Image segmentation 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

Image segmentation 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.

Image segmentation model list

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

50 models
ModelCapabilityContextInput $/1MOutput $/1MSpeed
briaai/RMBG-1.4
briaai
10.0
briaai/RMBG-2.0
briaai
10.0
chendelong/DirectSAM-1800px-0424
chendelong
10.0
CIDAS/clipseg-rd64-refined
CIDAS
10.0
cocktailpeanut/rm
cocktailpeanut
10.0
facebook/detr-resnet-50-panoptic
facebook
10.0
facebook/mask2former-swin-base-ade-semantic
facebook
10.0
facebook/mask2former-swin-base-coco-panoptic
facebook
10.0
facebook/mask2former-swin-large-ade-semantic
facebook
10.0
facebook/mask2former-swin-large-cityscapes-semantic
facebook
10.0
facebook/mask2former-swin-large-coco-instance
facebook
10.0
facebook/mask2former-swin-large-mapillary-vistas-semantic
facebook
10.0
facebook/mask2former-swin-small-ade-semantic
facebook
10.0
facebook/mask2former-swin-small-coco-instance
facebook
10.0
facebook/mask2former-swin-tiny-ade-semantic
facebook
10.0
facebook/mask2former-swin-tiny-coco-instance
facebook
10.0
facebook/maskformer-swin-tiny-coco
facebook
10.0
fashn-ai/fashn-human-parser
fashn-ai
10.0
jonathandinu/face-parsing
jonathandinu
10.0
mattmdjaga/segformer_b0_clothes
mattmdjaga
10.0
mattmdjaga/segformer_b2_clothes
mattmdjaga
10.0
mayocream/speech-bubble-segmentation
mayocream
10.0
microsoft/beit-base-finetuned-ade-640-640
microsoft
10.0
nvidia/NV-Segment-CT
nvidia
10.0
nvidia/segformer-b0-finetuned-ade-512-512
nvidia
10.0
nvidia/segformer-b0-finetuned-cityscapes-1024-1024
nvidia
10.0
nvidia/segformer-b1-finetuned-ade-512-512
nvidia
10.0
nvidia/segformer-b2-finetuned-ade-512-512
nvidia
10.0
nvidia/segformer-b2-finetuned-cityscapes-1024-1024
nvidia
10.0
nvidia/segformer-b3-finetuned-ade-512-512
nvidia
10.0
nvidia/segformer-b4-finetuned-ade-512-512
nvidia
10.0
nvidia/segformer-b5-finetuned-ade-640-640
nvidia
10.0
nvidia/segformer-b5-finetuned-cityscapes-1024-1024
nvidia
10.0
openmmlab/upernet-convnext-tiny
openmmlab
10.0
openmmlab/upernet-swin-large
openmmlab
10.0
PaddlePaddle/PP-DocLayoutV3
PaddlePaddle
10.0
PramaLLC/BEN2
PramaLLC
10.0
shi-labs/oneformer_ade20k_swin_large
shi-labs
10.0
shi-labs/oneformer_ade20k_swin_tiny
shi-labs
10.0
shi-labs/oneformer_cityscapes_swin_large
shi-labs
10.0
tue-mps/coco_panoptic_eomt_large_640
tue-mps
10.0
Xenova/modnet
Xenova
10.0
Xenova/segformer-b0-finetuned-ade-512-512
Xenova
10.0
ZhengPeng7/BiRefNet
ZhengPeng7
10.0
ZhengPeng7/BiRefNet_dynamic
ZhengPeng7
10.0
ZhengPeng7/BiRefNet_HR
ZhengPeng7
10.0
ZhengPeng7/BiRefNet_HR-matting
ZhengPeng7
10.0
ZhengPeng7/BiRefNet_lite
ZhengPeng7
10.0
ZhengPeng7/BiRefNet-matting
ZhengPeng7
10.0
ZhengPeng7/BiRefNet-portrait
ZhengPeng7
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.

Image segmentation 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.