Upload app.py

app.py

@@ -1,165 +1,197 @@
-import os
-import tempfile
-from PIL import Image
-import gradio as gr
-import google.generativeai as genai
-from io import BytesIO
-
-# Hardcode the Gemini API key
-GEMINI_API_KEY = "AIzaSyDL5Rilo7ptJpUOZdY6wy8PJYUcVcnDADs"
-
-def configure_api_key():
-    """Configure the Gemini API key."""
-    if not GEMINI_API_KEY:
-        raise gr.Error("Gemini API key is not set.")
-    genai.configure(api_key=GEMINI_API_KEY)
-
-def generate(text, images, model="gemini-2.5-flash"):
-    """Generate content using the Gemini model."""
-    configure_api_key()
-    
-    # Convert images to Gemini-compatible format
-    contents = []
-    for img in images:
-        if img.mode == "RGBA":
-            img = img.convert("RGB")
-        contents.append(img)
-    contents.append(text)
-    
-    try:
-        response = genai.GenerativeModel(model).generate_content(contents)
-        
-        text_response = ""
-        image_path = None
-        
-        for part in response.candidates[0].content.parts:
-            if hasattr(part, 'text') and part.text:
-                text_response += part.text + "\n"
-            elif hasattr(part, 'inline_data') and part.inline_data:
-                # Save generated image to a temporary file
-                with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
-                    image_path = tmp.name
-                    generated_image = Image.open(BytesIO(part.inline_data.data))
-                    generated_image.save(image_path)
-                    print(f"Generated image saved to: {image_path} with prompt: {text}")
-        
-        return image_path, text_response
-    except Exception as e:
-        raise gr.Error(f"Error generating content: {str(e)}")
-
-def load_uploaded_images(uploaded_files):
-    """Load and display uploaded images immediately."""
-    uploaded_images = []
-    if uploaded_files:
-        for file in uploaded_files:
-            if file.name.lower().endswith(('.png', '.jpg', '.jpeg', '.webp')):
-                img = Image.open(file.name)
-                uploaded_images.append(img)
-    return uploaded_images
-
-def process_image_and_prompt(uploaded_files, prompt):
-    """Process uploaded images and prompt to generate output."""
-    try:
-        if not uploaded_files:
-            raise gr.Error("Please upload at least one image.")
-        if not prompt:
-            raise gr.Error("Please provide a prompt.")
-        
-        # Load images
-        images = load_uploaded_images(uploaded_files)
-        
-        # Generate content
-        image_path, text_response = generate(
-            text=prompt,
-            images=images
-        )
-        
-        # Prepare outputs
-        output_images = [Image.open(image_path)] if image_path else None
-        return images, output_images, text_response
-    except Exception as e:
-        raise gr.Error(f"Error: {str(e)}")
-
-# Gradio interface
-with gr.Blocks(css="style.css") as demo:
-    gr.HTML("""
-    <div class="header-container">
-      <div>
-          <img src="https://www.gstatic.com/lamda/images/gemini_favicon_f069958c85030456e93de685481c559f160ea06b.png" alt="Gemini logo">
-      </div>
-      <div>
-          <h1>Gemini for Image Editing</h1>
-          <p>Powered by <a href="https://gradio.app/">Gradio</a>⚡️ | 
-          <a href="https://huggingface.co/spaces">Duplicate this Space</a> |
-          <a href="https://aistudio.google.com/apikey">Learn about Gemini API</a></p>
-      </div>
-    </div>
-    """)
-    
-    with gr.Accordion("⚠️ API Configuration ⚠️", open=False):
-        gr.Markdown("""
-        - **Note:** The Gemini API is pre-configured for this Space.
-        - **Issue:** ❗ Sometimes the model returns text instead of an image.
-        ### 🔧 Steps to Address:
-        1. **🛠️ Duplicate the Space**  
-           - Create a copy on Hugging Face Spaces for modifications.
-        2. **🔑 API Key Info**  
-           - The API key is already set up for this demo. For custom deployments, get your own key from Google AI Studio.
-        """)
-
-    with gr.Accordion("📌 Usage Instructions", open=False):
-        gr.Markdown("""
-        ### 📌 Usage  
-        - Upload an image and enter a prompt to generate outputs.
-        - If text is returned instead of an image, it will appear in the text output.
