checkpoint GFPGANS rollback

app.py

@@ -1,6 +1,3 @@
-import gradio as gr
-from gradio import themes
-from PIL import Image
 import numpy as np
 import cv2
 import torch
@@ -8,9 +5,11 @@ import albumentations as albu
 from pylab import imshow
 import matplotlib.pyplot as plt
 from diffusers import StableDiffusionInpaintPipeline
+from PIL import Image
 from iglovikov_helper_functions.utils.image_utils import load_rgb, pad, unpad
 from iglovikov_helper_functions.dl.pytorch.utils import tensor_from_rgb_image
-from cloths_segmentation.pre_trained_models import create_model 
+from cloths_segmentation.pre_trained_models import create_model
+import gradio as gr
 
 # Load Cloth Segmentation Model (Ensure this is available)
 try:
@@ -25,15 +24,6 @@ try:
 except Exception as e:
     raise RuntimeError(f"Error loading inpainting model: {e}")
 
-try:
-    from gfpgan import GFPGANer
-except ModuleNotFoundError:
-    import subprocess
-    subprocess.run(["pip", "install", "gfpgan"])
-
-# Initialize GFPGAN
-gfpgan = GFPGANer(model_path='https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth',upscale=1, device=torch.device('cpu'))
-
 
 def load_and_preprocess_image(image_path):
     image = load_rgb(image_path)
@@ -82,23 +72,26 @@ def image_segmentation_and_inpainting(image, prompt="Chinese Red and Golder Armo
         # Resize the output image to match the original image's dimensions
         output_image = resize_and_upscale(output_image, original_image.shape[1], original_image.shape[0])
 
-        # Apply GFPGAN
-        _, _, output = gfpgan.enhance(np.array(output_image), has_aligned=False, only_center_face=False, paste_back=True)
-        enhanced_image = Image.fromarray(output)
-
-        return output_image, enhanced_image  # Return both images
-
+        return output_image
     except Exception as e:
         raise gr.Error(f"Error processing image: {e}")
 
 
-with gr.Blocks(
-    title="Cloth Image Segmentation and Inpainting",
-    theme=themes.Soft(primary_hue="blue", secondary_hue="blue"),
-) as demo:
+
+with gr.Blocks() as demo:
     with gr.Row():
         # Header with Image and Description
-        gr.HTML(            """            <div style="display: flex; align-items: center;">                <img src="https://ant.dpu.ac.th/wp-content/uploads/2024/04/dpulogo.png" style="width: 100px; margin-right: 20px;">                <div>                    <h1>Cloth Image Segmentation and Inpainting</h1>                    <p>This research project explores cloth segmentation using a specialized library, followed by inpainting with Stable Diffusion using a new prompt. It is conducted by the College of Creative Design and Entertainment Technology, Dhurakij Pundit University, in the lab of Asst. Prof. Banyapon Poolsawas under the MIT License.</p>                </div>            </div>            """        )
+        gr.HTML(
+            """
+            <div style="display: flex; align-items: center;">
+                <img src="https://ant.dpu.ac.th/wp-content/uploads/2024/04/dpulogo.png" style="width: 100px; margin-right: 20px;">
+                <div>
+                    <h1>Cloth Image Segmentation and Inpainting</h1>
+                    <p>This research project explores cloth segmentation using a specialized library, followed by inpainting with Stable Diffusion using a new prompt. It is conducted by the College of Creative Design and Entertainment Technology, Dhurakij Pundit University, in the lab of Asst. Prof. Banyapon Poolsawas under the MIT License.</p>
+                </div>
+            </div>
+            """
+        )
 
     with gr.Row():
         with gr.Column():
@@ -107,12 +100,7 @@ with gr.Blocks(
             run_button = gr.Button("Run")
         with gr.Column():
             image_output = gr.Image(label="Result")
-            enhanced_image_output = gr.Image(label="Enhanced Result")  # Output for enhanced image
 
-    run_button.click(
-        fn=image_segmentation_and_inpainting,
-        inputs=[image_input, prompt_input],
-        outputs=[image_output, enhanced_image_output]  # Update outputs
-    )
+    run_button.click(fn=image_segmentation_and_inpainting, inputs=[image_input, prompt_input], outputs=image_output)
 
 demo.launch(share=True)