Update app.py

app.py

@@ -121,37 +121,16 @@ def infer(
     progress=gr.Progress(track_tqdm=True)
 ):
 
-
     # Генерация изображений с Ip_Adapter ------------------------------------------------------------------------------------------------------------------
-    if use_ip_adapter: #and ip_source_image is not None and ip_adapter_image is not None:
+    if use_ip_adapter: and ip_source_image is not None and ip_adapter_image is not None:
         
-        # Режим pose_estimation --------------------------------------------------------------------------------------------------------------------------- 
-        # prompt =  "A man runs through the park against the background of trees. The man's entire figure, face, arms and legs are visible. Anime style. The best quality."
-        # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
-
-        # seed = 4
-        # width = 512
-        # height = 512
-        # num_inference_steps = 50
-        # guidance_scale = 7.5
-        # lora_scale = 0.7
-
-        # strength_ip = 0.9        # Коэфф. зашумления IP_adapter
-        # ip_adapter_strength = 0.2 # Сила влияния IP_adapter
-        # controlnet_conditioning_scale = 0.99 # Сила влияния ControlNet
-
-        # use_ip_adapter = True     # Параметр для включения IP_adapter
-        # ip_source_image = load_image("ControlNet_1.jpeg") # Исходное изображение IP_adapter
-        # ip_adapter_image = load_image("Run.jpeg")   # Контрольное изображение IP_adapter
-
-        # #ip_adapter_mode = "pose_estimation" # Режим работы Ip_Adapter 
-
         if ip_adapter_mode == "pose_estimation":    
 
             print('ip_adapter_mode = ', ip_adapter_mode)
             
             # Инициализация ControlNet
-            controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype)
+            controlnet_model_path = "lllyasviel/sd-controlnet-openpose"
+            controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch_dtype)
 
             generator = torch.Generator(device).manual_seed(seed)
 
@@ -210,30 +189,10 @@ def infer(
                 height=height,
                 num_inference_steps=num_inference_steps,
                 guidance_scale=guidance_scale,
-                controlnet_conditioning_scale=controlnet_conditioning_scale,
+                controlnet_conditioning_scale=0.99, #controlnet_conditioning_scale,
                 generator=generator,
             ).images[0]
         else:
-            # Режим edge_detection ---------------------------------------------------------------------------------------------------------------------------        
-            # prompt =  "The smiling man. His face and hands are visible. Anime style. The best quality."
-            # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
-
-            # seed = 9
-            # width = 512
-            # height = 512
-            # num_inference_steps = 50
-            # guidance_scale = 7.5
-            # lora_scale = 0.7
-
-            # strength_ip = 0.5 #0.9         # Коэфф. зашумления IP_adapter
-            # ip_adapter_strength = 0.15 #0.1 # Сила влияния IP_adapter
-            # controlnet_conditioning_scale = 0.6 # Сила влияния ControlNet
-
-            # use_ip_adapter = True     # Параметр для включения IP_adapter
-            # ip_source_image = load_image("005_6.jpeg")  # Исходное изображение IP_adapter
-            # ip_adapter_image = load_image("edges.jpeg")   # Контрольное изображение IP_adapter
-
-            # #ip_adapter_mode = "edge_detection" # Режим работы Ip_Adapter 
 
             if ip_adapter_mode == "edge_detection":    
 
@@ -318,34 +277,15 @@ def infer(
                     height=height,
                     num_inference_steps=num_inference_steps,
                     guidance_scale=guidance_scale,
-                    controlnet_conditioning_scale=controlnet_conditioning_scale,
+                    controlnet_conditioning_scale=0.6, #controlnet_conditioning_scale,
                     generator=generator,
                 ).images[0]    
             else:
-                # Режим depth_map ---------------------------------------------------------------------------------------------------------------------------    
-                # prompt =  "The smiling girl, best quality, high quality"
-                # negative_prompt = "monochrome, lowres, bad anatomy, worst quality, low quality" #"Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
-
-                # seed = 6
-                # num_inference_steps = 50
-                # guidance_scale = 7.5
-                # lora_scale = 0.7
-
-                # strength_ip = 0.9         # Коэфф. зашумления IP_adapter
-                # ip_adapter_strength = 0.5 # Сила влияния IP_adapter
-                # controlnet_conditioning_scale = 0.99 # Сила влияния ControlNet
-
-                # use_ip_adapter = True     # Параметр для включения IP_adapter
-                # ip_adapter_image = load_image("032_3.jpeg")
-                # depth_map = load_image("depth_map.jpeg") 
-                
-                # #ip_adapter_mode = "depth_map" # Режим работы Ip_Adapter 
 
                 if ip_adapter_mode == "depth_map":    
 
                     print('ip_adapter_mode = ', ip_adapter_mode)
-
-                   
+                 
                     # Инициализация ControlNet
                     controlnet_model_path = "lllyasviel/control_v11f1p_sd15_depth"
                     controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16)
@@ -368,39 +308,21 @@ def infer(
                         num_inference_steps=num_inference_steps,
                         strength=strength_ip, # Коэфф. зашумления, чем больше, тем больше меняется результирующее изображение относитенльно исходного
                         guidance_scale=guidance_scale,
-                        controlnet_conditioning_scale=controlnet_conditioning_scale,
+                        controlnet_conditioning_scale=0.99, #controlnet_conditioning_scale,
                         generator=generator,
                     ).images[0]
     else:
         # Генерация изображений с ControlNet ----------------------------------------------------------------------------------------------------------------
-        if use_control_net: #and control_image is not None and cn_source_image is not None:
-
-            # Режим pose_estimation --------------------------------------------------------------------------------------------------------------------------- 
-            # prompt =  "A man runs through the park against the background of trees. The man's entire figure, face, arms and legs are visible. Anime style. The best quality."
-            # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
 
