Model reference · open weights
blip-large-long-cap is an open-weight language model from unography. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Maker | unography |
|---|---|
| Type | Language models |
| Task | Image→text |
| Parameters (lead) | 470M |
| Runs with | transformers |
| Released | 2024-04-16 |
| Popularity | 12k downloads / month |
| Licence | Open weights |
About
You can use this model for conditional and un-conditional image captioning
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.
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.
float16)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.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys blip-large-long-cap for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (blip-large-long-cap below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"blip-large-long-cap","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.