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 and Reset of Rejected SAM 3 Access
Hello SAM 3 Team,
I recently requested access to the official SAM 3 model checkpoints through Hugging Face, but unfortunately, my request was rejected.
I am an undergraduate student at Shanghai Jiao Tong University, conducting non-commercial academic research on fine-grained 3D shape editing and small-part localization and segmentation.
I realized that I entered "student" in the Affiliation field of my original application. This may have been incomplete or inaccurate, as I should have provided the full name of my university.
My research focuses on improving the localization and segmentation of small structural components in 3D objects. I would like to evaluate SAM 3's text-prompted segmentation capabilities as part of this research.
The model would be used solely for academic research and local experiments. I will comply with Meta's licensing terms and acceptable-use requirements, and I will not redistribute the model weights.
Could you please reconsider my application or reset its rejected status so that I can submit the correct affiliation information?
Hugging Face Username: Baobao0323
Affiliation: Shanghai Jiao Tong University
Position: Undergraduate Student
Thank you very much for your time and consideration.
Best regards,
Bao YuXin