Update app.py

app.py

@@ -1,13 +1,14 @@
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
 import gradio as gr
-from transformers import pipeline
-pipe = pipeline(
-    "image-text-to-text",
-    model="Salesforce/blip-image-captioning-base"
-)
-def launch(input):
-    out = pipe(input)
-    return out[0]['generated_text']
-iface = gr.Interface(launch,
-                     inputs=gr.Image(type='pil'),
-                     outputs="text")
-iface.launch()
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def caption(img):
+    inputs = processor(img, return_tensors="pt")
+    out = model.generate(**inputs)
+    return processor.decode(out[0], skip_special_tokens=True)
+
+demo = gr.Interface(caption, gr.Image(type="pil"), "text")
+demo.launch()