Update app.py

app.py

@@ -23,7 +23,7 @@ def verify_pro_status(token: Optional[Union[gr.OAuthToken, str]]) -> bool:
     elif isinstance(token, str):
         token_str = token
     else:
-        return False # Should not happen with correct type hints, but for safety
+        return False
     
     try:
         user_info = whoami(token=token_str)
@@ -52,12 +52,12 @@ def cleanup_temp_files():
 
 def generate_video(
     prompt: str,
-    duration: int = 8,  # These are not used by the fal.ai sora-2 model directly, but kept for interface consistency
-    size: str = "1280x720",  # These are not used by the fal.ai sora-2 model directly, but kept for interface consistency
+    duration: int = 8,
+    size: str = "1280x720",
     api_key: Optional[str] = None
 ) -> Tuple[Optional[str], str]:
     """
-    Generate video using Sora-2 Text-to-Video through Hugging Face Inference API with fal-ai provider.
+    Generate video using Sora-2 through Hugging Face Inference API with fal-ai provider.
     Returns tuple of (video_path, status_message).
     """
     # Clean up old files before generating new ones
@@ -74,15 +74,16 @@ def generate_video(
         else:
             temp_client = client
             if not os.environ.get("HF_TOKEN") and not api_key:
-                return None, "❌ Please set HF_TOKEN environment variable or provide an API key."
+                return None, "❌ Please set HF_TOKEN environment variable."
         
         # Call Sora-2 through Hugging Face Inference API
         video_bytes = temp_client.text_to_video(
             prompt,
-            model="akhaliq/sora-2", # Specific model for text-to-video
+            model="akhaliq/sora-2",
         )
         
         # Save to temporary file with proper cleanup
+        # Use NamedTemporaryFile with delete=True but keep reference
         temp_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
         try:
             temp_file.write(video_bytes)
@@ -98,65 +99,12 @@ def generate_video(
         error_msg = f"❌ Error generating video: {str(e)}"
         return None, error_msg
 
-def generate_image_to_video(
-    image_path: str,
-    prompt: str,
-    api_key: Optional[str] = None
-) -> Tuple[Optional[str], str]:
-    """
-    Generate video using Sora-2 Image-to-Video through Hugging Face Inference API with fal-ai provider.
-    Returns tuple of (video_path, status_message).
-    """
-    cleanup_temp_files() # Clean up old files
-    
-    if not image_path:
-        return None, "❌ Please upload an image."
-    if not prompt or prompt.strip() == "":
-        return None, "❌ Please enter a prompt for the video generation."
-
-    try:
-        if api_key:
-            temp_client = InferenceClient(
-                provider="fal-ai",
-                api_key=api_key,
-                bill_to="huggingface",
-            )
-        else:
-            temp_client = client
-            if not os.environ.get("HF_TOKEN") and not api_key:
-                return None, "❌ Please set HF_TOKEN environment variable or provide an API key."
-
-        with open(image_path, "rb") as image_file:
-            input_image_bytes = image_file.read()
-        
-        video_bytes = temp_client.image_to_video(
-            input_image_bytes,
-            prompt=prompt,
-            model="akhaliq/sora-2-image-to-video", # Specific model for image-to-video
-        )
-        
-        temp_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
-        try:
-            temp_file.write(video_bytes)
-            temp_file.flush()
-            video_path = temp_file.name
-        finally:
-            temp_file.close()
-        
-        status_message = f"✅ Video generated successfully from image and prompt!"
-        return video_path, status_message
-
-    except Exception as e:
-        error_msg = f"❌ Error generating video from image: {str(e)}"
-        return None, error_msg
-
-
 def generate_with_pro_auth(
     prompt: str, 
-    oauth_token: Optional[gr.OAuthToken] = None # Gradio will auto-inject this based on type hint
+    oauth_token: Optional[gr.OAuthToken] = None
 ) -> Tuple[Optional[str], str]:
     """
-    Wrapper function that checks if user is PRO before generating text-to-video.
+    Wrapper function that checks if user is PRO before generating video.
     """
     # Check if user is PRO
     if not verify_pro_status(oauth_token):
@@ -176,47 +124,14 @@ def generate_with_pro_auth(
     
     return video_path, status
 
-def generate_image_to_video_with_pro_auth(
-    image_path: str,
-    prompt: str,
-    oauth_token: Optional[gr.OAuthToken] = None # Gradio will auto-inject this based on type hint
-) -> Tuple[Optional[str], str]:
-    """
-    Wrapper function that checks if user is PRO before generating image-to-video.
-    """
-    if not verify_pro_status(oauth_token):
-        raise gr.Error("Access Denied. This app is exclusively for Hugging Face PRO users. Please subscribe to PRO to use this app.")
-    
-    if not image_path:
-        return None, "❌ Please upload an image."
-    if not prompt or prompt.strip() == "":
-        return None, "❌ Please enter a prompt"
-    
-    video_path, status = generate_image_to_video(
-        image_path,
-        prompt,
-        api_key=None  # This will use the environment HF_TOKEN
-    )
-    
-    return video_path, status
-
-
 def simple_generate(prompt: str) -> Optional[str]:
-    """Simplified wrapper for text-to-video examples that only returns video."""
+    """Simplified wrapper for examples that only returns video."""
     if not prompt or prompt.strip() == "":
         return None
     
     video_path, _ = generate_video(prompt, duration=8, size="1280x720", api_key=None)
     return video_path
 
