Models#
Attention
The .models namespace is deprecated; import the lazyslide_models package instead.
List all available models. |
Vision models#
chief GitHub Paper Params: 27.5M AGPL-3.0 [Wang et al., 2024] Clinical Histopathology Imaging Evaluation Foundation (CHIEF) |
|
crisp 🤗Hugging Face GitHub Paper Params: 631.2M MIT; CC-BY-NC-ND-4.0 [Zhao et al., 2026] A clinically-oriented foundation model for intraoperative pathology CRISP tile encoder for frozen sections. |
|
crown 🤗Hugging Face GitHub Paper Apache-2.0 [Zheng et al., 2026] A universal visual foundation model for computational cytopathology CROWN tile encoder for cytology. |
|
ctranspath GitHub Paper Params: 27.5M GPL-3.0 [Wang et al., 2022] Transformer-based unsupervised contrastive learning for histopathological image classification |
|
gpfm 🤗Hugging Face GitHub Paper Params: 303M CC BY-NC-ND 4.0 [Ma et al., 2025] Generalizable Pathology Foundation Model |
|
genbio-pathfm 🤗Hugging Face GitHub Paper Params: 1.1B GenBio AI Community License [Kapse et al., 2026] A state-of-the-art histopathology foundation model trained with JEDI (JEPA + DINO) |
|
gigapath 🤗Hugging Face GitHub Paper Params: 1.13B Apache 2.0 with conditions [Xu et al., 2024] A whole-slide foundation model for digital pathology Prov-GigaPath tile encoder. |
|
gigapath-flash 🤗Hugging Face GitHub Paper Params: 21.7M Apache 2.0 [Usuyama et al., 2026] An efficient whole-slide foundation model for digital pathology GigaPath-Flash tile encoder: a DINOv2-small ViT-S/16 with SwiGLU FFN. |
|
h0-mini 🤗Hugging Face GitHub Paper Params: 85.7M CC-BY-NC-ND-4.0 [Filiot et al., 2025] A distilled version of H-optimus-0 |
|
h-optimus-0 🤗Hugging Face GitHub Params: 1.13B Apache 2.0 [Saillard et al., 2024] Vision foundation model |
|
h-optimus-1 🤗Hugging Face GitHub Params: 1.13B CC-BY-NC-ND-4.0 [Bioptimus, 2025] Vision foundation model |
|
hibou-b 🤗Hugging Face GitHub Paper Params: 85.7M Apache 2.0 [Nechaev et al., 2024] A family of foundational vision transformers for pathology |
|
hibou-l 🤗Hugging Face GitHub Paper Params: 303.7M Apache 2.0 [Nechaev et al., 2024] A family of foundational vision transformers for pathology |
|
lunit-dino-s8 🤗Hugging Face GitHub Paper Params: 21.7M lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets |
|
lunit-dino-s8-moozy 🤗Hugging Face GitHub Paper Params: 21.7M lunit-non-commercial [Kang et al., 2023] Lunit DINO ViT-S/8 with the preprocessing MOOZY was trained on |
|
lunit-dino-s16 🤗Hugging Face GitHub Paper Params: 21.1M lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets |
|
lunit-bt 🤗Hugging Face GitHub Paper Params: 23.6M lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets |
|
lunit-mocov2 🤗Hugging Face GitHub Paper Params: 23.6M lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets |
|
lunit-swav 🤗Hugging Face GitHub Paper Params: 23.6M lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets |
|
mstar 🤗Hugging Face GitHub Paper Params: 303.4M CC-BY-NC-ND-4.0 [Xu et al., 2025] A multimodal knowledge-enhanced whole-slide pathology foundation model mSTAR tile encoder: a ViT-L/16 distilled with pathology reports and RNA-Seq. |
|
mascaret 🤗Hugging Face Paper Params: 1.14B Waiv custom non-commercial license [Filiot et al., 2026] Robustifying pathology foundation models via fine-tuning Mascaret: DINOv2-giant robustness-finetuned from |
|
midnight 🤗Hugging Face GitHub Paper Params: 1.14B MIT [Karasikov et al., 2025] Training state-of-the-art pathology foundation models with orders of magnitude less data |
