Top open image-segmentation models
Models that segment images into regions or objects.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | BiRefNet | ZhengPeng7 | 748.8K | 655 | – | MIT | Yes | GPU |
| 2 | clipseg-rd64-refined | CIDAS | 636.2K | 142 | – | Apache 2.0 | Yes | GPU |
| 3 | mask2former-swin-large-ade-semantic | 463.1K | 31 | – | Custom (other) | Check the license | GPU | |
| 4 | mask2former-swin-large-cityscapes-semantic | 439.9K | 40 | – | Custom (other) | Check the license | GPU | |
| 5 | segformer_b2_clothes | mattmdjaga | 411.8K | 510 | – | Custom (other) | Check the license | CPU |
| 6 | RMBG-2.0 | briaai | 391.6K | 1.5K | – | Custom (other) | Check the license | CPU |
| 7 | BiRefNet_lite | ZhengPeng7 | 335.1K | 22 | – | MIT | Yes | GPU |
| 8 | segformer-b0-finetuned-ade-512-512 | nvidia | 323.7K | 206 | – | Custom (other) | Check the license | GPU |
| 9 | RMBG-1.4 | briaai | 258.4K | 2K | – | Custom (other) | Check the license | CPU |
| 10 | segformer-b2-finetuned-ade-512-512 | nvidia | 206.9K | 14 | – | Custom (other) | Check the license | GPU |
| 11 | face-parsing | jonathandinu | 196K | 230 | – | Not stated | Check the license | CPU |
| 12 | segformer-b0-finetuned-ade-512-512 | Xenova | 188.7K | 2 | – | Not stated | Check the license | CPU |
| 13 | oneformer_cityscapes_swin_large | shi-labs | 156.9K | 2 | – | MIT | Yes | GPU |
| 14 | segformer-b3-finetuned-ade-512-512 | nvidia | 139K | 16 | – | Custom (other) | Check the license | GPU |
| 15 | modnet | Xenova | 127.7K | 86 | – | Apache 2.0 | Yes | CPU |
| 16 | BEN2 | PramaLLC | 100.6K | 250 | – | MIT | Yes | CPU |
| 17 | oneformer_coco_swin_large | shi-labs | 97.8K | 8 | – | MIT | Yes | GPU |
| 18 | mask2former-swin-tiny-coco-instance | 87K | 21 | – | Custom (other) | Check the license | GPU | |
| 19 | fashn-human-parser | fashn-ai | 67K | 32 | – | Custom (other) | Check the license | GPU |
| 20 | oneformer_ade20k_swin_large | shi-labs | 57.6K | 39 | – | MIT | Yes | GPU |
| 21 | coco_panoptic_eomt_large_640 | tue-mps | 56.7K | 14 | – | MIT | Yes | GPU |
| 22 | BiRefNet-portrait | ZhengPeng7 | 52.6K | 17 | – | MIT | Yes | GPU |
| 23 | BiRefNet_HR | ZhengPeng7 | 50.8K | 83 | – | MIT | Yes | GPU |
| 24 | segformer-b5-finetuned-ade-640-640 | nvidia | 50.3K | 52 | – | Custom (other) | Check the license | GPU |
| 25 | eomt-dinov3-coco-panoptic-base-640 | tue-mps | 48.3K | 0 | – | MIT | Yes | GPU |
Other model comparisons
Top open language modelsTop open image modelsTop open audio modelsTop open video modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-image modelsTop open text-to-speech modelsTop open speech-recognition modelsTop open feature-extraction modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open vision-language modelsTop open image-classification modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models