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 to re-review access for facebook/sam-3d-objects
Dear SAM 3D / Meta AI team,
I am writing to respectfully request a re-review of my access request for the gated model repository "facebook/sam-3d-objects" (and "facebook/sam3").
Purpose of use:
I am a student at Zhuhai College of Science and Technology conducting non-commercial academic research on single-image 3D scene reconstruction. I am studying and reproducing the open-source Mira-Scene pipeline, whose official documentation specifies SAM 3 for instance segmentation and SAM 3D Objects as the object-mesh generation backend. Access to these checkpoints is therefore required in order to run and evaluate the pipeline for my academic research.
I confirm that I will:
- use the models solely for non-commercial academic research and personal study;
- comply with the SAM License and all applicable Meta terms of use;
- not redistribute the model weights, derived weights, or converted checkpoints
to any third party; - cite the original work in any publication arising from this research.
HF id:Jing0505
If my earlier form was incomplete or used abbreviations, I apologize —I am happy to resubmit with my full legal name, date of birth and full organization name.