init 2

README.md

@@ -16,7 +16,7 @@ Detect whether an image is AI-generated or real using state-of-the-art machine l
 
 ## Overview
 
-This Gradio app uses the [Organika/sdxl-detector](https://huggingface.co/Organika/sdxl-detector) model to classify images as either AI-generated or real. The model has been specifically trained to detect images generated by various AI systems including:
+This Gradio app uses a specialized model to classify images as either AI-generated or real. The model has been specifically trained to detect images generated by various AI systems including:
 
 - DALL-E
 - Midjourney  
@@ -31,7 +31,6 @@ This Gradio app uses the [Organika/sdxl-detector](https://huggingface.co/Organik
 
 ## Model Information
 
-- **Model**: [Organika/sdxl-detector](https://huggingface.co/Organika/sdxl-detector)
 - **Task**: Image Classification (Binary: AI-generated vs Real)
 - **Framework**: Transformers + PyTorch
 - **Interface**: Gradio
@@ -46,7 +45,7 @@ This Gradio app uses the [Organika/sdxl-detector](https://huggingface.co/Organik
 
 ## Technical Details
 
-The app uses both the Transformers pipeline and direct model inference to provide robust classification results. The model outputs probabilities for each class, giving you confidence scores for the prediction.
+The app uses direct model inference to provide robust classification results. The model outputs probabilities for each class, giving you confidence scores for the prediction.
 
 ## Development
 

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
-from transformers import pipeline, AutoImageProcessor, AutoModelForImageClassification
+from transformers import AutoImageProcessor, AutoModelForImageClassification
 
 # Load the model and processor
 print("Loading model...")
 processor = AutoImageProcessor.from_pretrained("Organika/sdxl-detector")
 model = AutoModelForImageClassification.from_pretrained("Organika/sdxl-detector")
-pipe = pipeline("image-classification", model="Organika/sdxl-detector")
 print("Model loaded successfully!")
 
 def detect_ai(image):
@@ -22,10 +21,7 @@ def detect_ai(image):
         return {}
     
     try:
-        # Pipeline result
-        pipe_out = pipe(image)
-        
-        # Direct model inference for more detailed results
+        # Direct model inference
         inputs = processor(images=image, return_tensors="pt")
         outputs = model(**inputs)
         logits = outputs.logits
@@ -51,7 +47,7 @@ demo = gr.Interface(
     outputs=gr.Label(num_top_classes=2, label="AI vs Real Probability"),
     title="🤖 AI‑Generated Image Detector",
     description="""
-    Upload an image to detect whether it's AI-generated or real using the Organika/sdxl-detector model.
+    Upload an image to detect whether it's AI-generated or real.
     
     This model can help identify images generated by AI systems like DALL-E, Midjourney, Stable Diffusion, and others.
     
@@ -62,8 +58,7 @@ demo = gr.Interface(
     """,
     article="""
     ### About the Model
-    This detector uses the [Organika/sdxl-detector](https://huggingface.co/Organika/sdxl-detector) model 
-    to classify images as either AI-generated or real. The model has been trained to detect various AI-generated images 
+    The model has been trained to detect various AI-generated images 
     with a focus on SDXL and similar diffusion models.
     
     ### Limitations