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
Request to review or reopen my access application
Hello,
My access request was rejected, and I would like to understand the reason or request a review.
I am an independent AI developer working with local generation pipelines (ComfyUI, Stable Diffusion, LoRA training, image and video workflows). I evaluate models for practical use on consumer hardware and integrate them into structured workflows.
This model is relevant for my work, and I intend to use it strictly for local experimentation, evaluation, and pipeline integration β not for redistribution or misuse.
If my previous request was incomplete or unclear, I would appreciate the opportunity to correct it. Could you please review or reopen my application?
Hugging Face username: CaHeKpk
Thank you for your time.
Hello Meta SAM3 team,
My access request for facebook/sam3 was rejected.
I am a student using the model for a non-commercial graduation project on coral reef image segmentation.
Could you please help review my request manually or reset my application so I can reapply?
Hugging Face username: LGCRIS
Thank you.