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 to reset rejected SAM 3 access application
Hello Meta SAM Team,
My access request to facebook/sam3 was rejected. I may not have provided enough information in my original application.
Hugging Face username: dxgddd
Affiliation: Independent Developer
Job title: Software / AI Developer
Intended use:
I am evaluating SAM 3 locally for image segmentation and dataset annotation in a single-player video game research project.
The model will only be used for civilian software development, computer vision testing, and dataset annotation. It will not be used for military, weapons, surveillance, biometric identification, or other prohibited purposes.
I will comply with the SAM 3 license, Meta policies, privacy requirements, and all applicable use restrictions.
Could you please reset my rejected application to pending, or manually review my request again?
Thank you.