Update app.py

app.py

@@ -135,17 +135,14 @@ lazy_realesrgan_x2 = LazyRealESRGAN(device, scale=2)
 lazy_realesrgan_x4 = LazyRealESRGAN(device, scale=4)
 
 @timer_func
-def resize_and_upscale(input_image, scale_factor):
+def resize_and_upscale(input_image, resolution):
+    scale = 2 if resolution <= 2048 else 4
     input_image = input_image.convert("RGB")
     W, H = input_image.size
-    target_size = int(min(H, W) * scale_factor)
-    scale = 2 if target_size <= 2048 else 4
-    
-    k = float(target_size) / min(H, W)
+    k = float(resolution) / min(H, W)
     H = int(round(H * k / 64.0)) * 64
     W = int(round(W * k / 64.0)) * 64
     img = input_image.resize((W, H), resample=Image.LANCZOS)
-    
     if scale == 2:
         img = lazy_realesrgan_x2.predict(img)
     else:
@@ -169,18 +166,18 @@ def create_hdr_effect(original_image, hdr):
 lazy_pipe = LazyLoadPipeline()
 lazy_pipe.load()
 
-def prepare_image(input_image, scale_factor, hdr):
-    condition_image = resize_and_upscale(input_image, scale_factor)
+def prepare_image(input_image, resolution, hdr):
+    condition_image = resize_and_upscale(input_image, resolution)
     condition_image = create_hdr_effect(condition_image, hdr)
     return condition_image
 
 @spaces.GPU
 @timer_func
-def gradio_process_image(input_image, scale_factor, num_inference_steps, strength, hdr, guidance_scale):
+def gradio_process_image(input_image, resolution, num_inference_steps, strength, hdr, guidance_scale):
     print("Starting image processing...")
     torch.cuda.empty_cache()
     
-    condition_image = prepare_image(input_image, scale_factor, hdr)
+    condition_image = prepare_image(input_image, resolution, hdr)
     
     prompt = "masterpiece, best quality, highres"
     negative_prompt = "low quality, normal quality, ugly, blurry, blur, lowres, bad anatomy, bad hands, cropped, worst quality, verybadimagenegative_v1.3, JuggernautNegative-neg"
@@ -225,24 +222,24 @@ with gr.Blocks() as demo:
         with gr.Column():
             output_slider = ImageSlider(label="Before / After", type="numpy")
     with gr.Accordion("Advanced Options", open=False):
-        scale_factor = gr.Slider(minimum=1, maximum=4, value=2, step=0.1, label="Upscale Factor")
+        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")
 
     run_button.click(fn=gradio_process_image, 
-                     inputs=[input_image, scale_factor, num_inference_steps, strength, hdr, guidance_scale],
+                     inputs=[input_image, resolution, num_inference_steps, strength, hdr, guidance_scale],
                      outputs=output_slider)
 
     # Add examples with all required inputs
     gr.Examples(
         examples=[
-            ["image1.jpg", 2, 20, 0.4, 0, 3],
-            ["image2.png", 16, 20, 0.4, 0, 3],
-            ["image3.png", 2, 20, 0.4, 0, 3],
+            ["image1.jpg", 512, 20, 0.4, 0, 3],
+            ["image2.png", 512, 20, 0.4, 0, 3],
+            ["image3.png", 512, 20, 0.4, 0, 3],
         ],
-        inputs=[input_image, scale_factor, num_inference_steps, strength, hdr, guidance_scale],
+        inputs=[input_image, resolution, num_inference_steps, strength, hdr, guidance_scale],
         outputs=output_slider,
         fn=gradio_process_image,
         cache_examples=True,