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 β please reconsider (HF user: YLHEN6)
#643
by YLHEN6 - opened
Hi Meta team,
My access request for facebook/sam3 (HF username: YLHEN6) was rejected, possibly due to incomplete profile information, which I have now updated.
Affiliation: Shenzhen Huanchang Huyu Technology Co., Ltd.
Intended use: segmenting character illustrations into body parts (hair, face, eyes, accessories, hands) to prepare layered assets for 2D animation.
I will comply with the SAM 3 license terms and will not redistribute the weights. Could you please review my request again or reset it to pending so I can resubmit?
Thank you!
Are you able to download it now?