Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoFeatureExtractor
+import torch
+from PIL import Image
+import requests
+
+# Load the tokenizer, model, and feature extractor
+model_name = "Salesforce/BLIP-image-captioning-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+
+def generate_caption(image):
+    inputs = feature_extractor(images=image, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=128, num_beams=4, return_dict_in_generate=True)
+    caption = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
+    return caption
+
+# Create the Gradio interface
+interface = gr.Interface(fn=generate_caption,
+                         inputs=gr.inputs.Image(type="pil"),
+                         outputs="text",
+                         title="Image Captioning with BLIP",
+                         description="Upload an image to generate a caption.")
+
+if __name__ == "__main__":
+    interface.launch()