|
open-midnight 🤗Hugging Face GitHub Params: 1.1B Apache 2.0 [Kaplan et al., 2025] Open replication of Midnight, a state-of-the-art pathology foundation model trained on 12K slides |
|
path_orchestra 🤗Hugging Face GitHub CC-BY-NC-ND-4.0 [Yan et al., 2025] Foundation Model for Computational Pathology |
|
phaet 🤗Hugging Face Paper Params: 303.4M Waiv custom non-commercial license [Filiot et al., 2026] Robustifying pathology foundation models via fine-tuning Phaet: DINOv2-large robustness-finetuned from |
|
phikon 🤗Hugging Face GitHub Paper Params: 85.8M Owkin non-commercial license [Filiot et al., 2023] Scaling self-Supervised Learning for histopathology with Masked Image Modeling |
|
phikonv2 🤗Hugging Face GitHub Paper Params: 303.4M Owkin non-commercial license [Filiot et al., 2024] A large and public feature extractor for biomarker prediction |
|
rudolfv2 🤗Hugging Face Params: 1.13B CC-BY-NC-ND-4.0 with supplementary terms [Milbich et al., 2026] A family of robust and efficient open-weights pathology foundation models RudolfV-2: ViT-g/8 pretrained on 300,000 whole slide images. |
|
rudolfv2-b 🤗Hugging Face Params: 85.2M CC-BY-NC-ND-4.0 with supplementary terms [Milbich et al., 2026] A family of robust and efficient open-weights pathology foundation models RudolfV-2-B: ViT-B/8 distilled from RudolfV-2. |
|
rudolfv2-s 🤗Hugging Face Params: 21.4M CC-BY-NC-ND-4.0 with supplementary terms [Milbich et al., 2026] A family of robust and efficient open-weights pathology foundation models RudolfV-2-S: ViT-S/8 distilled from RudolfV-2. |
|
uni 🤗Hugging Face GitHub Paper Params: 303.4M CC-BY-NC-ND-4.0 [Chen et al., 2024] General-purpose self-supervised model for pathology |
|
uni2 🤗Hugging Face GitHub Paper Params: 681.4M CC-BY-NC-ND-4.0 [Chen et al., 2024] An improved version of UNI |
|
virchow 🤗Hugging Face Paper Params: 631.2M Apache 2.0 [Vorontsov et al., 2024] A foundation model for clinical-grade computational pathology and rare cancers detection |
|
virchow2 🤗Hugging Face Paper Params: 631.2M CC-BY-NC-ND-4.0 [Zimmermann et al., 2024] Scaling self-supervised mixed magnification models in pathology |
Multimodal models#
biomedclip 🤗Hugging Face GitHub Paper MIT [Zhang et al., 2024] A biomedical VLP foundation model pretrained on PMC-15M image-text pairs |
|
conch 🤗Hugging Face GitHub Paper Params: 395.2M CC-BY-NC-ND-4.0 [Lu et al., 2024] CONtrastive learning from Captions for Histopathology (CONCH) |
|
conceptclip 🤗Hugging Face GitHub Paper MIT [Nie et al., 2026] An explainable biomedical foundation model via large-scale concept-enhanced vision-language pretraining ConceptCLIP biomedical image-text model. |
|
keep 🤗Hugging Face GitHub Paper MIT [Zhou et al., 2026] Knowledge-enhanced pretraining for vision-language pathology foundation model on cancer diagnosis KEEP (KnowledgE-Enhanced Pathology) image-text model. |
|
musk 🤗Hugging Face GitHub Paper Params: 675.2M CC-BY-NC-ND-4.0 [Xiang et al., 2025] A Vision-Language Foundation Model for Precision Oncology |
|
medsiglip 🤗Hugging Face GitHub Paper Params: 878M health-ai-developer-foundations [Sellergren et al., 2025] MedSigLip is a variant of SigLip from Google for medical image analysis. |
|
omiclip 🤗Hugging Face GitHub Paper Params: 638.5M BSD-3-Clause [Chen et al., 2025] A visual-omics foundation model to bridge histopathology with spatial transcriptomics |
|
plip 🤗Hugging Face GitHub Paper Params: 87.8M Non-commercial [Huang et al., 2023] Pathology Language-Image Pretraining (PLIP) |
|
