Update app.py

app.py

@@ -1,73 +1,26 @@
 import gradio as gr
-import spacy
-from PIL import Image
+from diffusers import StableDiffusionPipeline
 import os
 import cv2
-import subprocess
 
-# --- Load SpaCy model dynamically (avoids build-time download issues) ---
-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")
-
-# --- Define asset mapping (character and background files) ---
-ASSET_MAP = {
-    "man": "assets/characters/man.png",
-    "woman": "assets/characters/woman.png",
-    "dog": "assets/characters/dog.png",
-    "park": "assets/backgrounds/park.jpg",
-    "office": "assets/backgrounds/office.jpg",
-    "home": "assets/backgrounds/home.jpg",
-    "school": "assets/backgrounds/school.jpg",
-    "street": "assets/backgrounds/street.jpg"
-}
+# --- Initialize Stable Diffusion pipeline ---
+pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")
 
 FRAME_FOLDER = "frames"
 VIDEO_OUTPUT = "generated_video.mp4"
 
-# --- Extract characters and scenes from prompt ---
-def extract_entities(prompt):
-    doc = nlp(prompt)
-    characters = []
-    scenes = []
-    
-    # Named Entity Recognition
-    for ent in doc.ents:
-        if ent.label_ in ["PERSON", "ORG"]:
-            characters.append(ent.text.lower())
-        elif ent.label_ in ["LOC", "GPE", "FAC"]:
-            scenes.append(ent.text.lower())
-
-    # If no scenes found → keyword matching from ASSET_MAP keys
-    if not scenes:
-        for keyword in ASSET_MAP.keys():
-            if keyword in prompt.lower() and keyword in ["park", "office", "home", "school", "street"]:
-                scenes.append(keyword)
-                break
-
-    # If still no scene → fallback default
-    if not scenes:
-        scenes.append("park")
-    
-    return characters, scenes
-
-# --- Compose a single image 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):
-        char_img = Image.open(char_path).convert('RGBA')
-        pos = (100 + idx*100, 200) if not char_positions else char_positions[idx]
-        bg.paste(char_img, pos, char_img)
-    bg.save(output_path)
+# --- Function to generate N frames using AI ---
+def generate_frames(prompt, num_frames=10):
+    os.makedirs(FRAME_FOLDER, exist_ok=True)
+    for i in range(num_frames):
+        image = pipe(prompt).images[0]
+        image.save(f"{FRAME_FOLDER}/frame_{i:03d}.png")
 
-# --- Create a video from image frames ---
-def create_video_from_frames(frame_folder, output_path, fps=24):
+# --- Function to create video from frames ---
+def create_video_from_frames(frame_folder, output_path, fps=2):
     images = sorted([img for img in os.listdir(frame_folder) if img.endswith(".png")])
     if not images:
-        print("No frames found!")
-        return
+        raise ValueError("No frames generated.")
     frame = cv2.imread(os.path.join(frame_folder, images[0]))
     height, width, _ = frame.shape
 
@@ -76,32 +29,18 @@ 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 ---
+# --- Main function called by Gradio ---
 def generate_video(prompt):
-    characters, scenes = extract_entities(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  # 2 sec @ 24fps; increase to 2880 for 2 min
-    for i in range(total_frames):
-        positions = [(100 + i*2, 200) for _ in char_paths]
-        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)
-    
-    details = f"Characters detected: {characters if characters else 'default'}, Scene: {scenes[0]}"
-    return VIDEO_OUTPUT, details
+    generate_frames(prompt, num_frames=10)  # Generate 10 frames
+    create_video_from_frames(FRAME_FOLDER, VIDEO_OUTPUT, fps=2)  # 2 fps
+    return VIDEO_OUTPUT
 
-# --- Gradio interface setup ---
+# --- Gradio UI ---
 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 (with fallback scenes)"
+    outputs=gr.Video(),
+    title="AI Text-to-Video Generator (No manual assets needed)"
 )
 
 if __name__ == "__main__":