🤖 image-to-text

kosmos-2-patch14-224

microsoft/kosmos-2-patch14-224

Get AI Model →
159.8K
Downloads
❤️
184
Likes
🏷️
10
Tags
📦
transformers
Library
Model Details
Full Model IDmicrosoft/kosmos-2-patch14-224
Pipeline / Taskimage-to-text
Librarytransformers
Downloads (all-time)159.8K
Likes184
Last Modified11/28/2023
Author / Orgmicrosoft
PrivateNo — public
⚡ Quick Usage (Python)

Using the 🤗 Transformers library. Install with pip install transformers

from transformers import pipeline

# Load the model
pipe = pipeline("image-to-text", model="microsoft/kosmos-2-patch14-224")

# Run inference
result = pipe("Your input here")
print(result)
🏷️ Tags
transformerspytorchsafetensorskosmos-2image-text-to-textimage-captioningimage-to-textlicense:mitendpoints_compatibleregion:us
More image-to-text Models
See all →
GLM-OCR

zai-org/GLM-OCR

7.3M❤️ 1.6K
Get AI Model →
blip-image-captioning-base

Salesforce/blip-image-captioning-base

2.2M❤️ 849
Get AI Model →
blip-image-captioning-large

Salesforce/blip-image-captioning-large

1.4M❤️ 1.5K
Get AI Model →
🚀 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-to-text

This model is designed for the image-to-text task. Explore more models for this use case.

All image-to-text Models →
📊 Popularity
Downloads159.8K
❤️ Community Likes184
🛠️ 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.
👋 Need help with code?