Updated app.py

Add multiple images in inference and download zip file

app.py

@@ -1,150 +1,133 @@
 import os
-
+import uuid
+import zipfile
 import cv2
 import gradio as gr
 import torch
+import numpy as np
 from basicsr.archs.srvgg_arch import SRVGGNetCompact
 from gfpgan.utils import GFPGANer
 from realesrgan.utils import RealESRGANer
 
-os.system("pip freeze")
-# download weights
+# ——— download weights if missing ———
 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://upload.wikimedia.org/wikipedia/commons/thumb/a/ab/Abraham_Lincoln_O-77_matte_collodion_print.jpg/1024px-Abraham_Lincoln_O-77_matte_collodion_print.jpg',
-    'lincoln.jpg')
-torch.hub.download_url_to_file(
-    'https://user-images.githubusercontent.com/17445847/187400315-87a90ac9-d231-45d6-b377-38702bd1838f.jpg',
-    'AI-generate.jpg')
-torch.hub.download_url_to_file(
-    'https://user-images.githubusercontent.com/17445847/187400981-8a58f7a4-ef61-42d9-af80-bc6234cef860.jpg',
-    'Blake_Lively.jpg')
-torch.hub.download_url_to_file(
-    'https://user-images.githubusercontent.com/17445847/187401133-8a3bf269-5b4d-4432-b2f0-6d26ee1d3307.png',
-    '10045.png')
-
-# background enhancer with RealESRGAN
+for fname, url in [
+    ('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'),
+]:
+    if not os.path.exists(fname):
+        os.system(f"wget {url} -P .")
+
+# ——— background upsampler ———
 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
-upsampler = RealESRGANer(scale=4, model_path=model_path, model=model, tile=0, tile_pad=10, pre_pad=0, half=half)
+upsampler = RealESRGANer(
+    scale=4, model_path='realesr-general-x4v3.pth', model=model,
+    tile=256, tile_pad=10, pre_pad=0,
+    half=torch.cuda.is_available()
+)
 
 os.makedirs('output', exist_ok=True)
 
+def process_single_image(img_path, version, scale):
+    img = cv2.imread(img_path, cv2.IMREAD_UNCHANGED)
+    if img is None:
+        return None
+
+    # handle alpha & grayscale
+    img_mode = 'RGBA' if (img.ndim==3 and img.shape[2]==4) else None
+    if img.ndim == 2:
+        img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+
+    h, w = img.shape[:2]
+
+    # robust resize
+    min_size, max_size = 512, 2048
+    if max(h, w) < min_size:
+        scale_factor = min_size / max(h, w)
+        img = cv2.resize(img, (int(w * scale_factor), int(h * scale_factor)))
+    elif max(h, w) > max_size:
+        scale_factor = max_size / max(h, w)
+        img = cv2.resize(img, (int(w * scale_factor), int(h * scale_factor)))
+
+    # map version → filename & arch
+    if version.startswith('v'):
+        model_fname = f'GFPGAN{version}.pth'
+        arch = 'clean'
+    else:
+        model_fname = f'{version}.pth'
+        arch = version
+
+    face_enhancer = GFPGANer(
+        model_path=model_fname,
+        upscale=2,
+        arch=arch,
+        channel_multiplier=2,
+        bg_upsampler=upsampler
+    )
 
