Spaces:
Build error
Build error
Update app.py
Browse files
app.py
CHANGED
@@ -5,88 +5,120 @@ from RealESRGAN import RealESRGAN
|
|
5 |
import gradio as gr
|
6 |
import numpy as np
|
7 |
import tempfile
|
|
|
8 |
import os
|
9 |
|
10 |
# Set device to GPU if available, otherwise use CPU
|
11 |
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
12 |
|
13 |
-
# Load the
|
14 |
-
|
15 |
-
model =
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
-
# Load the Real-ESRGAN
|
18 |
-
model2 =
|
19 |
-
model4 =
|
20 |
-
model8 =
|
21 |
|
22 |
-
#
|
23 |
-
|
24 |
-
|
25 |
-
model8.load_weights('weights/RealESRGAN_x8.pth', download=True)
|
26 |
|
27 |
-
#
|
28 |
def enhance_image(image, scale):
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
-
#
|
39 |
def generate_caption(image):
|
40 |
inputs = processor(images=image, return_tensors="pt").to(device)
|
41 |
output_ids = model.generate(**inputs)
|
42 |
-
|
|
|
43 |
|
44 |
-
#
|
45 |
-
def muda_dpi(
|
46 |
-
|
47 |
-
|
|
|
|
|
|
|
|
|
48 |
|
49 |
-
#
|
50 |
-
def resize_image(
|
51 |
-
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
-
#
|
54 |
def process_images(image_files, enhance, scale, adjust_dpi, dpi, resize, width, height):
|
55 |
processed_images = []
|
56 |
file_paths = []
|
57 |
captions = []
|
58 |
|
59 |
for i, image_file in enumerate(image_files):
|
60 |
-
|
|
|
61 |
|
62 |
-
# Enhance resolution if required
|
63 |
if enhance:
|
64 |
-
|
65 |
|
66 |
-
# Adjust DPI if required
|
67 |
if adjust_dpi:
|
68 |
-
|
69 |
-
|
70 |
-
# Resize if required
|
71 |
if resize:
|
72 |
-
|
73 |
-
|
74 |
-
# Generate caption
|
75 |
-
caption = generate_caption(
|
76 |
captions.append(caption)
|
77 |
|
78 |
-
#
|
79 |
custom_filename = f"Image_Captioning_with_BLIP_{i+1}.jpg"
|
|
|
|
|
80 |
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.jpg')
|
81 |
-
|
|
|
|
|
82 |
final_path = temp_file.name.replace(temp_file.name.split('/')[-1], custom_filename)
|
83 |
os.rename(temp_file.name, final_path)
|
|
|
|
|
84 |
file_paths.append(final_path)
|
85 |
-
processed_images.append(image)
|
86 |
|
87 |
return processed_images, file_paths, captions
|
88 |
|
89 |
-
#
|
90 |
iface = gr.Interface(
|
91 |
fn=process_images,
|
92 |
inputs=[
|
@@ -104,10 +136,11 @@ iface = gr.Interface(
|
|
104 |
gr.Files(label="Download Final Images"),
|
105 |
gr.Textbox(label="Image Captions")
|
106 |
],
|
107 |
-
title="
|
108 |
description="Upload multiple images (.jpg, .png), enhance using AI, adjust DPI, resize, generate captions, and download the final results."
|
109 |
)
|
110 |
|
|
|
111 |
iface.launch(debug=True)
|
112 |
|
113 |
|
|
|
5 |
import gradio as gr
|
6 |
import numpy as np
|
7 |
import tempfile
|
8 |
+
import time
|
9 |
import os
|
10 |
|
11 |
# Set device to GPU if available, otherwise use CPU
|
12 |
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
13 |
|
14 |
+
# Load the Real-ESRGAN model with specified scale
|
15 |
+
def load_model(scale):
|
16 |
+
model = RealESRGAN(device, scale=scale)
|
17 |
+
weights_path = f'weights/RealESRGAN_x{scale}.pth'
|
18 |
+
try:
|
19 |
+
model.load_weights(weights_path, download=True)
|
20 |
+
print(f"Weights for scale {scale} loaded successfully.")
|
21 |
+
except Exception as e:
|
22 |
+
print(f"Error loading weights for scale {scale}: {e}")
|
23 |
+
model.load_weights(weights_path, download=False)
|
24 |
+
return model
|
25 |
|
26 |
+
# Load different scales of the Real-ESRGAN model
|
27 |
+
model2 = load_model(2)
|
28 |
+
model4 = load_model(4)
|
29 |
+
model8 = load_model(8)
|
30 |
|
31 |
+
# Initialize BLIP processor and model for image captioning
|
32 |
+
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
|
33 |
+
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
|
|
|
34 |
|
35 |
+
# Enhance the image using the specified scale
|
36 |
def enhance_image(image, scale):
|
37 |
+
try:
|
38 |
+
print(f"Enhancing image with scale {scale}...")
