet_scale = gr.Slider(minimum=0.5, maximum=1.25, value=1.0, step=0.01, label="controlnet_scale")                 
                     generate_button = gr.Button("generate")

utils/dl_utils.py

@@ -33,7 +33,7 @@ def dl_cn_config(model_dir):
      shutil.copy(config_path, file_path)
 
 def dl_tagger_model(model_dir):
-    model_id = 'SmilingWolf/wd-swinv2-tagger-v3'
+    model_id = 'SmilingWolf/wd-vit-tagger-v3'
     files = [
         'config.json', 'model.onnx', 'selected_tags.csv', 'sw_jax_cv_config.json'
     ]

utils/image_utils.py

@@ -27,50 +27,6 @@ def canny_process(image_path, threshold1, threshold2):
     return canny
 
 
-def line_process(image_path, sigma, gamma):
-    def DoG_filter(image, kernel_size=0, sigma=1.0, k_sigma=2.0, gamma=1.5):
-        g1 = cv2.GaussianBlur(image, (kernel_size, kernel_size), sigma)
-        g2 = cv2.GaussianBlur(image, (kernel_size, kernel_size), sigma * k_sigma)
-        return g1 - gamma * g2
-
-    def XDoG_filter(image, kernel_size=0, sigma=1.4, k_sigma=1.6, epsilon=0, phi=10, gamma=0.98):
-        epsilon /= 255
-        dog = DoG_filter(image, kernel_size, sigma, k_sigma, gamma)
-        dog /= dog.max()
-        e = 1 + np.tanh(phi * (dog - epsilon))
-        e[e >= 1] = 1
-        return (e * 255).astype('uint8')
-
-    def binarize_image(image):
-        _, binarized = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-        return binarized
-
-    def process_XDoG(image, kernel_size=0, sigma=1.4, k_sigma=1.6, epsilon=0, phi=10, gamma=0.98):
-        xdog_image = XDoG_filter(image, kernel_size, sigma, k_sigma, epsilon, phi, gamma)
-        binarized_image = binarize_image(xdog_image)
-        final_image_pil = Image.fromarray(binarized_image)
-        return final_image_pil
-
-    # 画像を開き、RGBA形式に変換して透過情報を保持
-    img = Image.open(image_path)
-    img = img.convert("RGBA")
-
-    canvas_image = Image.new('RGBA', img.size, (255, 255, 255, 255))
-    
-    # 画像をキャンバスにペーストし、透過部分が白色になるように設定
-    canvas_image.paste(img, (0, 0), img)
-
-    # RGBAからRGBに変換し、透過部分を白色にする
-    image_pil = canvas_image.convert("RGB")
-    
-    # OpenCVが扱える形式に変換
-    image_cv = cv2.cvtColor(np.array(image_pil), cv2.COLOR_RGB2BGR)
-    image_gray = cv2.cvtColor(image_cv, cv2.COLOR_BGR2GRAY)
-    inv_Line = process_XDoG(image_gray, kernel_size=0, sigma=sigma, k_sigma=1.6, epsilon=0, phi=10, gamma=gamma)
-    return inv_Line
-
-
-
 def resize_image_aspect_ratio(image):
     # 元の画像サイズを取得
     original_width, original_height = image.size