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
Request for manual review or reset of SAM 3 access
Hello SAM 3 team,
My access request to facebook/sam3 was rejected. Could you
please manually review my request or reset it so that I can
provide any missing or corrected information?
Hugging Face username: Octopika
Affiliation: Fudan University
I am a student conducting research on offline 2D automatic
annotation for driving videos, including instance segmentation,
multi-object tracking, and annotation quality assessment.
I would like to evaluate the official SAM 3 video predictor
against an existing Grounding DINO + SAM 2 pipeline on public
datasets such as KITTI-MOTS.
Please let me know whether any additional information or
clarification is required, or whether an eligibility restriction
applies to my request. I will follow the applicable model
license and usage requirements.
Thank you for your consideration.