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 Review of Pending SAM 3 Access - [Donggyun Kim]
#533
by recodgk - opened
Hello Meta SAM 3 Team,
I initially applied for access to facebook/sam3 last week. I then carefully completed the application form again with detailed and accurate information and resubmitted it on October 7, 2026. However, my request is still shown as pending.
Hugging Face username: Donggyun Kim
Affiliation: RECO Inc.
Intended use: Internal R&D and evaluation of promptable image segmentation for waste-management computer vision, including load-level and material-composition analysis.
We plan to fully comply with the applicable license and access terms. Could you please review my request or let me know if any additional information is required?
Thank you for your time and consideration.