---
license: mit
datasets:
- imagenet-1k
language:
- en
pipeline_tag: unconditional-image-generation
tags:
- art
---

# TerDiT

This repository contains the trained model for the paper "TerDiT: Ternary Diffusion Models with Transformers"

256x256 4.2B model: [TerDiT-4.2B](https://huggingface.co/lucky-lance/TerDiT/tree/main/3B_1180000)

256x256 600M model: [TerDiT-600M](https://huggingface.co/lucky-lance/TerDiT/tree/main/600M_1750000)

512x512 4.2B model: [TerDiT-4.2B](https://huggingface.co/lucky-lance/TerDiT/tree/main/3B_512_1900000)

The codebase is extended from [Large-DiT-ImageNet](https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/Large-DiT-ImageNet) and highly motivated by [Lumina-T2X](https://github.com/Alpha-VLLM/Lumina-T2X). Thanks for their awesome work!