-            # seed = 444
-            # width = 512
-            # height = 512
-            # num_inference_steps = 50
-            # guidance_scale = 7.5
-            # lora_scale = 0.7
-
-            # strength_cn = 0.9       # Коэфф. зашумления ControlNet
-            # control_strength = 0.92  # Сила влияния ControlNet
-
-            # use_control_net = True   # Параметр для включения ControlNet
-            # cn_source_image = load_image("ControlNet_1.jpeg") # Исходное изображение ControlNet
-            # control_image = load_image("Run.jpeg")   # Контрольное изображение ControlNet
-
-            # #control_mode = "pose_estimation" # Режим работы ControlNet 
+        if use_control_net: and control_image is not None and cn_source_image is not None:
 
             if control_mode == "pose_estimation":     
 
                 print('control_mode = ', control_mode)
 
                 # Инициализация ControlNet
-                controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype)
+                controlnet_model_path = "lllyasviel/sd-controlnet-openpose"
+                controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch_dtype)
 
                 generator = torch.Generator(device).manual_seed(seed)
 
@@ -460,31 +382,13 @@ def infer(
                     generator=generator
                 ).images[0]
             else:
-                # Режим edge_detection ---------------------------------------------------------------------------------------------------------------------------        
-                # prompt =  "The smiling girl. Anime style. Best quality, high quality" # "the mona lisa"
-                # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
-
-                # seed = 8  # 1 8 12 14 18
-                # width = 512    
-                # height = 512
-                # num_inference_steps = 50
-                # guidance_scale = 7.5
-                # lora_scale = 0.7
-
-                # strength_cn = 0.2       # Коэфф. зашумления ControlNet
-                # control_strength = 0.8 # Сила влияния ControlNet
-
-                # use_control_net = True   # Параметр для включения ControlNet
-                # cn_source_image = load_image("edges_w.jpeg") # Исходное изображение ControlNet
-                # control_image = load_image("027_0_1.jpeg")   # Контрольное изображение ControlNet
-
-                # #control_mode = "edge_detection" # Режим работы ControlNet 
 
                 if control_mode == "edge_detection":     
 
                     print('control_mode = ', control_mode)
 
-                    controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16, use_safetensors=True)
+                    controlnet_model_path = "lllyasviel/sd-controlnet-canny"
+                    controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16, use_safetensors=True)
 
                     generator = torch.Generator(device).manual_seed(seed)
 
@@ -511,25 +415,6 @@ def infer(
                         generator=generator
                     ).images[0]
                 else:
-                    # Режим depth_map ---------------------------------------------------------------------------------------------------------------------------    
-                    # prompt = "lego batman and robin" #"Lego Harry Potter and Jean Granger" #"Harry Potter and Hagrid in the lego style" #"lego batman and robin"
-                    # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
-
-                    # seed = 8
-                    # width = 512
-                    # height = 512
-                    # num_inference_steps = 50
-                    # guidance_scale = 7.5
-                    # lora_scale = 0.7
-
-                    # strength_cn = 1.0       # Коэфф. зашумления ControlNet
-                    # control_strength = 0.0 # Сила влияния ControlNet
-
-                    # use_control_net = True   # Параметр для включения ControlNet
-                    # cn_source_image = load_image("edges_w.jpeg") # Исходное изображение ControlNet
-                    # control_image = load_image("014_3.jpeg")   # Контрольное изображение ControlNet
-
-                    # #control_mode = "depth_map" # Режим работы ControlNet 
 
                     if control_mode == "depth_map":     
 
@@ -538,7 +423,8 @@ def infer(
                         depth_estimator = pipeline("depth-estimation")
                         depth_map = get_depth_map(control_image, depth_estimator).unsqueeze(0).half().to(device)
 
-                        controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", torch_dtype=torch.float16, use_safetensors=True)
+                        controlnet_model_path = "lllyasviel/control_v11f1p_sd15_depth"
+                        controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch.float16, use_safetensors=True)
 
                         generator = torch.Generator(device).manual_seed(seed)
 
@@ -566,18 +452,10 @@ def infer(
                         ).images[0]
         else:
             # Генерация изображений с LORA без ControlNet и IP_Adapter ---------------------------------------------------------------------------------------------
-            # prompt = "A young man in anime style. The image is characterized by high definition and resolution. Handsome, thoughtful man, attentive eyes. The man is depicted in the foreground, close-up or in the middle. High-quality images of the face, eyes, nose, lips, hands and clothes. The background and background are blurred and indistinct. The play of light and shadow is visible on the face and clothes."
-            # negative_prompt = "Blurred details, low resolution, bad anatomy, no face visible, poor image of a man's face, poor quality, artifacts, black and white image."
-
-            # seed = 5
-            # width = 512
-            # height = 512
-            # num_inference_steps = 30
-            # guidance_scale = 7.5
-            # lora_scale = 0.7
 
             # Инициализация ControlNet
-            controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype)
+            controlnet_model_path = "lllyasviel/sd-controlnet-openpose"
+            controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch_dtype)
 
             generator = torch.Generator(device).manual_seed(seed)