clipseg-rd64-refined
clipseg-rd64-refined is a CLIP model available on HuggingFace without a declared task pipeline. Consult the model card for intended use cases and fine-tuning instructions.
1,789,787 ↓ · 140 ♡
image segmentation models
9 models · ranked by HuggingFace downloads
BiRefNet
BiRefNet has no registered pipeline_tag. It likely serves as a pretraining base or a specialized evaluation model — review the model card before use.
789,967 ↓ · 596 ♡
RMBG-2.0
RMBG-2.0 has no registered pipeline_tag. It likely serves as a pretraining base or a specialized evaluation model — review the model card before use.
613,006 ↓ · 1,270 ♡
mask2former-swin-large-ade-semantic
mask2former-swin-large-ade-semantic is an open-source image-segmentation model available on HuggingFace. Details are sourced from the public model registry.
392,719 ↓ · 21 ♡
segformer-b0-finetuned-ade-512-512
SegFormer-B0 fine-tuned on ADE20K at 512×512 resolution, providing semantic segmentation of 150 scene categories. The B0 variant is the smallest in the SegFormer family, optimized for speed over maximum accuracy.
343,393 ↓ · 190 ♡
RMBG-1.4
RMBG-1.4 is released without a specific pipeline. Common uses include feature extraction, encoder probing, and domain-specific fine-tuning.
324,866 ↓ · 1,983 ♡
face-parsing
A SegFormer-based face parsing model from jonathandinu that segments facial regions (hair, eyes, nose, mouth, skin, etc.) from portrait images. Trained on CelebAMask-HQ, it outputs per-pixel class labels for 19 semantic facial regions.
311,925 ↓ · 220 ♡
segformer_b2_clothes
segformer_b2_clothes is an open-source image-segmentation model available on HuggingFace. Details are sourced from the public model registry.
311,596 ↓ · 500 ♡
segformer-b0-finetuned-ade-512-512
segformer-b0-finetuned-ade-512-512 is an open-source image-segmentation model available on HuggingFace. Details are sourced from the public model registry.
304,124 ↓ · 1 ♡