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 of SAM 3 Access
Hello SAM 3 Team,
My access request for facebook/sam3 was rejected.
I’d like to use SAM 3 for academic research. My work involves segmenting specific objects in images and using those results for robotic planning. I think my first request may have been rejected because I didn’t explain my research use clearly enough. I will use the model strictly for non-commercial research. The model weights will not be redistributed, shared with unauthorized parties, or exposed through a public service. All use of SAM 3 will follow the applicable SAM license and Meta’s terms.
Hugging Face username: chen45954
Affiliation: Tsinghua University
SAM 3 would be very helpful for my current research, and I’d really appreciate the opportunity to use and build on your work. If possible, could you please take another look at my request and reconsider it?
Thank you very much for your help.
Thanks