1,054 models · refreshed nightly

Image segmentation models

Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All text-generation 410 text-to-image 153 ASR 92 image-text-to-text 89 sentence-similarity 61 feature-extraction 47 translation 47 text-classification 42 image-classification 34 token-classification 27 text-to-speech 12 audio-classification 11 object-detection 11 summarization 9 image-segmentation 9

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

9 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	clipseg-rd64-refined CIDAS · image-segmentation	150 M	—	✓ apache-2.0	1.1 M	from 1.2 GB
02	BiRefNet ZhengPeng7 · image-segmentation	220 M	—	✓ mit	1.0 M	from 1.0 GB
03	RMBG-2.0 briaai · image-segmentation · gated	220 M	—	other	628 K	from 1.5 GB
04	mask2former-swin-large-cityscapes-semantic facebook · image-segmentation	220 M	—	other	443 K	from 1.5 GB
05	segformer-b0-finetuned-ade-512-512 nvidia · image-segmentation	<0.1 M	—	other	357 K	from 0.5 GB
06	RMBG-1.4 briaai · image-segmentation	40 M	—	other	356 K	from 0.7 GB
07	mask2former-swin-large-ade-semantic facebook · image-segmentation	220 M	—	other	300 K	from 1.5 GB
08	segformer-b2-finetuned-ade-512-512 nvidia · image-segmentation	—	—	other	281 K	—
09	segformer_b2_clothes mattmdjaga · image-segmentation	30 M	—	other	224 K	from 0.6 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.