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")# pip install -U transformers accelerate # 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
Access request rejected for facebook/sam3 - request to reset
#676
by Dawn-me - opened
Hi Meta SAM team,
My Hugging Face account Dawn-me submitted an access request to facebook/sam3 and received a rejection notice. I'm a student at Shandong College of Electronic Technology (China), building a local, non-commercial research prototype: an industrial surface-defect image annotation tool. I want to use SAM 3 for point/box-prompt segmentation on my own RTX 4060 laptop, for personal study.
- No redistribution of weights, no commercial resale, fully local deployment.
- I accept the SAM License terms.
Could you please reset my request so I can resubmit with complete information, or grant access directly?
Thank you.