Update app.py

app.py

@@ -14,9 +14,20 @@ import numpy as np
 
 warnings.filterwarnings('ignore')
 
-# Initialize the Gradio client for model access
-client = Client("stabilityai/stable-diffusion-xl-base-1.0")
-arxiv_client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+# Initialize Gradio clients with public demo spaces
+def initialize_clients():
+    try:
+        # Use a public Stable Diffusion demo space instead of SDXL
+        image_client = Client("gradio/stable-diffusion-2")
+        arxiv_client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+        return image_client, arxiv_client
+    except Exception as e:
+        print(f"Error initializing clients: {str(e)}")
+        return None, None
+
+if gr.NO_RELOAD:
+    # Initialize clients in NO_RELOAD block to prevent multiple initializations
+    IMAGE_CLIENT, ARXIV_CLIENT = initialize_clients()
 
 STORY_GENRES = [
     "Science Fiction",
@@ -46,7 +57,7 @@ async def generate_speech(text, voice="en-US-AriaNeural"):
         return tmp_path
     except Exception as e:
         print(f"Error in text2speech: {str(e)}")
-        raise
+        return None
 
 def generate_story_prompt(base_prompt, genre, structure):
     """Generate an expanded story prompt based on genre and structure"""
@@ -62,7 +73,10 @@ def generate_story_prompt(base_prompt, genre, structure):
 def generate_story(prompt, model_choice):
     """Generate story using specified model"""
     try:
-        result = arxiv_client.predict(
+        if ARXIV_CLIENT is None:
+            return "Error: Story generation service is not available."
+        
+        result = ARXIV_CLIENT.predict(
             prompt,
             model_choice,
             True,
@@ -75,28 +89,41 @@ def generate_story(prompt, model_choice):
 def generate_image_from_text(text_prompt):
     """Generate an image from text description"""
     try:
-        result = client.predict(
+        if IMAGE_CLIENT is None:
+            return None
+            
+        result = IMAGE_CLIENT.predict(
             text_prompt,
-            num_inference_steps=30,
-            guidance_scale=7.5,
-            width=768,
-            height=512,
-            api_name="/text2image"
+            api_name="/predict"  # Updated API endpoint for the public demo
         )
         return result
     except Exception as e:
+        print(f"Error generating image: {str(e)}")
         return None
 
 def create_video_from_images(image_paths, durations):
     """Create video from a series of images"""
-    clips = [ImageClip(img_path).set_duration(dur) for img_path, dur in zip(image_paths, durations)]
-    final_clip = concatenate_videoclips(clips, method="compose")
-    output_path = tempfile.mktemp(suffix=".mp4")
-    final_clip.write_videofile(output_path, fps=24)
-    return output_path
+    try:
+        if not image_paths:
+            return None
+            
+        clips = [ImageClip(img_path).set_duration(dur) for img_path, dur in zip(image_paths, durations) if os.path.exists(img_path)]
+        if not clips:
+            return None
+            
+        final_clip = concatenate_videoclips(clips, method="compose")
+        output_path = tempfile.mktemp(suffix=".mp4")
+        final_clip.write_videofile(output_path, fps=24)
+        return output_path
+    except Exception as e:
+        print(f"Error creating video: {str(e)}")
+        return None
 
 def process_story(story_text, num_scenes=5):
     """Break story into scenes for visualization"""
+    if not story_text:
+        return []
+        
     sentences = story_text.split('.')
     scenes = []
     scene_length = max(1, len(sentences) // num_scenes)
@@ -110,33 +137,45 @@ def process_story(story_text, num_scenes=5):
 
 def story_generator_interface(prompt, genre, structure, model_choice, num_scenes, words_per_scene):
     """Main story generation and multimedia creation function"""
-    
-    # Generate expanded prompt
-    story_prompt = generate_story_prompt(prompt, genre, structure)
-    
-    # Generate story
-    story = generate_story(story_prompt, model_choice)
-    
-    # Process story into scenes
-    scenes = process_story(story, num_scenes)
-    
-    # Generate images for each scene
-    image_paths = []
-    for scene in scenes:
-        image = generate_image_from_text(scene)
-        if image is not None:
-            temp_path = tempfile.mktemp(suffix=".png")
-            Image.fromarray(image).save(temp_path)
-            image_paths.append(temp_path)
-    
-    # Generate speech
-    audio_path = asyncio.run(generate_speech(story))
-    
-    # Create video
-    scene_durations = [5.0] * len(image_paths)  # 5 seconds per scene
-    video_path = create_video_from_images(image_paths, scene_durations)
-    
-    return story, image_paths, audio_path, video_path
+    try:
+        # Generate expanded prompt
+        story_prompt = generate_story_prompt(prompt, genre, structure)
+        
+        # Generate story
+        story = generate_story(story_prompt, model_choice)
+        if story.startswith("Error"):
+            return story, None, None, None
+        
+        # Process story into scenes
+        scenes = process_story(story, num_scenes)
+        
+        # Generate images for each scene
+        image_paths = []
+        for scene in scenes:
+            image = generate_image_from_text(scene)
+            if image is not None:
+                if isinstance(image, (str, bytes)):
+                    image_paths.append(image)
+                else:
+                    temp_path = tempfile.mktemp(suffix=".png")
+                    Image.fromarray(image).save(temp_path)
+                    image_paths.append(temp_path)
+        
+        # Generate speech
+        audio_path = asyncio.run(generate_speech(story))
+        
+        # Create video if we have images
+        if image_paths:
+            scene_durations = [5.0] * len(image_paths)  # 5 seconds per scene
+            video_path = create_video_from_images(image_paths, scene_durations)
+        else:
+            video_path = None
+        
+        return story, image_paths, audio_path, video_path
+        
+    except Exception as e:
+        error_msg = f"An error occurred: {str(e)}"
+        return error_msg, None, None, None
 
 # Create Gradio interface
 with gr.Blocks(title="AI Story Generator & Visualizer") as demo: