k

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
+import torch
+from PIL import Image
+
+model_name = "nlpconnect/vit-gpt2-image-captioning"
+model = VisionEncoderDecoderModel.from_pretrained(model_name)
+feature_extractor = ViTImageProcessor.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+def generate_caption(image):
+    if image is None:
+        return "Please upload an image."
+
+    pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
+    pixel_values = pixel_values.to(device)
+
+    output_ids = model.generate(pixel_values, max_length=16, num_beams=4)
+    caption = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    return caption
+
+demo = gr.Interface(
+    fn=generate_caption,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="🖼️ Image Caption Generator",
+    description="Upload an image and get a caption describing it using a VisionEncoderDecoder model (ViT + GPT-2)."
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+gradio
+Pillow