Update app.py

app.py

@@ -104,13 +104,14 @@ def generate_item(user_input, ideas, generate_video=False, max_retries=3):
         user_input (str): The user's input concept or idea.
         ideas (list): List of ideas to choose from.
         generate_video (bool): Whether to generate a video from the image.
-        max_retries (int): Maximum number of retries if image generation fails.
+        max_retries (int): Maximum number of retries for both image and video generation.
     
     Returns:
         dict: A dictionary with 'text' (str), 'image_base64' (str), 'video_base64' (str or None), and 'ideas' (list).
     """
-    video_base64 = None  # Changed from a list to a single value (string or None)
+    video_base64 = None
     
+    # Retry loop for image generation
     for attempt in range(max_retries):
         selected_idea = random.choice(ideas)
         prompt = f"""
@@ -149,7 +150,7 @@ def generate_item(user_input, ideas, generate_video=False, max_retries=3):
                 prompt=image_prompt,
                 config=types.GenerateImagesConfig(
                     aspect_ratio="9:16",
-                    number_of_images=1  # Already set to 1 image
+                    number_of_images=1
                 )
             )
             if imagen.generated_images and len(imagen.generated_images) > 0:
@@ -164,69 +165,91 @@ def generate_item(user_input, ideas, generate_video=False, max_retries=3):
                 image.save(buffered, format="PNG")
                 img_str = base64.b64encode(buffered.getvalue()).decode()
 
