Update app.py

app.py

@@ -1,10 +1,24 @@
 import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
 
-with gr.Blocks(fill_height=True) as demo:
-    with gr.Sidebar():
-        gr.Markdown("# Inference Provider")
-        gr.Markdown("This Space showcases the Salesforce/blip-image-captioning-base model, served by the hf-inference API. Sign in with your Hugging Face account to use this API.")
-        button = gr.LoginButton("Sign in")
-    gr.load("models/Salesforce/blip-image-captioning-base", accept_token=button, provider="hf-inference")
-    
-demo.launch()
+# Load model and processor
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+# Inference function
+def generate_caption(image):
+    inputs = processor(images=image, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
+
+# Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("## 🖼️ Upload an image to generate a caption using BLIP")
+    image_input = gr.Image(type="pil", label="Image")
+    caption_output = gr.Textbox(label="Caption")
+    btn = gr.Button("Generate")
+    btn.click(fn=generate_caption, inputs=image_input, outputs=caption_output)
+
+demo.launch()