import gradio as gr from PIL import Image from transformers import AutoProcessor, BlipForConditionalGeneration # Load model and processor processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base") model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base") def caption_image(input_image): raw_image = input_image.convert("RGB") inputs = processor(raw_image, return_tensors="pt") # Generate caption output = model.generate(**inputs, max_length=50) # Decode caption caption = processor.decode(output[0], skip_special_tokens=True) return caption iface = gr.Interface( fn=caption_image, inputs=gr.Image(type="pil"), outputs="text", title="MTA – AI-Powered Image Captioning", description="Upload an image and MTA v1.0 (Meaningful Tagging Assistant) will generate an intelligent caption using a vision-language AI model." ) iface.launch()