import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("unography/blip-large-long-cap")
model = BlipForConditionalGeneration.from_pretrained("unography/blip-large-long-cap")

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')

inputs = processor(raw_image, return_tensors="pt")
pixel_values = inputs.pixel_values
out = model.generate(pixel_values=pixel_values, max_length=250)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach, wearing a checkered shirt and a dog collar. the woman is interacting with the dog, which is positioned towards the left side of the image. the setting is a beachfront with a calm sea and a golden hue.

Running the model on GPU

In full precision

Click to expand

python

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("unography/blip-large-long-cap")
model = BlipForConditionalGeneration.from_pretrained("unography/blip-large-long-cap").to("cuda")

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')

inputs = processor(raw_image, return_tensors="pt").to("cuda")
pixel_values = inputs.pixel_values
out = model.generate(pixel_values=pixel_values, max_length=250)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach, wearing a checkered shirt and a dog collar. the woman is interacting with the dog, which is positioned towards the left side of the image. the setting is a beachfront with a calm sea and a golden hue.

In half precision (`float16`)

Click to expand

python

import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("unography/blip-large-long-cap")
model = BlipForConditionalGeneration.from_pretrained("unography/blip-large-long-cap", torch_dtype=torch.float16).to("cuda")

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')

inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
pixel_values = inputs.pixel_values
out = model.generate(pixel_values=pixel_values, max_length=250)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach, wearing a checkered shirt and a dog collar. the woman is interacting with the dog, which is positioned towards the left side of the image. the setting is a beachfront with a calm sea and a golden hue.

unography/blip-large-long-cap

LongCap: Finetuned BLIP for generating long captions of images, suitable for prompts for text-to-image generation and captioning text-to-image datasets

Usage

Using the Pytorch model

Running the model on CPU

Running the model on GPU

In full precision

In half precision (float16)

unography/
blip-large-long-cap

In half precision (`float16`)