Create app.py

app.py

@@ -0,0 +1,115 @@
+import os
+import cv2
+import numpy as np
+import onnxruntime as ort
+import gradio as gr
+import subprocess
+import shutil
+from huggingface_hub import hf_hub_download
+
+# --- AUTH & MODEL SETUP ---
+HF_TOKEN = os.getenv("HF_TOKEN")
+
+def get_onnx_model():
+    try:
+        model_path = hf_hub_download(
+            repo_id="KingPro100/real-esrgan-onxx", 
+            filename="Real-ESRGAN-x4plus.onnx", 
+            token=HF_TOKEN
+        )
+        return model_path
+    except Exception as e:
+        # Fallback to Xenova if the path is tricky
+        return hf_hub_download(repo_id="Xenova/realesrgan-x4plus", filename="onnx/model.onnx")
+
+MODEL_FILE = get_onnx_model()
+
+# CPU Stability Settings
+sess_options = ort.SessionOptions()
+sess_options.intra_op_num_threads = 2 
+session = ort.InferenceSession(MODEL_FILE, sess_options, providers=['CPUExecutionProvider'])
+
+def upscale_frame(frame):
+    img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+    img = img.astype(np.float32) / 255.0
+    img = np.transpose(img, (2, 0, 1))
+    img = np.expand_dims(img, axis=0)
+    
+    inputs = {session.get_inputs()[0].name: img}
+    output = session.run(None, inputs)[0]
+    
+    output = np.squeeze(output)
+    output = np.clip(output, 0, 1)
+    output = np.transpose(output, (1, 2, 0))
+    output = cv2.cvtColor((output * 255.0).astype(np.uint8), cv2.COLOR_RGB2BGR)
+    return output
+
+def process_video(input_path, do_sharpen, progress=gr.Progress()):
+    if not input_path: return None
+    
+    cap = cv2.VideoCapture(input_path)
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    
+    # 1. Extract Audio
+    audio_path = "temp_audio.mp3"
+    subprocess.run(f"ffmpeg -i {input_path} -vn -acodec libmp3lame {audio_path} -y", shell=True)
+
+    # 2. Setup Frames Dir
+    frames_dir = "temp_frames"
+    if os.path.exists(frames_dir): shutil.rmtree(frames_dir)
+    os.makedirs(frames_dir)
+
+    count = 0
+    while True:
+        ret, frame = cap.read()
+        if not ret: break
+        
+        try:
+            upscaled = upscale_frame(frame)
+            cv2.imwrite(f"{frames_dir}/frame_{count:05d}.png", upscaled)
+        except Exception as e:
+            # Fallback for individual frame failure
+            h, w = frame.shape[:2]
+            upscaled = cv2.resize(frame, (w*4, h*4), interpolation=cv2.INTER_LANCZOS4)
+            cv2.imwrite(f"{frames_dir}/frame_{count:05d}.png", upscaled)
+            
+        count += 1
+        if count % 5 == 0:
+            progress(count/total_frames, desc=f"4x Scaling: {count}/{total_frames}")
+
+    cap.release()
+
+    # 3. Final Reassembly with Optional Sharpening
+    output_video = "upscaled_output.mp4"
+    
+    # FFmpeg 'unsharp' filter for clarity
+    # Settings: luma_matrix_width:luma_matrix_height:luma_amount
+    sharpen_filter = "-vf \"unsharp=5:5:1.0\"" if do_sharpen else ""
+    
+    ffmpeg_cmd = (
+        f"ffmpeg -framerate 24 -i {frames_dir}/frame_%05d.png -i {audio_path} "
+        f"{sharpen_filter} "
+        f"-c:v libx264 -preset superfast -pix_fmt yuv420p -c:a aac -shortest {output_video} -y"
+    )
+    subprocess.run(ffmpeg_cmd, shell=True)
+    
+    # Cleanup
+    shutil.rmtree(frames_dir)
+    if os.path.exists(audio_path): os.remove(audio_path)
+    
+    return output_video
+
+# --- Updated UI with Toggle ---
+demo = gr.Interface(
+    fn=process_video,
+    inputs=[
+        gr.Video(label="Upload Video"),
+        gr.Checkbox(label="Enable Post-Upscale Sharpening", value=False, info="Check this if the AI output looks too soft or blurry.")
+    ],
+    outputs=gr.Video(label="Upscaled Result"),
+    title="Real-ESRGAN 4x CPU (with Clarity Toggle)",
+    description="Processes video to 4x resolution. Use the toggle to add extra sharpness if needed."
+)
+
+if __name__ == "__main__":
+    demo.launch()