Blip Long Cap

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.

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.

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.