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
Gated access request rejected — could you please review?
#536
by Ravenveil - opened
Hi, I'm a researcher working on video world models and 4D scene reconstruction. My access request for facebook/sam3 was rejected — I believe it may have been a mistake, as the intended use is purely academic: I'm reproducing the ECCV 2026 paper OVOW (One Video, One World), which builds on SAM3 for promptable segmentation. I've re-read the license (research-only) and fully comply. Could you please re-review my access request? Thank you!