Sealbook

mit-han-lab/efficientvit

Efficient vision foundation models for high-resolution generation and perception.

deep-compression-autoencoderefficient-diffusion-modelefficientvithigh-resolutionimagenetsegment-anythingsegmentationvision-transformer

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push 13 months ago.