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
request for sam3
Hello Meta AI team,
My request to access the facebook/sam3 model repository was rejected. I would like to respectfully ask for reconsideration.
I am a student working on an academic digital human / face editing project. My intended use is research and learning only, not commercial deployment. I plan to use SAM3 for image and video segmentation experiments, especially to study how text-prompted segmentation can support face-region masking and related digital human workflows.
I am willing to provide the required contact information and comply with the model license, usage policy, and any restrictions specified by Meta and Hugging Face. I will not redistribute the model weights or use them for unauthorized purposes.
Could you please reconsider my access request, or let me know if there is any additional information I should provide?
Thank you very much for your time and consideration.
Best regards,
Xu Hongyang[Name]
alpsx[Hugging Face Username]
Beijing University of Posts and Telecommunications[University]