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 AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/sam3") model = AutoModel.from_pretrained("facebook/sam3") - Notebooks
- Google Colab
- Kaggle
Hello Meta SAM3 team
My access request to facebook/sam3 was rejected. I think my submitted information may have been incomplete or unclear.
I would like to use SAM3 for local research and development of an AI-assisted image annotation tool. The model will be deployed on our private/on-premise server only, used for interactive annotation assistance, such as generating bounding boxes and oriented bounding boxes from point prompts. We will not redistribute the model weights or provide public model access.
Could you please reconsider my request or reset my access status so I can submit the request again?
Hugging Face username: songshu
Organization/Company: 我个人对这个很感兴趣
Use case: Private on-premise AI-assisted image annotation
Email: 1138197646@qq.com
Thank you.