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 SAM3 access
#371
by cooper12hhh - opened
Hello,
My Hugging Face username is cooper12hhh. I am a university student
conducting non-commercial academic research on high-resolution visual
reasoning and visual-agent tool use.
I plan to use SAM3 only as a local image segmentation tool to evaluate
text-, point-, and bounding-box-guided segmentation. The model will not
be redistributed, exposed as a public service, or used commercially.
All usage will comply with the SAM license and Meta's terms.
My previous request was rejected, possibly because the research
description was incomplete. Could you please reconsider or reset my
access request?
Thank you.