|
39 |
+
start_time = time.time()
|
40 |
+
image_np = np.array(image.convert('RGB'))
|
41 |
+
print(f"Image converted to numpy array: shape {image_np.shape}, dtype {image_np.dtype}")
|
42 |
+
|
43 |
+
if scale == '2x':
|
44 |
+
result = model2.predict(image_np)
|
45 |
+
elif scale == '4x':
|
46 |
+
result = model4.predict(image_np)
|
47 |
+
else:
|
48 |
+
result = model8.predict(image_np)
|
49 |
+
|
50 |
+
enhanced_image = Image.fromarray(np.uint8(result))
|
51 |
+
print(f"Image enhanced in {time.time() - start_time:.2f} seconds")
|
52 |
+
return enhanced_image
|
53 |
+
except Exception as e:
|
54 |
+
print(f"Error enhancing image: {e}")
|
55 |
+
return image
|
56 |
|
57 |
+
# Generate captions for the images using BLIP
|
58 |
def generate_caption(image):
|
59 |
inputs = processor(images=image, return_tensors="pt").to(device)
|
60 |
output_ids = model.generate(**inputs)
|
61 |
+
caption = processor.decode(output_ids[0], skip_special_tokens=True)
|
62 |
+
return caption
|
63 |
|
64 |
+
# Adjust the DPI of the image
|
65 |
+
def muda_dpi(input_image, dpi):
|
66 |
+
dpi_tuple = (dpi, dpi)
|
67 |
+
image = Image.fromarray(input_image.astype('uint8'), 'RGB')
|
68 |
+
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.jpg')
|
69 |
+
image.save(temp_file, format='JPEG', dpi=dpi_tuple)
|
70 |
+
temp_file.close()
|
71 |
+
return Image.open(temp_file.name)
|
72 |
|
73 |
+
# Resize the image to the specified width and height
|
74 |
+
def resize_image(input_image, width, height):
|
75 |
+
image = Image.fromarray(input_image.astype('uint8'), 'RGB')
|
76 |
+
resized_image = image.resize((width, height))
|
77 |
+
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.jpg')
|
78 |
+
resized_image.save(temp_file, format='JPEG')
|
79 |
+
temp_file.close()
|
80 |
+
return Image.open(temp_file.name)
|
81 |
|
82 |
+
# Process the images: enhance, adjust DPI, resize, caption, and save
|
83 |
def process_images(image_files, enhance, scale, adjust_dpi, dpi, resize, width, height):
|
84 |
processed_images = []
|
85 |
file_paths = []
|
86 |
captions = []
|
87 |
|
88 |
for i, image_file in enumerate(image_files):
|
89 |
+
input_image = np.array(Image.open(image_file).convert('RGB'))
|
90 |
+
original_image = Image.fromarray(input_image.astype('uint8'), 'RGB')
|
91 |
|
|
|
92 |
if enhance:
|
93 |
+
original_image = enhance_image(original_image, scale)
|
94 |
|
|
|
95 |
if adjust_dpi:
|
96 |
+
original_image = muda_dpi(np.array(original_image), dpi)
|
97 |
+
|
|
|
98 |
if resize:
|
99 |
+
original_image = resize_image(np.array(original_image), width, height)
|
100 |
+
|
101 |
+
# Generate a caption for the image
|
102 |
+
caption = generate_caption(original_image)
|
103 |
captions.append(caption)
|
104 |
|
105 |
+
# Create a custom filename
|
106 |
custom_filename = f"Image_Captioning_with_BLIP_{i+1}.jpg"
|
107 |
+
|
108 |
+
# Save the image with the custom filename
|
109 |
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.jpg')
|
110 |
+
original_image.save(temp_file.name, format='JPEG')
|
111 |
+
|
112 |
+
# Rename the file with the custom name
|
113 |
final_path = temp_file.name.replace(temp_file.name.split('/')[-1], custom_filename)
|
114 |
os.rename(temp_file.name, final_path)
|
115 |
+
|
116 |
+
processed_images.append(original_image)
|
117 |
file_paths.append(final_path)
|
|
|
118 |
|
119 |
return processed_images, file_paths, captions
|
120 |
|
121 |
+
# Gradio interface setup
|
122 |
iface = gr.Interface(
|
123 |
fn=process_images,
|
124 |
inputs=[
|
|
|
136 |
gr.Files(label="Download Final Images"),
|
137 |
gr.Textbox(label="Image Captions")
|
138 |
],
|
139 |
+
title="Multi-Image Enhancer with Captioning",
|
140 |
description="Upload multiple images (.jpg, .png), enhance using AI, adjust DPI, resize, generate captions, and download the final results."
|
141 |
)
|
142 |
|
143 |
+
# Launch the Gradio interface
|
144 |
iface.launch(debug=True)
|
145 |
|
146 |
|