Create app.py

app.py

@@ -0,0 +1,132 @@
+import os
+import gradio as gr
+from PIL import Image, ImageEnhance
+import cv2
+from transformers import CLIPProcessor, CLIPModel
+import torch
+import openai
+
+# Set OpenAI API Key
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+# Load the CLIP model for object identification
+clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch16")
+clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch16")
+
+# Predefined object labels for CLIP
+object_labels = [
+    "cat", "dog", "house", "tree", "car", "mountain", "flower", "bird", "person", "robot",
+    "a digital artwork", "a portrait", "a landscape", "a futuristic cityscape"
+]
+
+def analyze_contrast_opencv(image_path):
+    """Analyze the contrast of the uploaded image using OpenCV."""
+    img = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
+    contrast = img.std()  # Standard deviation of pixel intensities
+    return contrast
+
+def identify_objects_with_clip(image_path):
+    """Identify objects in the image using CLIP."""
+    image = Image.open(image_path).convert("RGB")
+    inputs = clip_processor(text=object_labels, images=image, return_tensors="pt", padding=True)
+    
+    with torch.no_grad():
+        outputs = clip_model(**inputs)
+        logits_per_image = outputs.logits_per_image
+        probs = logits_per_image.softmax(dim=1).numpy().flatten()
+    
+    # Get the label with the highest probability
+    best_match_idx = probs.argmax()
+    best_match_label = object_labels[best_match_idx]
+    return best_match_label
+
+def enhance_contrast(image):
+    """Enhance the contrast of the image."""
+    enhancer = ImageEnhance.Contrast(image)
+    enhanced_image = enhancer.enhance(2.0)  # Increase contrast
+    enhanced_path = "enhanced_image.png"
+    enhanced_image.save(enhanced_path)
+    return enhanced_path
+
+def suggest_improvements_with_chatgpt(object_name):
+    """Generate improvement suggestions for the identified object using ChatGPT."""
+    prompt = f"Suggest ways to improve a digital artwork featuring a {object_name}."
+    response = openai.ChatCompletion.create(
+        model="gpt-4",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant providing expert art improvement suggestions."},
+            {"role": "user", "content": prompt}
+        ]
+    )
+    return response["choices"][0]["message"]["content"]
+
+def diane_multimodal(message, history):
+    """
+    Process both text and image input:
+    - Respond to text prompts about digital art.
+    - Analyze image contrast, identify objects, and provide feedback.
+    - Enhance contrast or suggest improvements when requested.
+    """
+    response = ""
+    num_images = len(message["files"])
+
+    if num_images > 0:
+        # Handle uploaded images
+        last_image_path = message["files"][-1]
+        contrast = analyze_contrast_opencv(last_image_path)
+        identified_object = identify_objects_with_clip(last_image_path)
+
+        if contrast < 25:  # Adjust threshold as needed
+            response = (
+                f"Hey, great drawing of a {identified_object}! However, it looks like the contrast is too low. "
+                "Would you like me to improve it?"
+            )
+            # Save the analyzed image path to the history
+            history.append({"role": "assistant", "content": (last_image_path,)})
+        else:
+            response = (
+                f"Hey, great drawing of a {identified_object}! Looks like the color contrast is great, be proud of yourself :)"
+            )
+        return {"role": "assistant", "content": response}
+
+    elif message["text"]:
+        # Handle text-based inputs
+        user_text = message["text"].lower()
+        if any(keyword in user_text for keyword in ["improve", "yes", "better"]):
+            # Check if an image was previously uploaded
+            for entry in reversed(history):
+                if isinstance(entry["content"], tuple):  # Check for image in history
+                    last_image_path = entry["content"][0]
+                    enhanced_image_path = enhance_contrast(Image.open(last_image_path).convert("RGB"))
+                    # Return the text message first
+                    history.append({"role": "assistant", "content": "Here's your improved image! Let me know if you'd like further adjustments."})
+                    # Return the image in a separate message
+                    return {"role": "assistant", "content": gr.Image(enhanced_image_path)}
+        elif "suggestions" in user_text:
+            for entry in reversed(history):
+                if isinstance(entry["content"], tuple):  # Check for image in history
+                    last_image_path = entry["content"][0]
+                    identified_object = identify_objects_with_clip(last_image_path)
+                    improvement_suggestions = suggest_improvements_with_chatgpt(identified_object)
+                    return {"role": "assistant", "content": improvement_suggestions}
+        else:
+            response = "Feel free to upload an image or ask for art tips!"
+    
+    return {"role": "assistant", "content": response}
+
+
+# Define the multimodal chatbot interface
+demo = gr.ChatInterface(
+    fn=diane_multimodal,
+    type="messages",
+    examples=[
+        {"text": "Teach me about digital art tools", "files": []},
+        {"text": "What is the best way to do shading digitally?", "files": []},
+    ],
+    multimodal=True,
+    textbox=gr.MultimodalTextbox(file_count="multiple", file_types=["image"]),
+    title="Your Digital Art Nice Expert (DIANE)",
+    description="Use this chatbot to improve your digital art skills or analyze and enhance image contrast.",
+)
+
+demo.launch()