Model Zoo

Model Zoo#

This section provides an overview of models in LazySlide.

Important

Disclaimer: The usage of any model in LazySlide is subject to the terms and conditions of the respective model’s license. Please ensure you comply with the license terms before using any model. If you use a model in your research, please cite the original paper or repository as appropriate. LazySlide does not redistribute any source code that’s not compatible with LazySlide’s MIT license.

Note

As of LazySlide version 0.11.0, we have transferred all LazySlide models to a separate package, lazyslide-models. All models are now imported from lazyslide_models instead of lazyslide.models. Please make sure to update your code accordingly.

Get model names#

In most of the cases, you only need to pass the model name as string to the function, for example, to use the UNI model in feature extraction, you can do: zs.tl.feature_extraction(wsi, model="uni").

To get all available models, you can use the list_models function:

from lazyslide_models import list_models

models = list_models()

You can also filter models by type:

from lazyslide_models import list_models

vision_models = list_models("vision")  # for vision models only
multimodal_models = list_models("multimodal")  # for multimodal models only
segmentation_models = list_models("segmentation")  # for segmentation models only
tile_prediction_models = list_models("tile_prediction")  # for tile_prediction models only

For feature extraction, we also support all timm models with feature extraction head. You can list them with:

from timm import list_models

timm_models = list_models()

To retrive a specific model class:

from lazyslide_models import MODEL_REGISTRY
model_module = MODEL_REGISTRY['instanseg']
model = model_module()  # Initiate the model

Get access to gated models#

indicates the model is publicly available. You can use it without a Hugging Face account or requesting access.

indicates the model is gated and requires permission. You must apply for access via the Hugging Face model card or the model’s repository.

To access gated models, follow these steps:

  1. Create a Hugging Face account: https://huggingface.co/

  2. Visit the model card page and request access. You can also use the Hugging Face button provided for each model below.

  3. In your account settings, go to Access Tokens and create a new token with the required permissions (read access is sufficient). This token will grant access to any new models you gain permission for in the future.

  4. Log in using your token to access gated models. Run the following command:

    hf auth login --token YOUR_TOKEN

Below is a list of available models categorized by their type:

Models#

Attention

The .models is already deprecated, please import from lazyslide_models instead.

list_models

List all available models.

Vision models#

CHIEF

GitHub Paper Params: 27.5M 768 features FLOPs: 8.99G AGPL-3.0 [Wang et al., 2024] Clinical Histopathology Imaging Evaluation Foundation (CHIEF)

CTransPath

GitHub Paper Params: 27.5M 768 features FLOPs: 8.99G GPL-3.0 [Wang et al., 2022] Transformer-based unsupervised contrastive learning for histopathological image classification

GPFM

🤗Hugging Face GitHub Paper Params: 303M 1024 features FLOPs: 155.53G CC BY-NC-ND 4.0 [Ma et al., 2025] Generalizable Pathology Foundation Model

GenBioPathFM

🤗Hugging Face GitHub Paper Params: 1.1B 4608 features 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 1536 features Apache 2.0 with conditions [Xu et al., 2024] A whole-slide foundation model for digital pathology

H0Mini

🤗Hugging Face GitHub Paper Params: 85.7M 1536 features FLOPs: 44.57G CC-BY-NC-ND-4.0 [Filiot et al., 2025] A distilled version of H-optimus-0

HOptimus0

🤗Hugging Face GitHub Params: 1.13B 1536 features Apache 2.0 [Saillard et al., 2024] Vision foundation model

HOptimus1

🤗Hugging Face GitHub Params: 1.13B 1536 features FLOPs: 591.61G CC-BY-NC-ND-4.0 [Bioptimus, 2025] Vision foundation model

HibouB

🤗Hugging Face GitHub Paper Params: 85.7M 768 features FLOPs: 47.08G Apache 2.0 [Nechaev et al., 2024] A family of foundational vision transformers for pathology

HibouL

🤗Hugging Face GitHub Paper Params: 303.7M 1024 features FLOPs: 164.85G Apache 2.0 [Nechaev et al., 2024] A family of foundational vision transformers for pathology

LunitDINOPatch8

🤗Hugging Face GitHub Paper Params: 21.7M 384 features lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

LunitDINOPatch16

🤗Hugging Face GitHub Paper Params: 21.1M 384 features lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