-        - Supported formats: PNG, JPG, JPEG, WEBP
-        - ❌ **Do not use NSFW images!**
-        """)
-
-    with gr.Row():
-        with gr.Column():
-            image_input = gr.File(
-                file_types=["image"],
-                file_count="multiple",
-                label="Upload Images"
-            )
-            prompt_input = gr.Textbox(
-                lines=2,
-                placeholder="Enter prompt here...",
-                label="Prompt"
-            )
-            submit_btn = gr.Button("Generate")
-        
-        with gr.Column():
-            uploaded_gallery = gr.Gallery(label="Uploaded Images")
-            output_gallery = gr.Gallery(label="Generated Outputs")
-            output_text = gr.Textbox(
-                label="Gemini Output",
-                placeholder="Text response will appear here if no image is generated."
-            )
-
-    submit_btn.click(
-        fn=process_image_and_prompt,
-        inputs=[image_input, prompt_input],
-        outputs=[uploaded_gallery, output_gallery, output_text]
-    )
-    
-    image_input.upload(
-        fn=load_uploaded_images,
-        inputs=[image_input],
-        outputs=[uploaded_gallery]
-    )
-
-    gr.Markdown("## Try these examples")
-    examples = [
-        ["data/1.webp", "change text to 'HUGGINGFACE'"],
-        ["data/2.webp", "remove the spoon from hand only"],
-        ["data/3.webp", "change text to 'AI POWERED'"],
-        ["data/1.jpg", "add futuristic style to background"],
-    ]
-    gr.Examples(
-        examples=examples,
-        inputs=[image_input, prompt_input]
-    )
-
-demo.launch()
+import json
+import os
+import time
+import uuid
+import tempfile
+from PIL import Image, ImageDraw, ImageFont
+import gradio as gr
+import base64
+import mimetypes
+from io import BytesIO
+
+from google import genai
+from google.genai import types
+
+def generate(text, images, api_key, model="gemini-2.5-flash-image-preview"):
+    # Initialize client using provided api_key (or fallback to env variable)
+    client = genai.Client(api_key=(api_key.strip() if api_key and api_key.strip() != ""
+                                     else os.environ.get("GEMINI_API_KEY")))
+    
+    # Prepare contents with images first, then text
+    contents = images + [text]
+    
+    response = client.models.generate_content(
+        model=model,
+        contents=contents,
+    )
+
+    text_response = ""
+    image_path = None
+    
+    for part in response.candidates[0].content.parts:
+        if part.text is not None:
+            text_response += part.text + "\n"
+        elif part.inline_data is not None:
+            # Create a temporary file to store the generated image
+            with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
+                temp_path = tmp.name
+                generated_image = Image.open(BytesIO(part.inline_data.data))
+                generated_image.save(temp_path)
+                image_path = temp_path
+                print(f"Generated image saved to: {temp_path} with prompt: {text}")
+    
+    return image_path, text_response
+
+def load_uploaded_images(uploaded_files):
+    """Load and display uploaded images immediately"""
+    uploaded_images = []
+    if uploaded_files:
+        for file in uploaded_files:
+            if file.name.lower().endswith(('.png', '.jpg', '.jpeg', '.webp')):
+                img = Image.open(file.name)
+                if img.mode == "RGBA":
+                    img = img.convert("RGBA")
+                uploaded_images.append(img)
+    return uploaded_images
+
+def process_image_and_prompt(uploaded_files, prompt, gemini_api_key):
+    try:
+        input_text = prompt 
+        model = "gemini-2.5-flash-image-preview" 
+
+        # Load images from uploaded files
+        images = []
+        uploaded_images = []
+        if uploaded_files:
+            for file in uploaded_files:
+                if file.name.lower().endswith(('.png', '.jpg', '.jpeg', '.webp')):
+                    img = Image.open(file.name)
+                    if img.mode == "RGBA":
+                        img = img.convert("RGBA")
+                    images.append(img)
+                    uploaded_images.append(img)
+
+        if not images:
+            raise gr.Error("Please upload at least one image", duration=5)
+
+        # Format: [dress_image, model_image, text_input] or [image1, image2, ..., text_input]
+        image_path, text_response = generate(text=input_text, images=images, api_key=gemini_api_key, model=model)
+        
+        if image_path:
+            # Load and convert the image if needed.
+            result_img = Image.open(image_path)
+            if result_img.mode == "RGBA":
+                result_img = result_img.convert("RGBA")
+            return uploaded_images, [result_img], ""  # Return uploaded images, generated image, and empty text output.
+        else:
+            # Return uploaded images, no generated image, and the text response.
