GigaTIME-flash

GigaTIME-flash is a lightweight, efficient variant of GigaTIME. It pairs a GigaPath-flash encoder with a convolutional decoder to translate routine H&E tiles into 21-channel virtual mIF maps.

📄 Paper • Code • License

Model Family

Model	Description	Weights	Code	Paper	License
GigaPath	Whole-slide foundation model	link	link	Nature (2024)	Apache-2.0
GigaPath-Flash	Efficient whole-slide foundation model	link	link	arXiv (2026)	Apache-2.0
GigaTIME	Spatial proteomics prediction from H&E	link	link	Cell (2026)	Apache-2.0
GigaTIME-Flash	Efficient spatial proteomics prediction from H&E	link	link	arXiv (2026)	Apache-2.0

What is this model?

• Task: GigaTIME-flash takes in an H&E slide and creates a virtual mIF slide across 21 protein channels.
• Inputs: The model processes the H&E slide at a tile size of 256×256. The input is a tensor of shape [B, 3, 256, 256].
• Outputs: The output is the 23-channel spatial proteomics maps (2 are background channels) of shape [B, 23, 256, 256]. The order of protein channels can be found in config.json and in the code.

Quickstart

You need to agree to the terms to access the model. Once you have access, set your HuggingFace read-only token as an environment variable:

export HF_TOKEN=<huggingface read-only token>

Then download and load the model:

import os
import torch
from huggingface_hub import snapshot_download

repo_id = "prov-gigatime/GigaTIME-flash"
local_dir = snapshot_download(repo_id=repo_id)

weights_path = os.path.join(local_dir, "model.pth")
state_dict = torch.load(weights_path, map_location="cpu")
model.load_state_dict(state_dict)

Checkout the scripts/gigatime_flash_testing.ipynb notebook at the GitHub Repo for a full inference example.

Model Uses

Intended Use

The data, code, and model checkpoints are intended to be used solely for (I) future research on pathology AI models and (II) reproducibility of the experimental results reported in the reference paper. The data, code, and model checkpoints are not intended to be used in clinical care or for any clinical decision-making purposes.

Primary Intended Use

The primary intended use is to support AI researchers reproducing and building on top of this work. GigaTIME-flash should be helpful for generating virtual mIF profiles from routine H&E pathology slides.

Out-of-Scope Use

Any deployed use case of the model --- commercial or otherwise --- is out of scope. Although we evaluated the models using a broad set of publicly-available research benchmarks, the models and evaluations are intended for research use only and not intended for deployed use cases.

License Notice

The model is not intended or made available for clinical use as a medical device, clinical support, diagnostic tool, or other technology intended to be used in the diagnosis, cure, mitigation, treatment, or prevention of disease or other conditions. The model is not designed or intended to be a substitute for professional medical advice, diagnosis, treatment, or judgment and should not be used as such. All users are responsible for reviewing the output of the developed model to determine whether the model meets the user's needs and for validating and evaluating the model before any clinical use.

Citation

@article{usuyama2026gigapathflash,
  title={{GigaPath-Flash} and {GigaTIME-Flash}: Efficient Pathology Foundation Models for Whole-Slide and Tumor Microenvironment Analysis},
  author={Usuyama, Naoto and Valanarasu, Jeya Maria Jose and Yao, Sicong and Xu, Hanwen and Bagga, Jaspreet and Qin, Guanghui and Kramer, Robert E. and Wong, Cliff and Lee, Soohee and Qiu, Hao and Zhao, Theodore Zhengde and Ben Shimol, Racheli and Crabtree, Angela and Matlock, Kevin and Lozano Garcia, Eduardo Alejandro and Sangani, Naiteek and Santamaria-Pang, Alberto and Rokuss, Maximilian and Hasija, Yashna and Patel, Naisargi Manishkumar and Entenmann, Jason and Bartlett, Alexandra Q. and Wright, Bill J. and Fox, Bernard A. and Piening, Brian and Zhang, Sheng and Wang, Sheng and Naumann, Tristan and Bifulco, Carlo and Poon, Hoifung},
  journal={arXiv preprint arXiv:2607.18218},
  year={2026},
  doi={10.48550/arXiv.2607.18218},
  url={https://arxiv.org/abs/2607.18218}
}

@article{valanarasu2025multimodal,
  title={Multimodal AI generates virtual population for tumor microenvironment modeling},
  author={Valanarasu, Jeya Maria Jose and Xu, Hanwen and Usuyama, Naoto and Kim, Chanwoo and Wong, Cliff and Argaw, Peniel and Shimol, Racheli Ben and Crabtree, Angela and Matlock, Kevin and Bartlett, Alexandra Q and others},
  journal={Cell},
  year={2025},
  publisher={Elsevier}
}