File size: 949 Bytes
fe6044e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
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()