Update app.py

app.py

@@ -1,10 +1,9 @@
-# app.py 07.02.25
-
 import gradio as gr
 import numpy as np
 import torch
-from diffusers import StableDiffusionPipeline
+from diffusers import StableDiffusionPipeline, ControlNetModel, StableDiffusionControlNetPipeline
 from peft import PeftModel, LoraConfig
+from controlnet_aux import OpenposeDetector
 import os
 
 MAX_SEED = np.iinfo(np.int32).max
@@ -14,13 +13,16 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model_default = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
+# Инициализация ControlNet и OpenposeDetector
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-openpose", torch_dtype=torch_dtype)
+openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
+
 def get_lora_sd_pipeline(
     lora_dir='./lora_man_animestyle',
     base_model_name_or_path=None, 
     dtype=torch.float16, 
     adapter_name="default"
-    ):
-
+):
     unet_sub_dir = os.path.join(lora_dir, "unet")
     text_encoder_sub_dir = os.path.join(lora_dir, "text_encoder")
     
@@ -59,6 +61,11 @@ def align_embeddings(prompt_embeds, negative_prompt_embeds):
            torch.nn.functional.pad(negative_prompt_embeds, (0, 0, 0, max_length - negative_prompt_embeds.shape[1]))
 
 pipe_default = get_lora_sd_pipeline(lora_dir='./lora_man_animestyle', base_model_name_or_path=model_default, dtype=torch_dtype).to(device)
+pipe_controlnet = StableDiffusionControlNetPipeline.from_pretrained(
+    model_default,
+    controlnet=controlnet,
+    torch_dtype=torch_dtype
+).to(device)
 
 def infer(
     prompt, 
@@ -70,34 +77,54 @@ def infer(
     seed=4, 
     guidance_scale=7.5, 
     lora_scale=0.5,
+    use_control_net=False,  # Параметр для включения ControlNet
+    control_strength=0.5,   # Сила влияния ControlNet
+    control_image=None,     # Контрольное изображение
     progress=gr.Progress(track_tqdm=True)
-    ):
-    
+):
     generator = torch.Generator(device).manual_seed(seed)
     
-    if model != model_default:
-        pipe = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype).to(device)
-        prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
-        negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
-        prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
+    if use_control_net and control_image is not None:
+        # Используем ControlNet
+        pose_image = openpose(control_image)
+        image = pipe_controlnet(
+            prompt=prompt,
+            negative_prompt=negative_prompt,
+            image=pose_image,
+            width=width,
+            height=height,
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+            controlnet_conditioning_scale=control_strength,
+            generator=generator
+        ).images[0]
     else:
-        pipe = pipe_default
-        prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
-        negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
-        prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
-        pipe.fuse_lora(lora_scale=lora_scale) # Коэфф. добавления lora
-    
-    params = {
-        'prompt_embeds': prompt_embeds,
-        'negative_prompt_embeds': negative_prompt_embeds,
-        'guidance_scale': guidance_scale,
-        'num_inference_steps': num_inference_steps,
-        'width': width,
-        'height': height,
-        'generator': generator,
-    }
+        # Стандартная генерация без ControlNet
+        if model != model_default:
+            pipe = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype).to(device)
+            prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
+            negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
+            prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
+        else:
+            pipe = pipe_default
+            prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
+            negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
+            prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
+            pipe.fuse_lora(lora_scale=lora_scale)
+        
+        params = {
+            'prompt_embeds': prompt_embeds,
+            'negative_prompt_embeds': negative_prompt_embeds,
+            'guidance_scale': guidance_scale,
+            'num_inference_steps': num_inference_steps,
+            'width': width,
+            'height': height,
+            'generator': generator,
+        }
+        
+        image = pipe(**params).images[0]
     
-    return pipe(**params).images[0]
+    return image
 
 examples = [
     "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.",
@@ -198,27 +225,14 @@ with gr.Blocks(css=css) as demo:
                     value=512,
                 )
 
-        # Функция для работы с ControlNet ---------------------------------------------------------------------
-        def process_input_ControlNet(image, use_control_net, control_strength, control_mode):
-            if use_control_net:
-                # Логика для обработки с использованием ControlNet
-                result = f"ControlNet активен! Режим: {control_mode}, Интенсивность: {control_strength}"
-            else:
-                # Логика для обработки без ControlNet
-                result = "ControlNet отключен."
-            return result
-
         with gr.Blocks():
             with gr.Row():
-                # Чекбокс для включения/отключения ControlNet
                 use_control_net = gr.Checkbox(
                     label="Use ControlNet",
                     value=False,
                 )
 
-            # Дополнительные опции для ControlNet
             with gr.Column(visible=False) as control_net_options:    
-                # Слайдер для настройки интенсивности
                 control_strength = gr.Slider(
                     label="Control Strength",
                     minimum=0.0,
@@ -227,59 +241,28 @@ with gr.Blocks(css=css) as demo:
                     step=0.05,
                 )
         
-                # Выпадающий список для выбора режима
                 control_mode = gr.Dropdown(
                     label="Control Mode",
                     choices=[
-                        "edge_detection",
-                        "canny_edge_detection",
                         "pose_estimation",
-                        "depth_map",
-                        "segmentation_map",
-                        "scribble_sketch",
-                        "normal_map",
-                        "hed_edge_detection",
-                        "openpose",
-                        "mlsd_line_detection",
-                        "scribble_diffusion",
-                        "semantic_segmentation",
-                        "style_transfer",
-                        "colorization",
-                        "custom_map"
                     ],
                     value="pose_estimation",
                 )
         
-                # Окно для загрузки изображений
                 control_image = gr.Image(label="Upload Control Image")
 
-                # Кнопка для запуска работы ControlNet
-                run_button = gr.Button("Run")
-
-                # Текстовое поле для вывода результата
-                output = gr.Textbox(label="Output")
-
-            # Логика для отображения/скрытия дополнительных опций
             use_control_net.change(
                 fn=lambda x: gr.Row.update(visible=x),
                 inputs=use_control_net,
                 outputs=control_net_options,
             )
 
-            # Привязка кнопки Run к функции работы с ControlNet
-            run_button.click(
-                fn=process_input_ControlNet,
-                inputs=[control_image, use_control_net, control_strength, control_mode],
-                outputs=output,
-            )
-
         gr.Examples(examples=examples, inputs=[prompt])
         gr.Examples(examples=examples_negative, inputs=[negative_prompt])
         
         run_button = gr.Button("Run", scale=1, variant="primary")
         result = gr.Image(label="Result", show_label=False)   
     
-
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn=infer,
@@ -293,10 +276,12 @@ with gr.Blocks(css=css) as demo:
             seed,
             guidance_scale,
             lora_scale,
+            use_control_net,  # Добавляем чекбокс для ControlNet
+            control_strength,  # Добавляем контроль силы
+            control_image,     # Добавляем контрольное изображение
         ],
         outputs=[result],
     )
 
 if __name__ == "__main__":
     demo.launch()
-