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 / reset of rejected SAM3 access
Hello Meta SAM3 Team,
My access request to the SAM3 Gating Group Collection was recently
rejected.
I would like to kindly ask if my request could be reconsidered, or
if my rejected access request could be reset so that I can provide
additional or corrected information.
I am an independent software developer working on an AI-assisted
Game UI asset extraction and segmentation tool.
My intended use of SAM3 is computer vision experimentation and
software development, particularly for segmenting visual elements
from game UI screenshots, such as buttons, panels, icons, avatars,
cards, and other UI components.
The model would be used for local experimentation and development.
I will comply with the SAM3 license, Meta's applicable policies,
and all usage restrictions.
I would be happy to provide any additional information required for
the access review.
Hugging Face username:
jackiewyb001
Thank you for your time and consideration.