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 for Manual Review / Reset of Rejected SAM 3 Access
Hello SAM 3 Team,
My access request for 'facebook/sam3' was rejected, and I was wondering if it would be possible to review it again or allow me to resubmit the request.
I’m currently reproducing the open-source CaP-X framework for embodied AI and robot manipulation. SAM 3 is used in its perception server for text-guided object segmentation, which is needed for the full perception and manipulation pipeline.
My purpose is academic research and local simulation experiments related to embodied intelligence, especially robot perception, object grounding, and long-horizon manipulation. I’ll follow the SAM 3 license and usage policy, and I won’t redistribute the model weights.
If anything in my previous application was unclear or incomplete, I’m happy to provide more information.
Thanks for your help!
Hugging Face username: yx1203