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 rejected access to facebook/sam3
#336
by danny1996 - opened
Hello Meta / SAM3 team,
My Hugging Face username is danny1996.
My previous access request to facebook/sam3 was rejected. I kindly ask for a re-review.
Use case
I am building a research / product prototype for architectural and interior material preview.
I only need SAM3 Tracker (point-prompt visual segmentation) to segment surfaces such as railings and wall regions from photos, then apply material textures locally.
I will not redistribute the model weights.
Compliance
I agree to Meta’s privacy policy and license terms for this model.
I can provide additional identity / affiliation details if needed.
Thank you very much for reconsidering my request.