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
Manual Review Request for Model Access β Username: chammi3001 (VFX Pipeline & ML Tool Development)
Dear Access Review Team,
I am writing to request a manual review and reset of my recent access request for SAM 3 (Username: chammi3001).
I am a professional VFX Supervisor and pipeline developer with over 15 years of experience in high-end commercial visual effects and post-production. My primary focus is building custom, production-grade machine learning tools and desktop applications to streamline rotoscoping, matting, and temporal segmentation workflows for studio pipelines (integrating into tools like Nuke, Houdini, and Blender).
The specific intended use case for this model access is:
ML Rotoscoping Tool Development: Building automated, high-precision mask generation and object tracking modules to accelerate iterative VFX roto tasks.
Pipeline Integration: Integrating efficient segmentation inferences into proprietary studio pipelines to handle complex commercial and broadcast delivery schedules.
All development is conducted within a controlled professional environment adhering strictly to responsible AI usage and data security standards.
Could you please kindly review my account or reset the access request status so I can resubmit with these details? Thank you very much for your time and assistance.
Best regards,