prism 🤗Hugging Face Paper Params: 557.7M CC-BY-NC-ND-4.0 [Shaikovski et al., 2024] A multi-modal generative foundation model for slide-level histopathology, the Prism models encode slide-level embeddings from |
|
prism2 🤗Hugging Face Paper Params: 4.4B CC-BY-NC-ND-4.0 [Vorontsov et al., 2026] An end-to-end multimodal pathology foundation model with clinical dialogue, PRISM2 encodes slide-level embeddings and generates free-text responses from |
|
quiltnet-b16 🤗Hugging Face GitHub Paper MIT [Ikezogwo et al., 2023] Quilt-1M: histopathology vision-language model trained on 1M image-text pairs |
|
quiltnet-b16-pmb 🤗Hugging Face GitHub Paper MIT [Ikezogwo et al., 2023] Quilt-1M: histopathology vision-language model trained on 1M image-text pairs ViT-B/16 image tower with PubMedBERT text tower. |
|
quiltnet-b32 🤗Hugging Face GitHub Paper MIT [Ikezogwo et al., 2023] Quilt-1M: histopathology vision-language model trained on 1M image-text pairs |
|
titan conch_v1.5 🤗Hugging Face GitHub Paper Params: 158.9M CC-BY-NC-ND-4.0 [Ding et al., 2024] Multimodal whole slide foundation model for pathology |
Segmentation models#
cellpose 🤗Hugging Face GitHub Paper BSD-3-Clause [Stringer et al., 2021] Cell segmentation model |
|
classpose 🤗Hugging Face GitHub Paper Params: 304M CC-BY-NC-4.0 [Mandal et al., 2025] Foundation-model-driven whole-slide-scale cell phenotyping in H&E. |
|
grandqc-artifact GitHub Paper Params: 6.3M CC-BY-NC-SA-4.0 [Weng et al., 2024] Artifact segmentation model from GrandQC |
|
grandqc-tissue GitHub Paper Params: 6.6M CC-BY-NC-SA-4.0 [Weng et al., 2024] Tissue segmentation model from GrandQC |
|
hest-tissue-segmentation 🤗Hugging Face Params: 39.6M CC-BY-NC-SA-4.0 DeepLabV3 model finetuned on HEST-1k and Acrobat for IHC/H&E tissue segmentation. |
|
histoplus 🤗Hugging Face GitHub Paper Params: 47.9M CC-BY-NC-ND-4.0 [Adjadj et al., 2026] Toward comprehensive cellular characterization of H&E slides |
|
instanseg GitHub Paper Params: 3.8M Apache 2.0 [Goldsborough et al., 2024] An embedding-based instance segmentation algorithm optimized for accurate, efficient and portable cell segmentation. |
|
nulite GitHub Paper Params: 47.9M Apache 2.0; CC-BY-NC-SA-4.0 [Tommasino et al., 2024] Nuclei instance segmentation and classification |
|
pathprofiler GitHub Paper Params: 50.3M GPL-3.0 [Haghighat et al., 2022] Tissue segmentation model from PathProfiler |
|
sam GitHub Paper Apache 2.0 SAM model for image segmentation |
|
This is a base class for any models from segmentation models pytorch |
Tile prediction models#
deepspotm 🤗Hugging Face GitHub Paper PolyForm-Noncommercial-1.0.0; CC-BY-NC-SA-4.0 [Nonchev et al., 2026] Transcriptome-wide virtual spatial transcriptomics from H&E images. |
|
focuslitenn focus GitHub Paper Params: 299 Prosperity Public License 3.0.0 [Wang et al., 2020] High efficiency Focus Quality Assessment for digital pathology |
|
pathprofilerqc GitHub Paper Params: 11.2M GPL-3.0 [Haghighat et al., 2022] Quality assessment of histology images |
|
spider-breast 🤗Hugging Face Params: 303.9M CC BY-NC 4.0 Tile classification for breast |
|
spider-colorectal 🤗Hugging Face Params: 303.9M CC BY-NC 4.0 Tile classification for colorectal |
|
spider-skin 🤗Hugging Face Params: 303.9M CC BY-NC 4.0 Tile classification for skin |
|
spider-thorax 🤗Hugging Face Params: 303.9M CC BY-NC 4.0 Tile classification for thorax |
Feature prediction models#
path2space GitHub Paper Params: 1.76B Apache-2.0 [Shulman et al., 2026] Predict spatial gene expression from CTransPath tile features. |
