---
license: apache-2.0
---
## EVF-SAM

[EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://huggingface.co/papers/2406.20076)


## Usage:
This is the checkpoint holder of [EVF-SAM](https://github.com/hustvl/EVF-SAM.git).  
Please refer to `"inference.py"` and `"inference_video.py"` in the source code for detailed usage.  
We haven't supported `"AutoModel.from_pretrained(...)"` yet, please import the model script from source code.