---
pipeline_tag: text-to-image
inference: false
---
# Model summary
This Segment Anything Model has been optimized to work with WebNN. This model is licensed under the [Apache-2.0](https://github.com/facebookresearch/segment-anything?tab=Apache-2.0-1-ov-file#readme) License. For terms of use, please visit the [Code of Conduct](https://github.com/facebookresearch/segment-anything/blob/main/CODE_OF_CONDUCT.md). If you comply with the license and terms of use, you have the rights described therin. By using this Model, you accept the terms.

Segment-Anything-WebNN is meant to be used with the corresponding sample [here](https://microsoft.github.io/webnn-developer-preview/).

# Model changes
Segment-Anything-Model-WebNN is an ONNX version of the Segment Anything Model, and is optimized for WebNN by using static input shapes and eliminates operators that are not in use.

Please find the original Segment Anything Model [here](https://github.com/facebookresearch/segment-anything).