File size: 784 Bytes
fe24d04
 
17646ed
 
6b4a9a6
fe24d04
 
 
6d97bc1
fe24d04
17646ed
 
b56d4a5
17646ed
 
b56d4a5
17646ed
b56d4a5
bf2de89
 
17646ed
 
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
from transformers import BlipProcessor, BlipForConditionalGeneration



model_id = "dblasko/blip-dalle3-img2prompt"
model = BlipForConditionalGeneration.from_pretrained(model_id)
processor = BlipProcessor.from_pretrained(model_id)

def generate_caption(image):
  inputs = processor(images=image, return_tensors="pt")
  pixel_values = inputs.pixel_values

  generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
  generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True, temperature=0.8, top_k=40, top_p=0.9)[0]

  return generated_caption



# Create a Gradio interface with an image input and a textbox output
demo = gr.Interface(fn=generate_caption, inputs=gr.Image(), outputs=gr.Textbox(label="Generated caption"))