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
access request rejected, request manual re-review
#709
by Champion88 - opened
Hello Meta team,
My Hugging Face username: 【Li Champion88】
My access application for sam-3d-body repo was rejected. I’m writing to ask for manual recheck.
I am an independent AI learning enthusiast. I only use this dataset and model for non-commercial self-learning and local technical experiments on 3D human body reconstruction. All inference runs on my private GPU.
I will not redistribute weights or data, and will never launch any public service or commercial project based on them.
I accept and will strictly follow the SAM License and Meta Privacy Policy.
I agree to share my Hugging Face username and email with Meta, and I accept the Meta Privacy Policy.
Thanks for your consideration.