File size: 868 Bytes
183ba69 471f43d 4273fa3 471f43d 183ba69 93b333b 183ba69 4a35a20 183ba69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 |
import gradio as gr
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
def caption(img):
raw_image = Image.open(img).convert('RGB')
inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs, min_length=30, max_length=1000)
return processor.decode(out[0], skip_special_tokens=True)
def greet(img):
return caption(img)
iface = gr.Interface(fn=greet, inputs=gr.Image(type='filepath'), outputs="text")
iface.launch() |