| 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") | |
| def caption(img, min_, max_): | |
| raw_image = Image.open(img).convert('RGB') | |
| inputs = processor(raw_image, return_tensors="pt") | |
| out = model.generate(**inputs, min_length=min_, max_length=max_) | |
| return processor.decode(out[0], skip_special_tokens=True) | |
| def greet(img): | |
| return caption(img) | |
| iface = gr.Interface(fn=greet, | |
| title='Blip Image Captioning Large', | |
| description="[Salesforce/blip-image-captioning-large](https://huggingface.co/Salesforce/blip-image-captioning-large)", | |
| inputs=[gr.Image(type='filepath', label='Image'), gr.Slider(label='Minimum Length', minimum=1, maximum=1000, value=30), gr.Slider(label='Maximum Length', minimum=1, maximum=1000, value=100)], | |
| outputs=gr.Textbox(label='Caption'), | |
| theme = gr.themes.Base(primary_hue="teal",secondary_hue="teal",neutral_hue="slate"),) | |
| iface.launch() |