Update app.py

app.py

@@ -1,5 +1,4 @@
 import os
-
 import cv2
 import gradio as gr
 import torch
@@ -7,35 +6,24 @@ from basicsr.archs.srvgg_arch import SRVGGNetCompact
 from gfpgan.utils import GFPGANer
 from realesrgan.utils import RealESRGANer
 
-os.system("pip freeze")
-# download weights
-if not os.path.exists('realesr-general-x4v3.pth'):
-    os.system("wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P .")
-if not os.path.exists('GFPGANv1.2.pth'):
-    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.2.pth -P .")
-if not os.path.exists('GFPGANv1.3.pth'):
-    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P .")
-if not os.path.exists('GFPGANv1.4.pth'):
-    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P .")
-if not os.path.exists('RestoreFormer.pth'):
-    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/RestoreFormer.pth -P .")
-if not os.path.exists('CodeFormer.pth'):
-    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/CodeFormer.pth -P .")
-
-torch.hub.download_url_to_file(
-    'https://thumbs.dreamstime.com/b/tower-bridge-traditional-red-bus-black-white-colors-view-to-tower-bridge-london-black-white-colors-108478942.jpg',
-    'a1.jpg')
-torch.hub.download_url_to_file(
-    'https://media.istockphoto.com/id/523514029/photo/london-skyline-b-w.jpg?s=612x612&w=0&k=20&c=kJS1BAtfqYeUDaORupj0sBPc1hpzJhBUUqEFfRnHzZ0=',
-    'a2.jpg')
-torch.hub.download_url_to_file(
-    'https://i.guim.co.uk/img/media/06f614065ed82ca0e917b149a32493c791619854/0_0_3648_2789/master/3648.jpg?width=700&quality=85&auto=format&fit=max&s=05764b507c18a38590090d987c8b6202',
-    'a3.jpg')
-torch.hub.download_url_to_file(
-    'https://i.pinimg.com/736x/46/96/9e/46969eb94aec2437323464804d27706d--victorian-london-victorian-era.jpg',
-    'a4.jpg')
-
-# background enhancer with RealESRGAN
+# Ensure numpy is compatible
+os.system("pip install --upgrade 'numpy<2'")
+
+# Download necessary model weights
+weights = {
+    "realesr-general-x4v3.pth": "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth",
+    "GFPGANv1.2.pth": "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.2.pth",
+    "GFPGANv1.3.pth": "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth",
+    "GFPGANv1.4.pth": "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth",
+    "RestoreFormer.pth": "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/RestoreFormer.pth",
+    "CodeFormer.pth": "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/CodeFormer.pth",
+}
+
+for file, url in weights.items():
+    if not os.path.exists(file):
+        os.system(f"wget {url} -P .")
+
+# Load ESRGAN model
 model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
 model_path = 'realesr-general-x4v3.pth'
 half = True if torch.cuda.is_available() else False
@@ -43,100 +31,91 @@ upsampler = RealESRGANer(scale=4, model_path=model_path, model=model, tile=0, ti
 
 os.makedirs('output', exist_ok=True)
 
-
-# def inference(img, version, scale, weight):
+# Image Processing Function
 def inference(img, version, scale):
-    # weight /= 100
-    print(img, version, scale)
     try:
-        extension = os.path.splitext(os.path.basename(str(img)))[1]
-        img = cv2.imread(img, cv2.IMREAD_UNCHANGED)
+        img_path = str(img)
+        extension = os.path.splitext(os.path.basename(img_path))[1]
+        img = cv2.imread(img_path, cv2.IMREAD_UNCHANGED)
+
         if len(img.shape) == 3 and img.shape[2] == 4:
             img_mode = 'RGBA'
-        elif len(img.shape) == 2:  # for gray inputs
+        elif len(img.shape) == 2:
             img_mode = None
             img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
         else:
             img_mode = None
 
-        h, w = img.shape[0:2]
+        h, w = img.shape[:2]
         if h < 300:
             img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)
 
