Update app.py

app.py

@@ -71,7 +71,7 @@ def download_models():
     for model, (url, folder, filename) in models.items():
         download_file(url, folder, filename)
 
-download_models()
+
 
 def timer_func(func):
     def wrapper(*args, **kwargs):
@@ -144,9 +144,6 @@ class LazyRealESRGAN:
         self.load_model()
         return self.model.predict(img)
 
-lazy_realesrgan_x2 = LazyRealESRGAN(device, scale=2)
-lazy_realesrgan_x4 = LazyRealESRGAN(device, scale=4)
-
 @timer_func
 def resize_and_upscale(input_image, resolution):
     scale = 2 if resolution <= 2048 else 4
@@ -176,8 +173,7 @@ def create_hdr_effect(original_image, hdr):
     hdr_image_8bit = np.clip(hdr_image * 255, 0, 255).astype('uint8')
     return Image.fromarray(cv2.cvtColor(hdr_image_8bit, cv2.COLOR_BGR2RGB))
 
-lazy_pipe = LazyLoadPipeline()
-lazy_pipe.load()
+
 
 def prepare_image(input_image, resolution, hdr):
     condition_image = resize_and_upscale(input_image, resolution)
@@ -453,59 +449,6 @@ class ControlNetDepthDesignModelMulti:
         return design_image
 
 
-def create_demo(model):
-    gr.Markdown("### Just try zeroGPU")
-    with gr.Row():
-        with gr.Column():
-            input_image = gr.Image(label="Input Image", type='pil', elem_id='img-display-input')
-            input_text = gr.Textbox(label='Prompt', placeholder='Please upload your image first', lines=2)
-            with gr.Accordion('Advanced options', open=False):
-                
-                num_steps = gr.Slider(label='Steps',
-                                      minimum=1,
-                                      maximum=50,
-                                      value=50,
-                                      step=1)
-                img_size = gr.Slider(label='Image size',
-                                      minimum=256,
-                                      maximum=768,
-                                      value=768,
-                                      step=64)
-                guidance_scale = gr.Slider(label='Guidance Scale',
-                                           minimum=0.1,
-                                           maximum=30.0,
-                                           value=10.0,
-                                           step=0.1)
-                seed = gr.Slider(label='Seed',
-                                 minimum=-1,
-                                 maximum=2147483647,
-                                 value=323*111,
-                                 step=1,
-                                 randomize=True)
-                strength = gr.Slider(label='Strength',
-                                           minimum=0.1,
-                                           maximum=1.0,
-                                           value=0.9,
-                                           step=0.1)
-                a_prompt = gr.Textbox(
-                    label='Added Prompt',
-                    value="interior design, 4K, high resolution, photorealistic")
-                n_prompt = gr.Textbox(
-                    label='Negative Prompt',
-                    value="window, door, low resolution, banner, logo, watermark, text, deformed, blurry, out of focus, surreal, ugly, beginner")
-
-                resolution = gr.Slider(minimum=256, maximum=2048, value=512, step=256, label="Resolution")
-                num_inference_steps = gr.Slider(minimum=1, maximum=50, value=20, step=1, label="Number of Inference Steps")
-                strength = gr.Slider(minimum=0, maximum=1, value=0.4, step=0.01, label="Strength")
-                hdr = gr.Slider(minimum=0, maximum=1, value=0, step=0.1, label="HDR Effect")
-                guidance_scale = gr.Slider(minimum=0, maximum=20, value=3, step=0.5, label="Guidance Scale")
-        
-            submit = gr.Button("Submit")
-        
-        with gr.Column():
-            design_image = gr.Image(label="Output Mask", elem_id='img-display-output')
-    
-    
     def on_submit(image, text, num_steps, guidance_scale, seed, strength, a_prompt, n_prompt, img_size):
         model.seed = seed
         model.neg_prompt = n_prompt
@@ -548,6 +491,13 @@ seg_image_processor, image_segmentor = get_segmentation_pipeline()
 depth_feature_extractor, depth_estimator = get_depth_pipeline()
 depth_estimator = depth_estimator.to(device)
 
+download_models()
+lazy_realesrgan_x2 = LazyRealESRGAN(device, scale=2)
+lazy_realesrgan_x4 = LazyRealESRGAN(device, scale=4)
+
+lazy_pipe = LazyLoadPipeline()
+lazy_pipe.load()
+
 
 
 def main():