Blog
Replicate
STABLE

Segment Anything Everything

Tryout SegmentAnything Model (SAM) by Meta.

Inputs
Image
Input image
Box Nms Thresh
The box IoU cutoff used by non-maximal suppression to filter duplicate masks.
Crop N Layers
If >0, mask prediction will be run again on crops of the image. Sets the number of layers to run, where each layer has 2**i_layer number of image crops
Crop N Points Downscale Factor
The number of points-per-side sampled in layer n is scaled down by crop_n_points_downscale_factor**n.
Crop Nms Thresh
The box IoU cutoff used by non-maximal suppression to filter duplicate masks between different crops.
Crop Overlap Ratio
Sets the degree to which crops overlap. In the first crop layer, crops will overlap by this fraction of the image length. Later layers with more crops scale down this overlap.
Mask Limit
maximum number of masks to return. If -1 or None, all masks will be returned. NOTE: The masks are sorted by predicted_iou.
Mask Only
If True, the output will only include mask.
Min Mask Region Area
If >0, postprocessing will be applied to remove disconnected regions and holes in masks with area smaller than min_mask_region_area.
Points Per Side
The number of points to be sampled along one side of the image. The total number of points is points_per_side**2. If None, point_grids must provide explicit point sampling.
Pred Iou Thresh
A filtering threshold in [0,1], using the model's predicted mask quality.
Stability Score Offset
The amount to shift the cutoff when calculated the stability score.
Stability Score Thresh
A filtering threshold in [0,1], using the stability of the mask under changes to the cutoff used to binarize the model's mask predictions.
Outputs
Urls
URLs of the images