|
stpath 🤗Hugging Face GitHub Paper Params: 49.2M Unlicensed [Huang et al., 2025] Predict spatial gene expression from GigaPath tile features with a spatially aware transformer. |
Slide encoder models#
prism 🤗Hugging Face Paper Params: 557.7M CC-BY-NC-ND-4.0 [Shaikovski et al., 2024] A multi-modal generative foundation model for slide-level histopathology, the Prism models encode slide-level embeddings from |
|
prism2 🤗Hugging Face Paper Params: 4.4B CC-BY-NC-ND-4.0 [Vorontsov et al., 2026] An end-to-end multimodal pathology foundation model with clinical dialogue, PRISM2 encodes slide-level embeddings and generates free-text responses from |
|
titan conch_v1.5 🤗Hugging Face GitHub Paper Params: 158.9M CC-BY-NC-ND-4.0 [Ding et al., 2024] Multimodal whole slide foundation model for pathology |
|
chief-slide-encoder GitHub Paper Params: 1.2M AGPL-3.0 [Wang et al., 2024] Clinical Histopathology Imaging Evaluation Foundation (CHIEF) |
|
gigapath-flash-slide-encoder 🤗Hugging Face GitHub Paper Params: 21.5M Apache 2.0 [Usuyama et al., 2026] An efficient whole-slide foundation model for digital pathology |
|
gigapath-slide-encoder 🤗Hugging Face GitHub Paper Apache 2.0 with conditions [Xu et al., 2024] A whole-slide foundation model for digital pathology |
|
madeleine 🤗Hugging Face GitHub Paper Params: 4.7M CC BY-NC-ND 4.0 [Jaume et al., 2024] Multistain Pretraining for Slide Representation Learning in Pathology MADELEINE H&E slide encoder. |
|
moozy 🤗Hugging Face GitHub Paper Params: 85.77M CC-BY-NC-SA-4.0 [Kotp et al., 2026] A patient-first foundation model for computational pathology MOOZY slide and case encoder. |
Computer vision features#
brightness Mean pixel intensity of a tile |
|
canny Fraction of pixels on a Canny edge |
|
color_deconvolution Paper [Ruifrok and Johnston, 2001] Mean amount of each stain in a tile (hematoxylin, eosin, DAB), by color deconvolution |
|
color_deconvolution_map Paper [Ruifrok and Johnston, 2001] Per-pixel amount of each stain, by color deconvolution |
|
contrast Spread between the 1st and 99th gray-level percentiles |
|
entropy Shannon entropy of the gray-level histogram, in bits |
|
haralick_texture Haralick texture features from the gray-level co-occurrence matrix |
|
saturation Mean saturation of the HSV saturation channel |
|
sharpness Variance of the Laplacian; higher means a sharper tile |
|
sobel Variance of the Sobel gradient, an edge-strength measure |
|
split_rgb Mean red, green and blue intensity of a tile |
Style transfer models#
gigatime GitHub Paper Params: 9M PROV-GIGATIME LICENSE [Valanarasu et al., 2025] Multimodal AI generates virtual population for tumor microenvironment modeling |
|
gigatime-flash 🤗Hugging Face GitHub Paper Params: 23.8M Apache 2.0 [Usuyama et al., 2026] Efficient spatial proteomics prediction from H&E GigaTIME-flash: 23-channel virtual mIF maps from 256x256 H&E tiles. |
|
rosie GitHub Paper Params: 50M CC-BY-NC-4.0 [Wu et al., 2025] AI generation of multiplex immunofluorescence staining from histopathology images |
Image generation models#
cytosyn 🤗Hugging Face Paper Params: 766M CC BY-NC-ND 4.0 A REPA-E Histopathology Image Generation Model |
Base model class#
Base class for models returning one value per pixel. |
|
Base class for models that predict from a tile-feature matrix. |
|
A dense map of named markers, one channel each. |
|
Base class for slide-level encoders. |
|
Base class for models returning named scalars per tile. |
|
A dense map of one or more synthesised RGB stains. |