import gradio as gr from gradio_client import Client, handle_file from google import genai from google.genai import types import os from typing import Optional, List from huggingface_hub import whoami from PIL import Image from io import BytesIO import tempfile # --- Google Gemini API Configuration --- GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY", "") if not GOOGLE_API_KEY: raise ValueError("GOOGLE_API_KEY environment variable not set.") client = genai.Client( api_key=os.environ.get("GOOGLE_API_KEY"), ) GEMINI_MODEL_NAME = 'gemini-2.5-flash-image-preview' def verify_pro_status(token: Optional[gr.OAuthToken]) -> bool: """Verifies if the user is a Hugging Face PRO user or part of an enterprise org.""" if not token: return False try: user_info = whoami(token=token.token) if user_info.get("isPro", False): return True orgs = user_info.get("orgs", []) if any(org.get("isEnterprise", False) for org in orgs): return True return False except Exception as e: print(f"Could not verify user's PRO/Enterprise status: {e}") return False def _extract_image_data_from_response(response) -> Optional[bytes]: """Helper to extract image data from the model's response.""" if hasattr(response, 'candidates') and response.candidates: for candidate in response.candidates: if hasattr(candidate, 'content') and hasattr(candidate.content, 'parts') and candidate.content.parts: for part in candidate.content.parts: if hasattr(part, 'inline_data') and hasattr(part.inline_data, 'data'): return part.inline_data.data return None def unified_image_generator( prompt: str, images: Optional[List[str]] = None, oauth_token: Optional[gr.OAuthToken] = None ) -> tuple: """ Handles all image generation tasks based on the number of input images. Returns: (output_image_path, video_button_visible, video_output_visible) """ if not verify_pro_status(oauth_token): raise gr.Error("Access Denied. This service is for PRO users only.") try: # Dynamically build the 'contents' list for the API contents = [] if images: # If there are images, open them and add to contents for image_path in images: print(image_path) contents.append(Image.open(image_path[0])) # Always add the prompt to the contents contents.append(prompt) response = client.models.generate_content( model=GEMINI_MODEL_NAME, contents=contents, ) image_data = _extract_image_data_from_response(response) if not image_data: raise ValueError("No image data found in the model response.") # Save the generated image to a temporary file to return its path pil_image = Image.open(BytesIO(image_data)) with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmpfile: pil_image.save(tmpfile.name) output_path = tmpfile.name # Determine if video button should be shown (only if exactly 1 input image) show_video_button = images and len(images) == 1 # Return output image path, video button visibility, and hide video output return output_path, gr.update(visible=show_video_button), gr.update(visible=False) except Exception as e: raise gr.Error(f"Image generation failed: {e}") def create_video_transition( input_image_gallery: List[str], prompt_input: str, output_image: str, oauth_token: Optional[gr.OAuthToken] = None ) -> tuple: """ Creates a video transition between the input and output images. Returns: (video_path, video_visible) """ if not verify_pro_status(oauth_token): raise gr.Error("Access Denied. This service is for PRO users only.") if not input_image_gallery or not output_image: raise gr.Error("Both input and output images are required for video creation.") try: video_client = Client("multimodalart/wan-2-2-first-last-frame", hf_token=oauth_token.token) input_image_path = input_image_gallery[0][0] result = video_client.predict( start_image_pil=handle_file(input_image_path), end_image_pil=handle_file(output_image), prompt=prompt_input, api_name="/generate_video" ) print(result) return result["video"] except Exception as e: raise gr.Error(f"Video creation failed: {e}") # --- Gradio App UI --- css = ''' #sub_title{margin-top: -35px !important} .tab-wrapper{margin-bottom: -33px !important} .tabitem{padding: 0px !important} .fillable{max-width: 980px !important} .dark .progress-text {color: white} .logo-dark{display: none} .dark .logo-dark{display: block !important} .dark .logo-light{display: none} .grid-container img{object-fit: contain} .grid-container {display: grid;grid-template-columns: repeat(2, 1fr)} .grid-container:has(> .gallery-item:only-child) {grid-template-columns: 1fr} #wan_ad p{text-align: center;padding: .5em} ''' with gr.Blocks(theme=gr.themes.Citrus(), css=css) as demo: gr.HTML(''' ''') gr.HTML("

Hugging Face PRO users can use Google's Nano Banana (Gemini 2.5 Flash Image Preview) on this Space. Subscribe to PRO

", elem_id="sub_title") pro_message = gr.Markdown(visible=False) main_interface = gr.Column(visible=False) with main_interface: with gr.Row(): with gr.Column(scale=1): with gr.Group(): image_input_gallery = gr.Gallery( label="Upload one or more images here. Leave empty for text-to-image", file_types=["image"], height="auto" ) prompt_input = gr.Textbox( label="Prompt", placeholder="Turns this photo into a masterpiece" ) generate_button = gr.Button("Generate", variant="primary") with gr.Column(scale=1): output_image = gr.Image(label="Output", interactive=False, elem_id="output", type="filepath") use_image_button = gr.Button("♻️ Use this Image for Next Edit") create_video_button = gr.Button("Create a video between the two images 🎥", variant="primary", visible=False) with gr.Group(visible=False) as video_group: video_output = gr.Video(label="Generated Video", show_download_button=True) gr.Markdown("Generate more with [Wan 2.2 first-last-frame](https://huggingface.co/spaces/multimodalart/wan-2-2-first-last-frame)", elem_id="wan_ad") gr.Markdown("## Thank you for being a PRO! 🤗") login_button = gr.LoginButton() # --- Event Handlers --- gr.on( triggers=[generate_button.click, prompt_input.submit], fn=lambda: [gr.update(visible=False), gr.update(visible=False)], inputs=[], outputs=[create_video_button, video_group], ).then( fn=unified_image_generator, inputs=[prompt_input, image_input_gallery], outputs=[output_image, create_video_button, video_group], ) use_image_button.click( lambda img_path: [img_path] if img_path else None, inputs=[output_image], outputs=[image_input_gallery] ) # Video creation handler create_video_button.click( fn=lambda: gr.update(visible=True), inputs=[], outputs=[video_group], ).then( fn=create_video_transition, inputs=[image_input_gallery, prompt_input, output_image], outputs=[video_output], ) # --- Access Control Logic --- def control_access( profile: Optional[gr.OAuthProfile] = None, oauth_token: Optional[gr.OAuthToken] = None ): if not profile: return gr.update(visible=False), gr.update(visible=False) if verify_pro_status(oauth_token): return gr.update(visible=True), gr.update(visible=False) else: message = ( "## ✨ Exclusive Access for PRO Users\n\n" "Thank you for your interest! This app is available exclusively for our Hugging Face **PRO** members.\n\n" "To unlock this and many other cool stuff, please consider upgrading your account.\n\n" "### [**Become a PRO Today!**](http://huggingface.co/subscribe/pro?source=nana_banana)" ) return gr.update(visible=False), gr.update(visible=True, value=message) demo.load(control_access, inputs=None, outputs=[main_interface, pro_message]) if __name__ == "__main__": demo.queue(max_size=None, default_concurrency_limit=None) demo.launch()