-                # Generate video if enabled (only 1 video)
+                # Generate video if enabled (with retries)
                 if generate_video:
-                    try:
-                        # Enhance the image prompt for video generation
-                        video_prompt = f"""
-                        The user concept is "{user_input}". Based on this and the scene: {image_prompt}, create a video.
-                        Use a close-up shot with a slow dolly shot circling around the subject, 
-                        using shallow focus on the main subject to emphasize details, in a realistic style with cinematic lighting.
-                        """
-                        operation = client.models.generate_videos(
-                            model="veo-2.0-generate-001",
-                            prompt=video_prompt,
-                            image=generated_image.image,
-                            config=types.GenerateVideosConfig(
-                                aspect_ratio="9:16",
-                                number_of_videos=1,  # Changed to 1 video
-                                duration_seconds=8,
-                                negative_prompt="blurry, low quality, text, letters"
+                    for video_attempt in range(max_retries):
+                        try:
+                            # Base video prompt
+                            video_prompt_base = f"""
+                            The user concept is "{user_input}". Based on this and the scene: {image_prompt}, create a video.
+                            Use a close-up shot with a slow dolly shot circling around the subject, 
+                            using shallow focus on the main subject to emphasize details, in a realistic style with cinematic lighting.
+                            """
+                            # Modify the prompt slightly for each retry
+                            if video_attempt == 0:
+                                video_prompt = video_prompt_base
+                            elif video_attempt == 1:
+                                video_prompt = f"""
+                                The user concept is "{user_input}". Based on this and the scene: {image_prompt}, create a video.
+                                Use a close-up shot focusing on the subject, 
+                                with soft lighting and a realistic style.
+                                """
+                            else:
+                                video_prompt = f"""
+                                The user concept is "{user_input}". Based on this and a simplified scene: {image_prompt}, create a video.
+                                Use a static close-up shot of the subject in a realistic style.
+                                """
+
+                            print(f"Attempting video generation (attempt {video_attempt + 1}): {video_prompt}")
+                            operation = client.models.generate_videos(
+                                model="veo-2.0-generate-001",
+                                prompt=video_prompt,
+                                image=generated_image.image,
+                                config=types.GenerateVideosConfig(
+                                    aspect_ratio="9:16",
+                                    number_of_videos=1,
+                                    duration_seconds=8,
+                                    negative_prompt="blurry, low quality, text, letters"
+                                )
                             )
-                        )
-                        # Wait for video to generate
-                        while not operation.done:
-                            time.sleep(20)
-                            operation = client.operations.get(operation)
-                        
-                        # Enhanced error handling for video generation response
-                        if operation.error:
-                            raise ValueError(f"Video generation operation failed with error: {operation.error.message}")
-                        if operation.response is None:
-                            raise ValueError("Video generation operation failed: No response")
-                        if not hasattr(operation.response, 'generated_videos') or operation.response.generated_videos is None:
-                            raise ValueError("Video generation operation failed: No generated_videos in response")
-                        
-                        # Process the single generated video
-                        if len(operation.response.generated_videos) > 0:
-                            video = operation.response.generated_videos[0]
-                            if video is None or not hasattr(video, 'video'):
-                                raise ValueError("Video is invalid or missing video data")
-                            fname = 'with_image_input.mp4'  # Removed numbering since only 1 video
-                            print(f"Generated video: {fname}")
-                            # Download the video and get the raw bytes
-                            video_data = client.files.download(file=video.video)
-                            # Ensure video_data is in bytes
-                            if isinstance(video_data, bytes):
-                                video_bytes = video_data
+                            # Wait for video to generate
+                            while not operation.done:
+                                time.sleep(20)
+                                operation = client.operations.get(operation)
+                            
+                            # Enhanced error handling for video generation response
+                            if operation.error:
+                                raise ValueError(f"Video generation operation failed with error: {operation.error.message}")
+                            if operation.response is None:
+                                raise ValueError("Video generation operation failed: No response")
+                            if not hasattr(operation.response, 'generated_videos') or operation.response.generated_videos is None:
+                                raise ValueError("Video generation operation failed: No generated_videos in response")
+                            
+                            # Process the single generated video
+                            if len(operation.response.generated_videos) > 0:
+                                video = operation.response.generated_videos[0]
+                                if video is None or not hasattr(video, 'video'):
+                                    raise ValueError("Video is invalid or missing video data")
+                                fname = 'with_image_input.mp4'
+                                print(f"Generated video: {fname}")
+                                # Download the video and get the raw bytes
+                                video_data = client.files.download(file=video.video)
+                                # Ensure video_data is in bytes
+                                if isinstance(video_data, bytes):
+                                    video_bytes = video_data
+                                else:
+                                    # If video_data is a file-like object, read the bytes
+                                    video_buffer = BytesIO()
+                                    for chunk in video_data:
+                                        video_buffer.write(chunk)
+                                    video_bytes = video_buffer.getvalue()
+                                # Encode the video bytes as base64
+                                video_base64 = base64.b64encode(video_bytes).decode()
+                                break  # Success, exit the retry loop
+                            else:
+                                raise ValueError("No video was generated")
+                        except Exception as e:
+                            print(f"Error generating video (attempt {video_attempt + 1}): {e}")
+                            if video_attempt == max_retries - 1:
+                                print("Max retries reached for video generation. Proceeding without video.")
+                                video_base64 = None
                             else:
-                                # If video_data is a file-like object, read the bytes
-                                video_buffer = BytesIO()
-                                for chunk in video_data:
-                                    video_buffer.write(chunk)
-                                video_bytes = video_buffer.getvalue()
-                            # Encode the video bytes as base64
-                            video_base64 = base64.b64encode(video_bytes).decode()
-                        else:
-                            raise ValueError("No video was generated")
-                    except Exception as e:
-                        print(f"Error generating video: {e}")
-                        video_base64 = None  # Proceed without video if generation fails
+                                continue  # Retry with a modified prompt
 
                 return {
                     'text': text,
                     'image_base64': img_str,
-                    'video_base64': video_base64,  # Now a single string or None
+                    'video_base64': video_base64,
                     'ideas': ideas
                 }
             else:
@@ -309,7 +332,7 @@ def start_feed(user_input, generate_video, current_index, feed_items):
             margin: 0 auto;
             background-color: #000;
             height: 640px;
-            border: 1px solidBundled #333;
+            border: 1px solid #333;
             border-radius: 10px;
             color: white;
             font-family: Arial, sans-serif;