lazyslide_models.style_transfer.GigaTIMEFlash

lazyslide_models.style_transfer.GigaTIMEFlash#

class GigaTIMEFlash(model_path=None, token=None)#

Bases: MarkerMapModel

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.

The HuggingFace repo ships only model.pth and config.json — the architecture lives in the upstream notebook scripts/gigatime_flash_testing.ipynb and is reproduced below.

predict(image)#

Predict from a [B, C, H, W] tile batch.

Returns a float tensor of shape [B, C, H, W], already activated and within output_range when that is declared.