requirements.txt

streamlit
transformers
torch
protobuf
sentencepiece

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+import torch
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda")
+
+def execute(image): 
+    inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
+    out = model.generate(**inputs)
+    output = processor.decode(out[0], skip_special_tokens=True)
+    return output
+    
+iface = gr.Interface(
+    execute,
+    inputs=[
+        gr.Image(type="pil"),
+        "image",
+    ], 
+    outputs="textbox"
+)
+
+iface.launch()