Create app.py

app.py

@@ -0,0 +1,58 @@
+import streamlit as st
+from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
+from PIL import Image
+import torch
+
+# Load the processor and model directly
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
+model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
+
+# Streamlit app
+st.title("Image Description Generator")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    # Open the image
+    image = Image.open(uploaded_file)
+    st.image(image, caption='Uploaded Image.', use_column_width=True)
+    st.write("Generating description...")
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "image",
+                    "image": image,
+                },
+                {"type": "text", "text": "Describe this image."},
+            ],
+        }
+    ]
+
+    # Preparation for inference
+    text = processor.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+    # Pass the image to the processor
+    inputs = processor(
+        text=[text],
+        images=[image],
+        padding=True,
+        return_tensors="pt",
+    )
+    inputs = inputs.to("cpu")
+
+    # Inference: Generation of the output
+    generated_ids = model.generate(**inputs, max_new_tokens=128)
+    generated_ids_trimmed = [
+        out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    ]
+    output_text = processor.batch_decode(
+        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )
+    
+    st.write("Description:")
+    st.write(output_text[0])