File size: 701 Bytes
c6a1f1b
 
f48b20b
 
 
 
 
 
 
 
de259b5
f48b20b
 
 
 
 
 
 
 
 
 
 
a964b00
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
import gradio as gr

# gr.Interface.load("prasanna2003/blip-image-captioning").launch()

from PIL import Image
import requests
import gradio as gr

from transformers import BlipProcessor, BlipForConditionalGeneration

model_id = "prasanna2003/blip-image-captioning"

model = BlipForConditionalGeneration.from_pretrained(model_id)
processor = BlipProcessor.from_pretrained(model_id)

def launch(input):
    image = Image.open(requests.get(input, stream=True).raw).convert('RGB')
    inputs = processor(image, return_tensors="pt")
    out = model.generate(**inputs)
    return processor.decode(out[0], skip_special_tokens=True)

iface = gr.Interface(launch, inputs="text", outputs="text")
iface.launch()