👁 Homepage

👁 Hugging Face
👁 X

👁 License

Raon-VisionEncoder is a 1.14B-parameter vision-language foundation model by KRAFTON for image and text feature extraction. It supports zero-shot image classification, image-text retrieval, and native aspect ratio inference via NaFlex. Built on OpenCLIP with a LocCa (Localized CoCa) architecture and ViT-SO400M vision encoder.

Pretrained Models

Requirements

pip install torch torchvision timm transformers huggingface-hub safetensors ftfy

Quick Start

import torch
from transformers import AutoModel
from PIL import Image

# Load model + processor
model = AutoModel.from_pretrained("KRAFTON/Raon-VisionEncoder", trust_remote_code=True)
model = model.to(dtype=torch.bfloat16).eval()
processor = model.get_processor("KRAFTON/Raon-VisionEncoder")

# Encode image and text
img_inputs = processor(images=Image.open("assets/photo.jpg"))
txt_inputs = processor(text=["a cat", "a dog"])

with torch.no_grad():
 img_feat = model.encode_image(**img_inputs)
 txt_feat = model.encode_text(**txt_inputs)

 # Compute similarity with learned scale and bias
 logits = model.logit_scale.exp() * (img_feat @ txt_feat.T) + model.logit_bias
 probs = logits.softmax(dim=-1)
 print(probs)

API Reference

License

This repository is licensed under the Apache License 2.0. Third-party notices in NOTICE.

© 2026 KRAFTON

9 items • Updated 28 days ago • 46