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")# 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 request
Dear Meta AI / SAM 3 Access Team,
I am writing to respectfully request a reconsideration of my SAM 3 access request, which was recently rejected, likely due to an automated filter or incomplete profile information.
I am a student at Shanghai Jiao Tong University and an independent researcher. I would like to use SAM 3 strictly for non-commercial, personal image processing, academic learning, and testing. I will not use it for commercial purposes, redistribute the weights, or use it in any prohibited applications. I have read and agree to comply with the SAM 3 license and acceptable use policy.
My correct Hugging Face username is: JeordLee.
University email: lizhengwen@sjtu.edu.cn
Affiliation: Shanghai Jiao Tong University
ORCID iD: https://orcid.org/0009-0003-5010-9936
Intended use: Non-commercial personal image processing, academic learning, and testing
If necessary, I can provide additional information to verify my student status or intended use. Thank you for your time and consideration.
Best regards,
Zhengwen Li
Shanghai Jiao Tong University
lizhengwen@sjtu.edu.cn