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 Review / Reset of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
My access request for facebook/sam3 was rejected.
I would like to kindly request a manual review or reset of my access
request so that I can submit the required information again.
Hugging Face username: mifanfan
Affiliation: Sun Yat-sen University
Role: Master Student
Intended use:
I plan to use SAM 3 solely for non-commercial academic research in
robotic perception and embodied AI. Specifically, I would like to use
SAM 3 for open-vocabulary object segmentation in RGB/RGB-D images,
as part of a robotic pick-and-place perception pipeline.
I will comply with the SAM license, Meta policies, and Hugging Face
terms, and will not redistribute the model checkpoints.
Thank you for considering my request.