Update app.py

app.py

@@ -3,10 +3,16 @@ import spacy
 from PIL import Image
 import os
 import cv2
+import subprocess
 
-# Load SpaCy model
-nlp = spacy.load("en_core_web_sm")
+# --- Dynamic SpaCy model loading (avoids download at build time) ---
+try:
+    nlp = spacy.load("en_core_web_sm")
+except OSError:
+    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
+    nlp = spacy.load("en_core_web_sm")
 
+# --- Asset mapping (character/background library) ---
 ASSET_MAP = {
     "man": "assets/characters/man.png",
     "woman": "assets/characters/woman.png",
@@ -18,6 +24,7 @@ ASSET_MAP = {
 FRAME_FOLDER = "frames"
 VIDEO_OUTPUT = "generated_video.mp4"
 
+# --- Extract characters/scenes from prompt ---
 def extract_entities(prompt):
     doc = nlp(prompt)
     characters = []
@@ -29,6 +36,7 @@ def extract_entities(prompt):
             scenes.append(ent.text.lower())
     return characters, scenes
 
+# --- Compose a single frame ---
 def compose_frame(background_path, character_paths, output_path, char_positions=None):
     bg = Image.open(background_path).convert('RGBA')
     for idx, char_path in enumerate(character_paths):
@@ -37,6 +45,7 @@ def compose_frame(background_path, character_paths, output_path, char_positions=
         bg.paste(char_img, pos, char_img)
     bg.save(output_path)
 
+# --- Create video from frames ---
 def create_video_from_frames(frame_folder, output_path, fps=24):
     images = sorted([img for img in os.listdir(frame_folder) if img.endswith(".png")])
     if not images:
@@ -50,31 +59,34 @@ def create_video_from_frames(frame_folder, output_path, fps=24):
         video.write(cv2.imread(os.path.join(frame_folder, img)))
     video.release()
 
+# --- Main function triggered by Gradio ---
 def generate_video(prompt):
     characters, scenes = extract_entities(prompt)
     
     if not scenes:
-        return None, "No scene detected! Please mention a place/location in your prompt."
+        return None, "No scene detected! Please include a place in your prompt."
 
     os.makedirs(FRAME_FOLDER, exist_ok=True)
+    
     bg_path = ASSET_MAP.get(scenes[0], ASSET_MAP["park"])
     char_paths = [ASSET_MAP.get(char, ASSET_MAP["man"]) for char in characters]
 
-    total_frames = 48  # Change to higher for longer video (e.g., 2880 for 2 mins)
+    total_frames = 48  # ~2 seconds at 24fps; increase to 2880 for 2 min
     for i in range(total_frames):
-        positions = [(100 + i*2, 200) for _ in char_paths]
+        positions = [(100 + i*2, 200) for _ in char_paths]  # Simple horizontal movement
         frame_path = os.path.join(FRAME_FOLDER, f"frame_{i:03d}.png")
         compose_frame(bg_path, char_paths, frame_path, char_positions=positions)
 
     create_video_from_frames(FRAME_FOLDER, VIDEO_OUTPUT)
     return VIDEO_OUTPUT, f"Characters: {characters}, Scenes: {scenes}"
 
-# Gradio Interface
+# --- Gradio interface ---
 iface = gr.Interface(
     fn=generate_video,
     inputs=gr.Textbox(lines=3, placeholder="Describe your scene here..."),
     outputs=[gr.Video(), gr.Textbox()],
-    title="Text to Video AI App (Gradio)"
+    title="Text to Video AI App"
 )
 
-iface.launch()
+if __name__ == "__main__":
+    iface.launch()