Upload giga_App.py

giga_App.py

@@ -6,8 +6,16 @@ import torch
 import os
 import time
 from pathlib import Path
+import platform
 import argparse
 
+def open_folder():
+    open_folder_path = os.path.abspath("outputs")
+    if platform.system() == "Windows":
+        os.startfile(open_folder_path)
+    elif platform.system() == "Linux":
+        os.system(f'xdg-open "{open_folder_path}"')
+
 # Force CPU usage
 torch.set_default_tensor_type(torch.FloatTensor)
 
@@ -21,21 +29,29 @@ aura_sr = AuraSR.from_pretrained("fal/AuraSR-v2")
 # Restore original torch.load
 torch.load = original_load
 
-def process_single_image(input_image_path):
+def process_single_image(input_image_path, reduce_seams):
     if input_image_path is None:
         raise gr.Error("Please provide an image to upscale.")
 
-    # Load the image
+    # Send an initial progress update.
+    yield [[], "Starting upscaling..."]
+
+    # Load the image.
     pil_image = Image.open(input_image_path)
 
-    # Upscale the image using AuraSR
+    # Upscale using the chosen method.
     start_time = time.time()
-    upscaled_image = aura_sr.upscale_4x(pil_image)
+    if reduce_seams:
+        # Using upscale_4x_overlapped to reduce seam artifacts.
+        print("using reduce seams")
+        upscaled_image = aura_sr.upscale_4x_overlapped(pil_image)
+    else:
+        # Default upscaling method.
+        upscaled_image = aura_sr.upscale_4x(pil_image)
     processing_time = time.time() - start_time
-
     print(f"Processing time: {processing_time:.2f} seconds")
 
-    # Save the upscaled image
+    # Save the upscaled image.
     output_folder = "outputs"
     os.makedirs(output_folder, exist_ok=True)
     
@@ -50,9 +66,11 @@ def process_single_image(input_image_path):
     
     upscaled_image.save(output_path)
 
-    return [input_image_path, output_path]
+    # Send the final progress update along with the before/after gallery.
+    yield [[input_image_path, output_path],
+           f"Upscaling complete in {processing_time:.2f} seconds"]
 
-def process_batch(input_folder, output_folder=None):
+def process_batch(input_folder, output_folder=None, reduce_seams=False):
     if not input_folder:
         raise gr.Error("Please provide an input folder path.")
 
@@ -60,18 +78,24 @@ def process_batch(input_folder, output_folder=None):
         output_folder = "outputs"
 
     os.makedirs(output_folder, exist_ok=True)
-
-    input_files = [f for f in os.listdir(input_folder) if f.lower().endswith(('.png', '.jpg', '.jpeg', '.bmp', '.tiff'))]
+    input_files = [f for f in os.listdir(input_folder) if f.lower().endswith(
+        ('.png', '.jpg', '.jpeg', '.bmp', '.tiff'))]
     total_files = len(input_files)
     processed_files = 0
     results = []
 
+    # Initial progress update.
+    yield [results, "Starting batch processing..."]
+
     for filename in input_files:
         input_path = os.path.join(input_folder, filename)
         pil_image = Image.open(input_path)
 
         start_time = time.time()
-        upscaled_image = aura_sr.upscale_4x(pil_image)
+        if reduce_seams:
+            upscaled_image = aura_sr.upscale_4x_overlapped(pil_image)
+        else:
+            upscaled_image = aura_sr.upscale_4x(pil_image)
         processing_time = time.time() - start_time
 
         output_filename = os.path.splitext(filename)[0] + ".png"
@@ -85,17 +109,17 @@ def process_batch(input_folder, output_folder=None):
         upscaled_image.save(output_path)
 
         processed_files += 1
-        print(f"Processed {processed_files}/{total_files}: {filename} in {processing_time:.2f} seconds")
-        
         results.append(output_path)
+        # Yield progress update after processing each image.
+        yield [results, f"Processed {processed_files}/{total_files}: {filename} in {processing_time:.2f} seconds"]
 
-    print(f"Batch processing complete. {processed_files} images processed.")
-    return results
+    # Final update.
+    yield [results, f"Batch processing complete. {processed_files} images processed."]
 
-title = """<h1 align="center">AuraSR Giga Upscaler V1 by SECourses - Upscales to 4x</h1>
+title = """<h1 align="center">AuraSR Giga Upscaler V2 by SECourses - Upscales to 4x</h1>
 <p><center>AuraSR: new open source super-resolution upscaler based on GigaGAN. Works perfect on some images and fails on some images so give it a try</center></p>
 <p><center>Works very fast and very VRAM friendly</center></p>
-<h2 align="center">Latest version on : <a href="https://www.patreon.com/posts/110060645">https://www.patreon.com/posts/110060645</a></h1>
+<h2 align="center">Latest version on : <a href="https://www.patreon.com/posts/110060645">https://www.patreon.com/posts/110060645</a></h2>
 """
 
 def create_demo():
@@ -106,27 +130,43 @@ def create_demo():
             with gr.Row():
                 with gr.Column(scale=1):
                     input_image = gr.Image(label="Input Image", type="filepath")
+                    reduce_seams = gr.Checkbox(
+                        label="Reduce Seam Artifacts",
+                        value=False,
+                        info="upscale_4x upscales the image in tiles that do not overlap. This can result in seams. Use upscale_4x_overlapped to reduce seams. This will double the time upscaling by taking an additional pass and averaging the results."
+                    )
                     process_btn = gr.Button(value="Upscale Image", variant="primary")
                 with gr.Column(scale=1):
                     output_gallery = gr.Gallery(label="Before / After", columns=2)
+                    progress_text = gr.Markdown("Progress messages will appear here.")
+                    btn_open_outputs = gr.Button("Open Outputs Folder", variant="primary")
+                    btn_open_outputs.click(fn=open_folder)
 
+            # The function now yields two outputs: a gallery and a progress message.
             process_btn.click(
                 fn=process_single_image,
-                inputs=[input_image],
-                outputs=output_gallery
+                inputs=[input_image, reduce_seams],
+                outputs=[output_gallery, progress_text]
             )
 
         with gr.Tab("Batch Processing"):
             with gr.Row():
                 input_folder = gr.Textbox(label="Input Folder Path")
                 output_folder = gr.Textbox(label="Output Folder Path (Optional)")
+                reduce_seams_batch = gr.Checkbox(
+                    label="Reduce Seam Artifacts",
+                    value=False,
+                    info="upscale_4x upscales the image in tiles that do not overlap. This can result in seams. Use upscale_4x_overlapped to reduce seams. This will double the time upscaling by taking an additional pass and averaging the results."
+                )
             batch_process_btn = gr.Button(value="Process Batch", variant="primary")
-            output_gallery = gr.Gallery(label="Processed Images")
+            with gr.Column():
+                output_gallery_batch = gr.Gallery(label="Processed Images")
+                progress_text_batch = gr.Markdown("Progress messages will appear here.")
 
             batch_process_btn.click(
                 fn=process_batch,
-                inputs=[input_folder, output_folder],
-                outputs=output_gallery
+                inputs=[input_folder, output_folder, reduce_seams_batch],
+                outputs=[output_gallery_batch, progress_text_batch]
             )
 
     return demo