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 access to sam3 -- andylwy
Dear Meta / SAM 3 repository maintainers,
I am writing to request a reset of my access status for facebook/sam3.
I previously submitted a request to access the model checkpoints. The request was rejected.
I am currently a student from CMU and I intend to use SAM 3 solely for a non-commercial academic project: a PyBullet RGB-D tabletop pick-and-place pipeline. The model would run locally for text-prompted instance segmentation in simulation. I will not use the weights for commercial products, redistribution or any prohibited purpose. I agree to the Meta Privacy Policy and to the terms associated with this repository.
If possible, I would be grateful if you could approve access for local research use as described above.
Thank you for your time and for releasing SAM 3 to the community.
Sincerely,
Wenyue
Hugging Face username: andylwy