LunitResNet50BT

🤗Hugging Face GitHub Paper Params: 23.6M 2048 features lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

LunitResNet50MoCoV2

🤗Hugging Face GitHub Paper Params: 23.6M 2048 features lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

LunitResNet50SwAV

🤗Hugging Face GitHub Paper Params: 23.6M 2048 features lunit-non-commercial [Kang et al., 2023] Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

Midnight

🤗Hugging Face GitHub Paper Params: 1.14B 3072 features FLOPs: 582.55G MIT [Karasikov et al., 2025] Training state-of-the-art pathology foundation models with orders of magnitude less data

OpenMidnight

🤗Hugging Face GitHub Params: 1.1B 1536 features Apache 2.0 [Kaplan et al., 2025] Open replication of Midnight, a state-of-the-art pathology foundation model trained on 12K slides

PathOrchestra

🤗Hugging Face GitHub CC-BY-NC-ND-4.0 [Yan et al., 2025] Foundation Model for Computational Pathology

Phikon

🤗Hugging Face GitHub Paper Params: 85.8M 768 features FLOPs: 33.70G 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 1024 features FLOPs: 119.29G Owkin non-commercial license [Filiot et al., 2024] A large and public feature extractor for biomarker prediction

UNI

🤗Hugging Face GitHub Paper Params: 303.4M 1024 features 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 1536 features CC-BY-NC-ND-4.0 [Chen et al., 2024] An improved version of UNI

Virchow

🤗Hugging Face Paper Params: 631.2M 2560 features FLOPs: 323.93G 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 2560 features FLOPs: 328.97G 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 512 features 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 512 features FLOPs: 35.08G CC-BY-NC-ND-4.0 [Lu et al., 2024] CONtrastive learning from Captions for Histopathology (CONCH)

MUSK

🤗Hugging Face GitHub Paper Params: 675.2M 1024 features FLOPs: 382.13G 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 1152 features 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 FLOPs: 156.94G 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 512 features FLOPs: 8.73G 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 Virchow.

QuiltNetB16

🤗Hugging Face GitHub Paper 512 features MIT [Ikezogwo et al., 2023] Quilt-1M: histopathology vision-language model trained on 1M image-text pairs

QuiltNetB16PMB

🤗Hugging Face GitHub Paper 512 features 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.

QuiltNetB32

🤗Hugging Face GitHub Paper 512 features MIT [Ikezogwo et al., 2023] Quilt-1M: histopathology vision-language model trained on 1M image-text pairs

Titan

🤗Hugging Face GitHub Paper Params: 158.9M 768 features 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

GrandQCArtifact

GitHub Paper Params: 6.3M FLOPs: 4.63G CC-BY-NC-SA-4.0 [Weng et al., 2024] Artifact segmentation model from GrandQC

GrandQCTissue

GitHub Paper Params: 6.6M FLOPs: 8.46G CC-BY-NC-SA-4.0 [Weng et al., 2024] Tissue segmentation model from GrandQC

HESTTissueSegmentation

🤗Hugging Face Params: 39.6M FLOPs: 62.61G 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 FLOPs: 3.81T CC-BY-NC-ND-4.0 [Adjadj et al., 2025] Towards Comprehensive Cellular Characterisation of H&E slides

Instanseg

GitHub Paper Params: 3.8M FLOPs: 27.55G 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 FLOPs: 48.10G Apache 2.0; CC-BY-NC-SA-4.0 [Tommasino et al., 2024] Nuclei instance segmentation and classification

PathProfilerTissueSegmentation

GitHub Paper Params: 50.3M FLOPs: 44.94G GPL-3.0 [Haghighat et al., 2022] Tissue segmentation model from PathProfiler

SAM

GitHub Paper FLOPs: 975.67G Apache 2.0 SAM model for image segmentation

SMPBase

This is a base class for any models from segmentation models pytorch

Tile prediction models#

FocusLiteNN

GitHub Paper Params: 299 FLOPs: 1.53M Prosperity Public License 3.0.0 [Wang et al., 2020] High efficiency Focus Quality Assessment for digital pathology

PathProfilerQC

GitHub Paper Params: 11.2M FLOPs: 3.63G GPL-3.0 [Haghighat et al., 2022] Quality assessment of histology images

SpiderBreast

🤗Hugging Face Params: 303.9M FLOPs: 164.85G CC BY-NC 4.0 Tile classification for breast

