| from PIL import Image | |
| import requests | |
| import gradio as gr | |
| from transformers import BlipProcessor, BlipForConditionalGeneration | |
| model_id = "Salesforce/blip-image-captioning-large" | |
| model = BlipForConditionalGeneration.from_pretrained(model_id) | |
| processor = BlipProcessor.from_pretrained(model_id) | |
| def launch(input): | |
| image = Image.open(input).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="image", outputs="text") | |
| iface.launch() |