Mask Generation
Transformers
ONNX
sam3
sam-3
image-segmentation
text-promptable
open-vocabulary
concept-segmentation
Instructions to use jshirota/sam3-text-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jshirota/sam3-text-onnx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="jshirota/sam3-text-onnx")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jshirota/sam3-text-onnx", device_map="auto") - Notebooks
- Google Colab
- Kaggle
SAM 3 โ Text-Promptable Image Segmentation (ONNX)
This repository contains a copy of the models made available at:
https://huggingface.co/danilobukvic/sam3-text-onnx
License
This export inherits the license of the original facebook/sam3 weights: the SAM 3 License Agreement. Read it before using these weights โ it includes restrictions on commercial use.
Acknowledgments
- Meta AI for releasing SAM 3 and its weights
- HuggingFace for the
transformersintegration that made the architecture introspectable - PyTorch team for
torch.onnx.export(especially the legacydynamo=Falsepath, which is what got the decoder across the line) - Danilo Bukvic (
danilobukvic) for the original ONNX exports
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for jshirota/sam3-text-onnx
Base model
facebook/sam3