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
Appeal for SAM3 Access – Research on Underwater Segmentation
Dear Meta AI Team,
I am a master's student at Guangzhou University, conducting research on underwater image segmentation. I had previously applied for access to SAM3, but my request was declined.
I fully understand that access may be restricted based on specific criteria, yet I would like to respectfully ask for a second review. Underwater segmentation presents unique challenges—such as low visibility, color shift, and uneven illumination—where SAM3's strong generalization ability could offer substantial improvements over existing methods.
I would be glad to share further details about my research objectives, datasets, and intended use cases. Thank you for considering my appeal.
Sincerely,
Chen
Guangzhou University
My Hugging face ID is: akarin1016