-# def inference(img, version, scale, weight):
-def inference(img, version, scale):
-    # weight /= 100
-    print(img, version, scale)
-    if scale > 4:
-        scale = 4  # avoid too large scale value
     try:
-        extension = os.path.splitext(os.path.basename(str(img)))[1]
-        img = cv2.imread(img, cv2.IMREAD_UNCHANGED)
-        if len(img.shape) == 3 and img.shape[2] == 4:
-            img_mode = 'RGBA'
-        elif len(img.shape) == 2:  # for gray inputs
-            img_mode = None
-            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
-        else:
-            img_mode = None
-
-        h, w = img.shape[0:2]
-        if h > 3500 or w > 3500:
-            print('too large size')
-            return None, None
-        
-        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)
-
-        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
-            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)
-        return None, None
-
-
-title = "GFPGAN: Practical Face Restoration Algorithm"
-description = r"""Gradio demo for <a href='https://github.com/TencentARC/GFPGAN' target='_blank'><b>GFPGAN: Towards Real-World Blind Face Restoration with Generative Facial Prior</b></a>.<br>
-It can be used to restore your **old photos** or improve **AI-generated faces**.<br>
-To use it, simply upload your image.<br>
-If GFPGAN is helpful, please help to ⭐ the <a href='https://github.com/TencentARC/GFPGAN' target='_blank'>Github Repo</a> and recommend it to your friends 😊
-"""
-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)
-
-If you have any question, please email 📧 `[email protected]` or `[email protected]`.
-
-<center><img src='https://visitor-badge.glitch.me/badge?page_id=akhaliq_GFPGAN' alt='visitor badge'></center>
-<center><img src='https://visitor-badge.glitch.me/badge?page_id=Gradio_Xintao_GFPGAN' alt='visitor badge'></center>
-"""
+        _, _, restored = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
+    except RuntimeError as e:
+        print("GFPGAN error:", e)
+        return None
+
+    if restored is None:
+        print(f"Restoration failed for {img_path}")
+        return None
+
+    # sanitize output to avoid black rectangles
+    restored = np.nan_to_num(restored, nan=0.0, posinf=255.0, neginf=0.0)
+    restored = np.clip(restored, 0, 255).astype(np.uint8)
+
+    # rescale if needed
+    if scale != 2:
+        interp = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
+        h, w = img.shape[:2]
+        restored = cv2.resize(restored, (int(w * scale / 2), int(h * scale / 2)), interpolation=interp)
+
+    ext = 'png' if img_mode == 'RGBA' else 'jpg'
+    base = os.path.basename(img_path).rsplit('.', 1)[0]
+    out_path = os.path.join('output', f"{base}_restored.{ext}")
+    cv2.imwrite(out_path, restored)
+    return out_path
+
+def inference(img_files, version, scale):
+    """
+    img_files: list of file objects or paths
+    returns: path to a ZIP archive containing all restored images
+    """
+    saved = []
+    for p in img_files or []:
+        img_path = p.name if hasattr(p, 'name') else p
+        out = process_single_image(img_path, version, scale)
+        if out:
+            saved.append(out)
+
+    zip_name = f"output/restored_{uuid.uuid4().hex}.zip"
+    with zipfile.ZipFile(zip_name, 'w') as z:
+        for fpath in saved:
+            z.write(fpath, arcname=os.path.basename(fpath))
+
+    return zip_name
+
+# ——— Gradio interface ———
+title = "GFPGAN Multi‑Image Face Restoration + ZIP Download"
+description = "Upload multiple images; restored outputs will be bundled into a ZIP for download."
+
 demo = gr.Interface(
-    inference, [
-        gr.Image(type="filepath", label="Input"),
-        # gr.Radio(['v1.2', 'v1.3', 'v1.4', 'RestoreFormer', 'CodeFormer'], type="value", value='v1.4', label='version'),
-        gr.Radio(['v1.2', 'v1.3', 'v1.4', 'RestoreFormer'], type="value", value='v1.4', label='version'),
-        gr.Number(label="Rescaling factor", value=2),
-        # gr.Slider(0, 100, label='Weight, only for CodeFormer. 0 for better quality, 100 for better identity', value=50)
-    ], [
-        gr.Image(type="numpy", label="Output (The whole image)"),
-        gr.File(label="Download the output image")
+    fn=inference,
+    inputs=[
+        gr.File(file_count="multiple", file_types=["image"], label="Input Images"),
+        gr.Radio(['v1.2', 'v1.3', 'v1.4', 'RestoreFormer'], value='v1.4', label='GFPGAN Version'),
+        gr.Number(label="Rescaling Factor", value=2)
     ],
+    outputs=gr.File(label="Download Restored ZIP"),
     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=[['AI-generate.jpg', 'v1.4', 2], ['lincoln.jpg', 'v1.4', 2], ['Blake_Lively.jpg', 'v1.4', 2],
-              ['10045.png', 'v1.4', 2]])
-demo.queue().launch()
+)
+
+if _name_ == "_main_":
+    demo.queue().launch(share=True)