Instructions to use 1038lab/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 1038lab/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="1038lab/sam3")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("1038lab/sam3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
*.safetensors* no need in ComfyUI?
#2
by jimzlf - opened
"These mirrored weights are used in the AILab SAM3 ComfyUI node (RMBG edition) to enable promptable segmentation workflows directly inside ComfyUI. The node loads sam3.safetensors, tokenizer assets, and the SAM3 processors locally, so the entire pipeline stays compatible even when offline."
In ComfyUI, I downloaded the .safetensors and put in SAM3, but the node SAM3 Segmentation (RMBG) was still dowloading the .pt, so actually there's no need to use .safetensors right?