-def simple_generate_image_to_video(image_path: str, prompt: str) -> Optional[str]:
-    """Simplified wrapper for image-to-video examples that only returns video."""
-    if not image_path or not prompt or prompt.strip() == "":
-        return None
-    
-    video_path, _ = generate_image_to_video(image_path, prompt, api_key=None)
-    return video_path
-
 def create_ui():
     """Create the Gradio interface with PRO verification."""
     
@@ -237,11 +152,11 @@ def create_ui():
     }
     '''
     
-    with gr.Blocks(title="Sora-2 Text & Image-to-Video Generator", theme=gr.themes.Soft(), css=css) as demo:
+    with gr.Blocks(title="Sora-2 Text-to-Video Generator", theme=gr.themes.Soft(), css=css) as demo:
         gr.HTML("""
             <div style="text-align: center; max-width: 800px; margin: 0 auto;">
                 <h1 style="font-size: 2.5em; margin-bottom: 0.5em;">
-                    🎬 Sora-2 Text & Image-to-Video Generator
+                    🎬 Sora-2 Text-to-Video Generator
                     <span class="pro-badge">PRO</span>
                 </h1>
                 <p style="font-size: 1.1em; color: #666; margin-bottom: 20px;">Generate stunning videos using OpenAI's Sora-2 model</p>
@@ -271,115 +186,62 @@ def create_ui():
                 </div>
             """)
             
-            with gr.Tabs() as tab_selector: 
-                with gr.TabItem("Text-to-Video", id=0):
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            prompt_input_text = gr.Textbox(
-                                label="Enter your text prompt",
-                                placeholder="Describe the video you want to create...",
-                                lines=4
-                            )
-                            
-                            with gr.Accordion("Advanced Settings", open=False):
-                                gr.Markdown("*Coming soon: Duration and resolution controls*")
-                            
-                            generate_btn_text = gr.Button("🎥 Generate Video from Text", variant="primary", size="lg")
-                        
-                        with gr.Column(scale=1):
-                            video_output_text = gr.Video(
-                                label="Generated Video",
-                                height=400,
-                                interactive=False,
-                                show_download_button=True
-                            )
-                            status_output_text = gr.Textbox(
-                                label="Status",
-                                interactive=False,
-                                visible=True
-                            )
-                    
-                    # Examples section with queue disabled
-                    gr.Examples(
-                        examples=[
-                            "A serene beach at sunset with waves gently rolling onto the shore",
-                            "A butterfly emerging from its chrysalis in slow motion",
-                            "Northern lights dancing across a starry night sky",
-                            "A bustling city street transitioning from day to night in timelapse",
-                            "A close-up of coffee being poured into a cup with steam rising",
-                            "Cherry blossoms falling in slow motion in a Japanese garden"
-                        ],
-                        inputs=prompt_input_text,
-                        outputs=video_output_text,
-                        fn=simple_generate,  # Examples use simplified function
-                        cache_examples=False,
-                        api_name=False,
-                        show_api=False,
+            with gr.Row():
+                with gr.Column(scale=1):
+                    prompt_input = gr.Textbox(
+                        label="Enter your prompt",
+                        placeholder="Describe the video you want to create...",
+                        lines=4
                     )
                     
