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")# pip install -U transformers accelerate # 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 Manual Review / Reset of Rejected SAM 3 Access
Dear Meta SAM 3 Team,
My access request for the facebook/sam3 repository was recently rejected, and the interface no longer allows me to submit a new request.
I am an independent developer working on computer vision projects. I would like to use the official SAM 3 checkpoints to integrate advanced image segmentation into my local workflow (specifically using the LightCraft software).
I intend to use the model for non-commercial, local development and testing. I fully comply with the SAM 3 License and the Meta privacy policy, and I will not redistribute the model weights.
Could you please manually review my application or reset my status so that I can submit a new request with accurate information?
Hugging Face username: neoakira
Affiliation: Independent Developer
Intended use: Local development and integration in LightCraft for image segmentation.
Thank you for your time and consideration.
Best regards,
neoakira