unography/blip-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

You can use this model for conditional and un-conditional image captioning

Using the Pytorch model

Running the model on CPU

Click to expand

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

processor = BlipProcessor.from_pretrained("unography/blip-long-cap")
model = BlipForConditionalGeneration.from_pretrained("unography/blip-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, num_beams=3, repetition_penalty=2.5)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the sand, interacting with a dog wearing a blue and white checkered collar. the dog is positioned to the left of the woman, who is holding something in their hand. the background features a serene beach setting with waves crashing onto the shore. there are no other animals or people visible in the image. the time of day appears to be either early morning or late afternoon, based on the lighting and shadows.

Running the model on GPU

In full precision

Click to expand

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

processor = BlipProcessor.from_pretrained("unography/blip-long-cap")
model = BlipForConditionalGeneration.from_pretrained("unography/blip-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, num_beams=3, repetition_penalty=2.5)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the sand, interacting with a dog wearing a blue and white checkered collar. the dog is positioned to the left of the woman, who is holding something in their hand. the background features a serene beach setting with waves crashing onto the shore. there are no other animals or people visible in the image. the time of day appears to be either early morning or late afternoon, based on the lighting and shadows.

In half precision (float16)

Click to expand

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

processor = BlipProcessor.from_pretrained("unography/blip-long-cap")
model = BlipForConditionalGeneration.from_pretrained("unography/blip-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, num_beams=3, repetition_penalty=2.5)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the sand, interacting with a dog wearing a blue and white checkered collar. the dog is positioned to the left of the woman, who is holding something in their hand. the background features a serene beach setting with waves crashing onto the shore. there are no other animals or people visible in the image. the time of day appears to be either early morning or late afternoon, based on the lighting and shadows.