-                    # Event handler for generation with queue disabled
-                    generate_btn_text.click(
-                        fn=generate_with_pro_auth,
-                        inputs=[prompt_input_text], # OAuth token is auto-injected by type hint
-                        outputs=[video_output_text, status_output_text],
-                        queue=False,
-                        api_name=False,
-                        show_api=False,
-                    )
-
-                with gr.TabItem("Image-to-Video", id=1):
-                    with gr.Row():
-                        with gr.Column(scale=1):
-                            image_input = gr.Image(
-                                label="Upload your input image",
-                                type="filepath",
-                                height=300,
-                                value="https://huggingface.co/spaces/akhaliq/sora-2/raw/main/cat.png" # Example image
-                            )
-                            prompt_input_image = gr.Textbox(
-                                label="Enter your text prompt for the video",
-                                placeholder="Describe the action or style you want for the video (e.g., 'The cat starts to dance')",
-                                lines=3
-                            )
-                            
-                            generate_btn_image = gr.Button("🖼️ Generate Video from Image", variant="primary", size="lg")
-                        
-                        with gr.Column(scale=1):
-                            video_output_image = gr.Video(
-                                label="Generated Video",
-                                height=400,
-                                interactive=False,
-                                show_download_button=True
-                            )
-                            status_output_image = gr.Textbox(
-                                label="Status",
-                                interactive=False,
-                                visible=True
-                            )
-
-                    gr.Examples(
-                        examples=[
-                            ["https://huggingface.co/spaces/akhaliq/sora-2/raw/main/cat.png", "The cat starts to dance"],
-                            ["https://huggingface.co/spaces/akhaliq/sora-2/raw/main/forest.png", "A magical forest where trees shimmer with light"],
-                            ["https://huggingface.co/spaces/akhaliq/sora-2/raw/main/car.png", "A classic car driving through a futuristic city"]
-                        ],
-                        inputs=[image_input, prompt_input_image],
-                        outputs=video_output_image,
-                        fn=simple_generate_image_to_video,
-                        cache_examples=False,
-                        api_name=False,
-                        show_api=False,
+                    with gr.Accordion("Advanced Settings", open=False):
+                        gr.Markdown("*Coming soon: Duration and resolution controls*")
+                    
+                    generate_btn = gr.Button("🎥 Generate Video", variant="primary", size="lg")
+                
+                with gr.Column(scale=1):
+                    video_output = gr.Video(
+                        label="Generated Video",
+                        height=400,
+                        interactive=False,
+                        show_download_button=True
                     )
-
-                    generate_btn_image.click(
-                        fn=generate_image_to_video_with_pro_auth,
-                        inputs=[image_input, prompt_input_image], # OAuth token is auto-injected by type hint
-                        outputs=[video_output_image, status_output_image],
-                        queue=False,
-                        api_name=False,
-                        show_api=False,
+                    status_output = gr.Textbox(
+                        label="Status",
+                        interactive=False,
+                        visible=True
                     )
             
+            # Hidden manual token input removed - not needed anymore
+            
+            # Examples section with queue disabled
+            gr.Examples(
+                examples=[
+                    "A serene beach at sunset with waves gently rolling onto the shore",
+                    "A butterfly emerging from its chrysalis in slow motion",
+                    "Northern lights dancing across a starry night sky",
+                    "A bustling city street transitioning from day to night in timelapse",
+                    "A close-up of coffee being poured into a cup with steam rising",
+                    "Cherry blossoms falling in slow motion in a Japanese garden"
+                ],
+                inputs=prompt_input,
+                outputs=video_output,
+                fn=simple_generate,  # Examples use simplified function
+                cache_examples=False,
+                api_name=False,
+                show_api=False,
+            )
+            
+            # Event handler for generation with queue disabled
+            generate_btn.click(
+                fn=generate_with_pro_auth,
+                inputs=[prompt_input],
+                outputs=[video_output, status_output],
+                queue=False,
+                api_name=False,
+                show_api=False,
+            )
+            
             # Footer
             gr.HTML("""
                 <div style="text-align: center; margin-top: 40px; padding: 20px; border-top: 1px solid #e0e0e0;">
@@ -388,9 +250,7 @@ def create_ui():
             """)
         
         def control_access(profile: Optional[gr.OAuthProfile] = None, oauth_token: Optional[gr.OAuthToken] = None):
-            """Control interface visibility based on PRO status.
-            Gradio automatically injects gr.OAuthProfile and gr.OAuthToken based on type hints
-            when OAuth is enabled for the Space."""
+            """Control interface visibility based on PRO status."""
             if not profile:
                 # User not logged in
                 return gr.update(visible=False), gr.update(visible=False)
@@ -403,12 +263,12 @@ def create_ui():
                 message = """
                 ## ✨ Exclusive Access for PRO Users
                 
-                Thank you for your interest in the Sora-2 Text & Image-to-Video Generator!
+                Thank you for your interest in the Sora-2 Text-to-Video Generator!
                 
                 This advanced AI video generation tool is available exclusively for Hugging Face **PRO** members.
                 
                 ### What you get with PRO:
-                - ✅ Unlimited access to Sora-2 video generation (Text-to-Video & Image-to-Video)
+                - ✅ Unlimited access to Sora-2 video generation
                 - ✅ High-quality video outputs up to 1280x720
                 - ✅ Fast generation times with priority queue
                 - ✅ Access to other exclusive PRO Spaces
@@ -440,11 +300,9 @@ def create_ui():
                 return gr.update(visible=False), gr.update(visible=True, value=message)
         
         # Check access on load
-        # No explicit inputs are needed here as gr.OAuthProfile and gr.OAuthToken are
-        # provided automatically by Gradio to the function based on type hints.
         demo.load(
             control_access,
-            inputs=None, # Removed explicit instantiation of OAuthProfile and OAuthToken
+            inputs=None,
             outputs=[main_interface, pro_message]
         )