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") - Notebooks
- Google Colab
- Kaggle
Request for Reconsideration β Access to SAM3
Hello Meta AI team,
Recently, I requested access to the SAM3 project, but my request was rejected. I would really appreciate if my application could be reconsidered.
My name is Lucas Gauto, and I work in the AI and data field in Argentina. At my job, we are exploring ways to automate image segmentation workflows for computer vision tasks, and SAM3 appears to be a very promising solution for this use case.
We are particularly interested in using Segment Anything Model capabilities with text prompting to improve and accelerate segmentation pipelines that currently require significant manual effort.
Access to the project would be used for professional and development purposes related to computer vision automation and model training workflows.
I would truly appreciate the opportunity to evaluate and experiment with the project in our environment.
Thank you for your time and consideration.
Best regards,
Lucas Gauto