---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---

# LUMIC

<!-- Provide a quick summary of what the model is/does. -->
Latent diffUsion for Multiplexed Images of Cells is a diffusion model pipeline developed to generate the high-content fluorescent microscopy images of different cell type and chemical compound interactions. LUMIC combines diffusion models with DINO (self-Distillation with NO labels), a vision-transformer based, self-supervised method that can be trained on images to learn feature embeddings, and HGraph2Graph, a hierarchical graph encoder-decoder to represent chemicals.

- **1d_diff_75000.pt**: 1D diffusion model checkpoint
- **dino_checkpoint.pth**: DINO checkpoint trained on all images
- **lowres_imagen_150000**: Low-res diffusion model checkpoint
- **model.ckpt.156260**: HGraph2graph checkpoint trained on ZINC 250K and our compounds
- **tensors-[0-6].pkl**: Preprocessed tensors for Hgraph2Graph
- **upsample_1000000.pt**: High-res diffusion model checkpoint

[Github repo](https://github.com/)