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
SAM 3 access request rejected — clarification and reconsideration
Hello SAM 3 team,
My Hugging Face username is PCZJU.
My access request for facebook/sam3 was rejected. I selected “Personal” for my affiliation because I am developing this project independently.
I would like to evaluate SAM 3 in a local proof of concept for segmenting printed design graphics, such as wanted-poster artwork on canvas tote bags. The experiment compares SAM 3 text-prompt segmentation with existing SAM 2.1 and GroundingDINO results, focusing on target completeness and background removal.
The model would run locally in Docker on my NVIDIA GPU. This experiment does not involve identifying people or making automated approval decisions.
I am willing to agree to the required license terms and contact-information sharing conditions. Could you please clarify whether my application was missing any information, and whether the request can be reconsidered or reset so I can correct it?
Thank you for your time and for sharing SAM 3.
Best regards,
PCZJU