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 to Review or Reset My Access Application
Hello Meta SAM3 Team,
My access request for the facebook/sam3.1 repository was rejected. I believe my previous application may not have provided enough information about my intended use.
I would greatly appreciate it if you could review my request again or reset my application so that I can submit an updated one.
I am using SAM3.1 solely for academic research and non-commercial computer vision experiments. Specifically, I am integrating SAM3.1 with the open-source VLM-FO1 project to study vision-language-guided object detection and segmentation. The model will only be used for local inference and research purposes.
I will not use the model for any prohibited applications, including surveillance, biometric identification, military, or other restricted uses.
Hugging Face username: chen359
Thank you very much for your time and consideration. I would sincerely appreciate another opportunity to access the model.
Best regards,