Create app.py

app.py

@@ -0,0 +1,30 @@
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from huggingface_hub import login
+from PIL import Image
+ 
+# Step 1: Authenticate with Hugging Face using your token
+login(token="")  # Paste your token here
+ 
+# Step 2: Load the processor and the private model
+model_name = "anushettypsl/paligemma_vqav2"  # Replace with actual model link
+processor = BlipProcessor.from_pretrained(model_name)
+model = BlipForConditionalGeneration.from_pretrained(model_name)
+ 
+# Step 3: Define the prediction function
+def predict(image):
+    inputs = processor(image, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    generated_text = processor.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+ 
+# Step 4: Create the Gradio interface
+interface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),  # Image input
+    outputs="text",               # Text output
+    title="Image-to-Text Model"
+)
+ 
+# Step 5: Launch the app
+interface.launch()