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 reconsideration / reset of rejected SAM 3 access request
Hello SAM 3 Team,
My access request for the facebook/sam3 repository was recently rejected. I would appreciate it if you could manually reconsider my request or reset it to pending so that I can provide any additional information required.
I am a PhD student conducting non-commercial academic research on industrial artificial intelligence and image segmentation. My current research involves industrial image segmentation and computer vision, and I would like to use SAM 3 / SAM 3.1 for academic experiments and comparative evaluation.
The model will be used solely for legitimate academic research and will not be used for military, surveillance, weapons, or other restricted applications. I will comply with the SAM license, Meta policies, and applicable requirements.
Hugging Face username: xinchenstar
Thank you for your consideration.