-        if version == 'v1.2':
-            face_enhancer = GFPGANer(
-            model_path='GFPGANv1.2.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
-        elif version == 'v1.3':
-            face_enhancer = GFPGANer(
-            model_path='GFPGANv1.3.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
-        elif version == 'v1.4':
-            face_enhancer = GFPGANer(
-            model_path='GFPGANv1.4.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
-        elif version == 'RestoreFormer':
-            face_enhancer = GFPGANer(
-            model_path='RestoreFormer.pth', upscale=2, arch='RestoreFormer', channel_multiplier=2, bg_upsampler=upsampler)
-        elif version == 'CodeFormer':
-             face_enhancer = GFPGANer(
-             model_path='CodeFormer.pth', upscale=2, arch='CodeFormer', channel_multiplier=2, bg_upsampler=upsampler)
-        elif version == 'RealESR-General-x4v3':
-             face_enhancer = GFPGANer(
-             model_path='realesr-general-x4v3.pth', upscale=2, arch='realesr-general', channel_multiplier=2, bg_upsampler=upsampler)
-
-        try:
-            # _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True, weight=weight)
-            _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
-        except RuntimeError as error:
-            print('Error', error)
-
-        try:
-            if scale != 2:
-                interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
-                h, w = img.shape[0:2]
-                output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
-        except Exception as error:
-            print('wrong scale input.', error)
-        if img_mode == 'RGBA':  # RGBA images should be saved in png format
+        # Load Face Enhancement Model
+        model_paths = {
+            'v1.2': 'GFPGANv1.2.pth',
+            'v1.3': 'GFPGANv1.3.pth',
+            'v1.4': 'GFPGANv1.4.pth',
+            'RestoreFormer': 'RestoreFormer.pth',
+            'CodeFormer': 'CodeFormer.pth',
+            'RealESR-General-x4v3': 'realesr-general-x4v3.pth'
+        }
+
+        face_enhancer = GFPGANer(
+            model_path=model_paths[version],
+            upscale=2,
+            arch='clean' if version.startswith('v1') else version,
+            channel_multiplier=2,
+            bg_upsampler=upsampler
+        )
+
+        _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
+
+        if scale != 2:
+            interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
+            h, w = img.shape[:2]
+            output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
+
+        if img_mode == 'RGBA':
             extension = 'png'
         else:
             extension = 'jpg'
+
         save_path = f'output/out.{extension}'
         cv2.imwrite(save_path, output)
-
         output = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
+
         return output, save_path
+
     except Exception as error:
-        print('global exception', error)
+        print("Error:", error)
         return None, None
 
+# Gradio Blocks UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 📸 Image Upscaling & Restoration")
+    gr.Markdown("### Enhance old or AI-generated images using GFPGAN & RealESRGAN")
+
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(type="filepath", label="Upload Image")
+            version_selector = gr.Radio(
+                ['v1.2', 'v1.3', 'v1.4', 'RestoreFormer', 'CodeFormer', 'RealESR-General-x4v3'],
+                label="Model Version",
+                value="v1.4"
+            )
+            scale_factor = gr.Number(value=2, label="Rescaling Factor")
+
+            enhance_button = gr.Button("Enhance Image 🚀")
+
+        with gr.Column():
+            output_image = gr.Image(type="numpy", label="Enhanced Output")
+            download_link = gr.File(label="Download Enhanced Image")
+
+    enhance_button.click(
+        fn=inference,
+        inputs=[image_input, version_selector, scale_factor],
+        outputs=[output_image, download_link]
+    )
 
-title = "Image Upscaling & Restoration(esp. Face) using GFPGAN Algorithm"
-description = r"""Gradio demo for <a href='https://github.com/TencentARC/GFPGAN' target='_blank'><b>GFPGAN: Towards Real-World Blind Face Restoration and Upscalling of the image with a Generative Facial Prior</b></a>.<br>
-Practically the algorithm is used to restore your **old photos** or improve **AI-generated faces**.<br>
-To use it, simply just upload the concerned image.<br>
-"""
-article = r"""
-[![download](https://img.shields.io/github/downloads/TencentARC/GFPGAN/total.svg)](https://github.com/TencentARC/GFPGAN/releases)
-[![GitHub Stars](https://img.shields.io/github/stars/TencentARC/GFPGAN?style=social)](https://github.com/TencentARC/GFPGAN)
-[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2101.04061)
-<center><img src='https://visitor-badge.glitch.me/badge?page_id=dj_face_restoration_GFPGAN' alt='visitor badge'></center>
-"""
-demo = gr.Interface(
-    inference, [
-        gr.inputs.Image(type="filepath", label="Input"),
-        # gr.inputs.Radio(['v1.2', 'v1.3', 'v1.4', 'RestoreFormer', 'CodeFormer'], type="value", default='v1.4', label='version'),
-        gr.inputs.Radio(['v1.2', 'v1.3', 'v1.4', 'RestoreFormer','CodeFormer','RealESR-General-x4v3'], type="value", default='v1.4', label='version'),
-        gr.inputs.Number(label="Rescaling factor", default=2),
-        # gr.Slider(0, 100, label='Weight, only for CodeFormer. 0 for better quality, 100 for better identity', default=50)
-    ], [
-        gr.outputs.Image(type="numpy", label="Output (The whole image)"),
-        gr.outputs.File(label="Download the output image")
-    ],
-    title=title,
-    description=description,
-    article=article,
-    # examples=[['AI-generate.jpg', 'v1.4', 2, 50], ['lincoln.jpg', 'v1.4', 2, 50], ['Blake_Lively.jpg', 'v1.4', 2, 50],
-    #           ['10045.png', 'v1.4', 2, 50]]).launch()
-    examples=[['a1.jpg', 'v1.4', 2], ['a2.jpg', 'v1.4', 2], ['a3.jpg', 'v1.4', 2],['a4.jpg', 'v1.4', 2]])
-    
-demo.queue(concurrency_count=4)
-demo.launch()
+# Launch the App
+demo.launch()