SpiderColorectal

🤗Hugging Face Params: 303.9M FLOPs: 164.85G CC BY-NC 4.0 Tile classification for colorectal

SpiderSkin

🤗Hugging Face Params: 303.9M FLOPs: 164.85G CC BY-NC 4.0 Tile classification for skin

SpiderThorax

🤗Hugging Face Params: 303.9M FLOPs: 164.85G CC BY-NC 4.0 Tile classification for thorax

Slide encoder models#

multimodal.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 Virchow.

multimodal.Titan

🤗Hugging Face GitHub Paper Params: 158.9M 768 features CC-BY-NC-ND-4.0 [Ding et al., 2024] Multimodal whole slide foundation model for pathology

vision.CHIEFSlideEncoder

GitHub Paper Params: 1.2M FLOPs: 131.28M AGPL-3.0 [Wang et al., 2024] Clinical Histopathology Imaging Evaluation Foundation (CHIEF)

vision.GigaPathSlideEncoder

🤗Hugging Face GitHub Paper Apache 2.0 with conditions [Xu et al., 2024] A whole-slide foundation model for digital pathology

vision.MadeleineSlideEncoder

🤗Hugging Face GitHub Paper Params: 3.2M FLOPs: 421.63M CC BY-NC-ND 4.0 [Jaume et al., 2024] Multistain Pretraining for Slide Representation Learning in Pathology

vision.Moozy

🤗Hugging Face GitHub Paper Params: 85.77M 768 features 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

Canny

Contrast

Entropy

HaralickTexture

Saturation

Sharpness

Sobel

SplitRGB

Style transfer models#

GigaTIME

GitHub Paper Params: 9M FLOPs: 52.88G PROV-GIGATIME LICENSE [Valanarasu et al., 2025] Multimodal AI generates virtual population for tumor microenvironment modeling

ROSIE

GitHub Paper Params: 50M FLOPs: 17.37G CC-BY-NC-4.0 [Wu et al., 2025] AI generation of multiplex immunofluorescence staining from histopathology images

Image generation models#

CytoSyn

GitHub Paper Params: 766M CC BY-NC-ND 4.0 A REPA-E Histopathology Image Generation Model

Base model class#

ImageGenerationModel

ImageModel

ImageTextModel

ModelBase

SegmentationModel

SlideEncoderModel

Base class for slide-level encoders.

StyleTransferModel

TilePredictionModel

TimmModel

Use model in an offline environment#

For huggingface gated models, to run in an environment without internet access. The model must be downloaded first, for example, run the model initiation code on an HPC login node or your local machine.

from huggingface_hub import snapshot_download

snapshot_download("model-repo-name")

hf download model-repo-name

If you need to copy from your local machine to an HPC login node, you would need to mimic the same directory structure as the model repository. The huggingface model is by default downloaded to ~/.cache/huggingface. This is controlled by the environment variable HF_HOME.

You can either copy the whole local ~/.cache/huggingface directory to the same path on HPC login node, or copy the specific model directory to the HPC login node.

When you submit a job to compute node without internet connection. Please set the environment variable HF_HUB_OFFLINE=1 so huggingface will not make any HTTP request.

Alternatively, You can set it at the start of your python session

import os
os.environ['HF_HUB_OFFLINE'] = 1

How to use new models#

If you want to use a model that’s not available in LazySlide, you can still use it by wrapping it with LazySlide’s model classes. If you are familiar with class inheritance, the following example should be quite easy for you.

Suppose you have a new vision model and you want to use it for feature extraction, you can simply inherit from one of our base classes (here is ImageModel) and implement necessary methods.

import torch

from lazyslide_models.base import ImageModel

class MyGreatModel(ImageModel):

    def __init__(self):
        from huggingface_hub import hf_hub_download

        model_file = hf_hub_download("my-repo/my-great-model", "model.pt")
        self.model = torch.jit.load(model_file, map_location="cpu")
        self.model.eval()

    # Define the transformation here, will automatically be applied
    def get_transform(self):
        return self.model.get_custom_transform()

    @torch.inference_mode()
    def encode_image(self, image):
        """
        Encode the input image using the model.
        The model should expect a tensor of shape [B, C, H, W].
        """
        output = self.model(image)
        return output

Once you finish with implementing your own model, you are welcomed to submit it to LazySlide. Please take a look at Contribution to new models