Model Details
Full Model IDSalesforce/blip2-opt-2.7b
Pipeline / Taskimage-text-to-text
Librarytransformers
Downloads (all-time)433.2K
Likes439
Last Modified2/3/2025
Author / OrgSalesforce
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("image-text-to-text", model="Salesforce/blip2-opt-2.7b")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
transformerspytorchsafetensorsblip-2visual-question-answeringvisionimage-to-textimage-captioningimage-text-to-textenarxiv:2301.12597license:mitendpoints_compatibleregion:us
More image-text-to-text Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: image-text-to-text
This model is designed for the image-text-to-text task. Explore more models for this use case.
All image-text-to-text Models →📊 Popularity
⬇ Downloads433.2K
❤️ Community Likes439
🛠️ Requirements
- →Install: pip install transformers
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.