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 of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
I recently created a Hugging Face account and applied for access to the SAM 3 model, but my request was rejected.
I am a computer vision engineer working on a household robotics project involving indoor object detection, instance segmentation, and automatic dataset annotation.
I would like to use the official SAM 3 checkpoints to evaluate text-prompted segmentation and generate preliminary annotations for indoor objects and household obstacles.
Could you please manually review my application or reset my access request so I can reapply?
Your Wendy
Hello Meta SAM Team,
My access request for the SAM3 Gating Group Collection was recently rejected.
I am working as an AI intern on an industrial computer vision research project focused on detecting and segmenting corrosion, coating defects, and surface damage on metal structures.
I would like to evaluate SAM 3 and SAM 3.1, compare their performance with SAM 2.1, and investigate their suitability for industrial damage segmentation.
I am willing to comply with all applicable licensing terms, usage restrictions, and data protection requirements.
Could you please review my rejected access request or let me know if additional information is required?
Thank you for your time and consideration.