Mask Generation
Transformers
Safetensors
sam2
sam2_video
feature-extraction
libreyolo
promptable-segmentation
image-segmentation
# Use SAM2 with videos
import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor
predictor = SAM2VideoPredictor.from_pretrained(LibreYOLO/LibreSAM2base-plus)
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
state = predictor.init_state(<your_video>)
# add new prompts and instantly get the output on the same frame
frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>):
# propagate the prompts to get masklets throughout the video
for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
...LibreSAM2base-plus
SAM-2.1 Hiera Base Plus rehosted for LibreYOLO's LibreSAM promptable segmentation tier.
Source
Derived from facebook/sam2.1-hiera-base-plus at commit
b7320756a13354e7530a63935656d35b2f91a290 and the Apache-2.0
facebookresearch/sam2 source
release.
Modifications
Learned parameters are unchanged. The upstream Transformers-compatible snapshot
files are mirrored here for LibreYOLO distribution. This repository adds
LibreYOLO model-card packaging plus LICENSE and NOTICE files for Apache-2.0
redistribution.
Usage
from libreyolo import LibreSAM
model = LibreSAM("sam2-base-plus")
result = model("image.jpg", points=[500, 375], labels=[1])
License
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for LibreYOLO/LibreSAM2base-plus
Base model
facebook/sam2.1-hiera-base-plus
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained(LibreYOLO/LibreSAM2base-plus) with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)