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 Manual Review / Reset of Rejected SAM 3 Access
Hello Meta SAM 3 Team,
My access request for facebook/sam3 was rejected. I would like to request
a manual review, or a reset of the rejected status so that I can resubmit
the access form if necessary.
I am a DevOps / infrastructure engineer working with local AI/ML and
image-processing workflows.
My intended use of SAM 3 is local evaluation of promptable image segmentation
and automatic mask generation for ComfyUI-based image-editing workflows.
In particular, I plan to use SAM 3 to identify user-specified objects or image
regions and generate segmentation masks for downstream local editing and
inpainting workflows. The generated masks can be reviewed before the edit is
applied, allowing changes to remain localized to the intended region.
The model will run locally for development, testing, and evaluation purposes.
I will comply with the SAM License and the applicable Meta and Hugging Face
terms.
Hugging Face username: mortiferius
If my original request was incomplete or unclear, I would appreciate the
opportunity to correct it. Please let me know if any additional information
is required.
Thank you for your time and consideration.