A new image segmentation model that can segment almost anything via prompt.

– Zero-shot generalization
– Based on Transformers
– Code and dataset released
– 632M + 4M params
– Can be prompted via background points, mask, and bounding box. https://t.co/etBlCd9yCj

— Jean de Dieu Nyandwi (@Jeande_d) 5 avril 2023

A new image segmentation model that can segment almost anything via prompt. – Zero-shot generalization
– Based on Transformers
– Code and dataset released
– 632M + 4M params
– Can be prompted via background points, mask, and bounding box.

→ View original post on X — @jeande_d,