Instructions to use facebook/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="facebook/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request for Manual Review of SAM3 Access
Hello,
My request to access the SAM3 repository was rejected on July 30, 2026, and I would like to respectfully ask for a manual review.
I am a student from Shenzhen University, currently working with a professor from the Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences, on a CT medical imaging research project. My intended use of SAM3 is strictly limited to academic research, experiment reproduction, and model evaluation in a local/server environment.
At the moment, my work is blocked because the project depends on the SAM3 base checkpoint (sam3.pt), and I cannot continue the training and evaluation pipeline without approved access. I understand that this repository is gated and subject to the authors' approval and usage terms. If access is granted, I will only use the model for research purposes and will not redistribute the weights.
If possible, I would be very grateful if you could reconsider my request. If any additional information is needed, I would be happy to provide it.
Thank you very much for your time and consideration.