Huggingface Space EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
EVF-SAM extends SAM-2's capabilities with text-prompted segmentation, achieving high accuracy in Referring Expression Segmentation.
docker run -it -p 7860:7860 --platform=linux/amd64 --gpus all registry.hf.space/wondervictor-evf-sam2:latest python app.py
docker run -it -p 7860:7860 --platform=linux/amd64 registry.hf.space/fffiloni-sam2-image-predictor:latest python app.py