+            return uploaded_images, None, text_response
+    except Exception as e:
+        raise gr.Error(f"Error Getting {e}", duration=5)
+
+
+# Build a Blocks-based interface with a custom HTML header and CSS
+with gr.Blocks(css_paths="style.css",) as demo:
+    # Custom HTML header with proper class for styling
+    gr.HTML(
+    """
+    <div class="header-container">
+      <div>
+          <img src="https://www.gstatic.com/lamda/images/gemini_favicon_f069958c85030456e93de685481c559f160ea06b.png" alt="Gemini logo">
+      </div>
+      <div>
+          <h1>Gemini for Image Editing</h1>
+          <p>Powered by <a href="https://gradio.app/">Gradio</a>⚡️| 
+          <a href="https://huggingface.co/spaces/ameerazam08/Gemini-Image-Edit?duplicate=true">Duplicate</a> this Repo |
+          <a href="https://aistudio.google.com/apikey">Get an API Key</a> | 
+          Follow me on Twitter: <a href="https://x.com/Ameerazam18">Ameerazam18</a></p>
+      </div>
+    </div>
+    """
+    )
+    
+    with gr.Accordion("⚠️ API Configuration ⚠️", open=False, elem_classes="config-accordion"):
+        gr.Markdown("""
+    - **Issue:** ❗ Sometimes the model returns text instead of an image.  
+    ### 🔧 Steps to Address:
+    1. **🛠️ Duplicate the Repository**  
+       - Create a separate copy for modifications.  
+    2. **🔑 Use Your Own Gemini API Key**  
+       - You **must** configure your own Gemini key for generation!  
+    """)
+
+    with gr.Accordion("📌 Usage Instructions", open=False, elem_classes="instructions-accordion"):
+        gr.Markdown("""
+    ### 📌 Usage  
+    - Upload an image and enter a prompt to generate outputs.
+    - If text is returned instead of an image, it will appear in the text output.
+    - Upload Only PNG Image
+    - ❌ **Do not use NSFW images!**
+    """)
+
+    with gr.Row(elem_classes="main-content"):
+        with gr.Column(elem_classes="input-column"):
+            image_input = gr.File(
+                file_types=["image"],
+                file_count="multiple",
+                label="Upload Images ",
+                elem_id="image-input",
+                elem_classes="upload-box"
+            )
+            gemini_api_key = gr.Textbox(
+                lines=1,
+                placeholder="Enter Gemini API Key (optional)",
+                label="Gemini API Key (optional)",
+                elem_classes="api-key-input"
+            )
+            prompt_input = gr.Textbox(
+                lines=2,
+                placeholder="Enter prompt here...",
+                label="Prompt",
+                elem_classes="prompt-input"
+            )
+            submit_btn = gr.Button("Generate", elem_classes="generate-btn")
+        
+        with gr.Column(elem_classes="output-column"):
+            uploaded_gallery = gr.Gallery(label="Uploaded Images", elem_classes="uploaded-gallery")
+            output_gallery = gr.Gallery(label="Generated Outputs", elem_classes="output-gallery")
+            output_text = gr.Textbox(
+                label="Gemini Output", 
+                placeholder="Text response will appear here if no image is generated.",
+                elem_classes="output-text"
+            )
+
+    # Set up the interaction with three outputs.
+    submit_btn.click(
+        fn=process_image_and_prompt,
+        inputs=[image_input, prompt_input, gemini_api_key],
+        outputs=[uploaded_gallery, output_gallery, output_text],
+    )
+    
+    # Update uploaded gallery immediately when files are uploaded
+    image_input.upload(
+        fn=load_uploaded_images,
+        inputs=[image_input],
+        outputs=[uploaded_gallery],
+    )
+    
+    gr.Markdown("## Try these examples", elem_classes="gr-examples-header")
+    
+    examples = [
+        ["data/1.webp", 'change text to "AMEER"'],
+        ["data/2.webp", "remove the spoon from hand only"],
+        ["data/3.webp", 'change text to "Make it "'],
+        ["data/1.jpg", "add joker style only on face"],
+        ["data/1777043.jpg", "add joker style only on face"],
+        ["data/2807615.jpg", "add lipstick on lip only"],
+        ["data/76860.jpg", "add lipstick on lip only"],
+        ["data/2807615.jpg", "make it happy looking face only"],
+    ]
+    
+    gr.Examples(
+        examples=examples,
+        inputs=[image_input, prompt_input,],
+        elem_id="examples-grid"
+    )
+
+demo.queue(max_size=50).launch(mcp_server=True, share=True)