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 AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3") - Notebooks
- Google Colab
- Kaggle
Request for access
#260
by Bridgee - opened
Hello SAM3 team,
My access request for sam3 is still pending, and I wanted to kindly ask whether it could be reviewed.
I am a postdoctoral researcher at MIT and would like to use SAM3 for non-commercial academic research on zero-shot text-prompted segmentation/tracking. I will follow the model license, will not redistribute the checkpoint, and will cite the work properly.
Please let me know if I should provide any additional information.
Thank you,
Bridge