Pure Rust image understanding engine based on SigLIP 2. Zero-shot image classification, image embeddings, and image-text similarity. No Python runtime, no CUDA, no external dependencies.

Try: https://huggingface.co/qoranet/QORA-Vision-Image

Zero-shot classification (fast, from binary)

qora-vision.exe siglip --load model.qora-vision --image photo.jpg --labels "cat,dog,bird,car"

Image-text similarity

qora-vision.exe siglip --load model.qora-vision --image photo.jpg --text "a photo of a sunset"

Image embedding only

qora-vision.exe siglip --load model.qora-vision --image photo.jpg

Load from safetensors (slow, first time)

qora-vision.exe siglip --model-path ../SigLIP2/ --image photo.jpg --labels "cat,dog,bird,car"

Save binary for fast loading

qora-vision.exe siglip --model-path ../SigLIP2/ --save model.qora-vision