Mask generation AI Models

Models listed

50

Reviewed and live in this category

Worth weighing up

What goes in and out, licence terms, and whether you can host it yourself

How we treat data

Published specs only — we don't estimate numbers a vendor hasn't stated

Mask generation models are a source-backed task collection in this directory. The current editorial inventory contains 25 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.

Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.

This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.

Mask generation model list

Scan the table below, then open any model for pricing, limits and the full write-up.

50 models
ModelCapabilityContextInput $/1MOutput $/1MSpeed
apple/coreml-sam2.1-baseplus
apple
10.0
apple/coreml-sam2.1-small
apple
10.0
apple/coreml-sam2.1-tiny
apple
10.0
bodhicitta/sam3
bodhicitta
10.0
DiffusionWave/sam3
DiffusionWave
10.0
erectbranch/sam3-gguf
erectbranch
10.0
facebook/sam2.1-hiera-base-plus
facebook
10.0
facebook/sam2.1-hiera-large
facebook
10.0
facebook/sam2.1-hiera-small
facebook
10.0
facebook/sam2.1-hiera-tiny
facebook
10.0
facebook/sam2-hiera-base-plus
facebook
10.0
facebook/sam2-hiera-large
facebook
10.0
facebook/sam2-hiera-small
facebook
10.0
facebook/sam2-hiera-tiny
facebook
10.0
facebook/sam3
facebook
10.0
facebook/sam3.1
facebook
10.0
facebook/sam-vit-base
facebook
10.0
facebook/sam-vit-huge
facebook
10.0
facebook/sam-vit-large
facebook
10.0
finegrain/finegrain-box-segmenter
finegrain
10.0
flaviagiammarino/medsam-vit-base
flaviagiammarino
10.0
fxmarty/sam-vit-tiny-random
fxmarty
10.0
jadechoghari/robustsam-vit-large
jadechoghari
10.0
jesusoctavioas/sam3-original
jesusoctavioas
10.0
jetjodh/sam3
jetjodh
10.0
Justin331/sam3
Justin331
10.0
litert-community/SAM2.1-Hiera-Tiny-Mask-Decoder
litert-community
10.0
MIUProject/sam3
MIUProject
10.0
nielsr/mobilesam
nielsr
10.0
nielsr/slimsam-50-uniform
nielsr
10.0
nielsr/slimsam-77-uniform
nielsr
10.0
onnx-community/sam3-tracker-ONNX
onnx-community
10.0
OpenIXCLab/SeC-4B
OpenIXCLab
10.0
pankjkkkkkk/sam3_pt
pankjkkkkkk
10.0
research21/sam3
research21
10.0
safe-models/SUM
safe-models
10.0
strangervisionhf/sam3.1-st-bf16
strangervisionhf
10.0
syscv-community/sam-hq-vit-base
syscv-community
10.0
syscv-community/sam-hq-vit-huge
syscv-community
10.0
tiiuae/Falcon-Perception
tiiuae
10.0
Translsis/sam3-model
Translsis
10.0
vil-uob/sam3-litetext-s0
vil-uob
10.0
wanglab/medsam-vit-base
wanglab
10.0
Xenova/sam-vit-base
Xenova
10.0
Xenova/sam-vit-large
Xenova
10.0
Xenova/slimsam-50-uniform
Xenova
10.0
Xenova/slimsam-77-uniform
Xenova
10.0
yonigozlan/EdgeTAM-hf
yonigozlan
10.0
Zigeng/SlimSAM-uniform-50
Zigeng
10.0
Zigeng/SlimSAM-uniform-77
Zigeng
10.0

50 models · click a column to sort

About the capability score: a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.

Mask generation model questions

It groups source-backed directory records for research and comparison. Review each model page and its primary documentation because collection membership alone does not prove quality, availability, or suitability.