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 Reconsideration of SAM 3 Model Access
Dear SAM 3 Team,
I am writing to kindly request a reconsideration of my access to the SAM 3 model on Hugging Face. My Hugging Face username is Kevin2319.
I am currently a third-year undergraduate student at Peking University, working on academic research related to computer vision, generative image models, and physics-aware image generation/editing.
I would like to use SAM 3 solely for non-commercial academic research and reproducibility purposes. In particular, I am currently reproducing and analyzing recent research on physically grounded image generation and transparent-object rendering. SAM 3 is used as a segmentation component in one of the publicly released research pipelines I am studying, and access to the official checkpoint would help me reproduce the authors' experimental setup faithfully and conduct further research analysis.
I have no intention of using the model for commercial purposes or for any application that violates the model's license or usage policy. I am happy to comply with all applicable terms and conditions.
My previous access request appears to have been rejected, so I would greatly appreciate it if you could review my request again or reset the application so that I may reapply.
Thank you very much for your time and consideration.
Best regards,
Kevin
Undergraduate Student
Peking University
Hugging Face: Kevin2319