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 Manual Review
#389
by aljfl - opened
I am Lyu Jinlong, an undergraduate student majoring in Computer Science at Shenzhen University (SZU). My academic email is 2025150054@mails.szu.edu.cn. I am requesting access to the SAM3 model solely for non‑commercial academic research in the field of computer vision. My current project focuses on image segmentation and visual understanding, and I believe SAM3's advanced capabilities will significantly benefit my studies. I fully agree to abide by the model's license and the terms of use set by Meta and Hugging Face. I do not intend to use the model for any commercial or production purposes. Thank you for your consideration.