import gradio as gr
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("GEMINI_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 run_single_image_logic(prompt: str, image_path: Optional[str] = None) -> str:
"""Handles text-to-image or single image-to-image using Google Gemini."""
try:
contents = [prompt]
if image_path:
input_image = Image.open(image_path)
contents.append(input_image)
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)
return tmpfile.name
except Exception as e:
raise gr.Error(f"Image generation failed: {e}")
def run_multi_image_logic(prompt: str, images: List[str]) -> str:
"""
Handles multi-image editing by sending a list of images and a prompt.
"""
if not images:
raise gr.Error("Please upload at least one image in the 'Multiple Images' tab.")
try:
contents = [Image.open(image_path[0]) for image_path in images]
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.")
pil_image = Image.open(BytesIO(image_data))
with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as tmpfile:
pil_image.save(tmpfile.name)
return tmpfile.name
except Exception as e:
raise gr.Error(f"Image generation failed: {e}")
# --- Gradio App UI ---
css = '''
#sub_title{margin-top: -35px !important}
.tab-wrapper{margin-bottom: -33px !important}
.tabitem{padding: 0px !important}
#output{margin-top: 25px}
.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}
'''
with gr.Blocks(theme=gr.themes.Citrus(), css=css) as demo:
gr.HTML('''
''')
gr.HTML("