Downloads · 30 days
0
TerDiT
lucky-lance/TerDiT
TerDiT is a unconditional image generation model from lucky-lance. Use it for the unconditional image generation task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains the trained model for the paper "TerDiT: Ternary Diffusion Models with Transformers"
Access
Public
Updated Apr 15, 2025
Repo size
2.4 GB
Likes
13
Public
Repo makeup
Click a slice to open those files.
.pth2.4 GB · 100%
At a glance
- Task
- Unconditional Image Generation
- License
- mit
- Access
- Public
- Created
- May 18, 2024
- Updated
- Apr 15, 2025
- SHA
- 95795f0e
Datasets
Model card
From the Hugging Face model README
TerDiT
This repository contains the trained model for the paper "TerDiT: Ternary Diffusion Models with Transformers"
Code: https://github.com/Lucky-Lance/TerDiT
256x256 4.2B model: TerDiT-4.2B
256x256 600M model: TerDiT-600M
512x512 4.2B model: TerDiT-4.2B
The codebase is extended from Large-DiT-ImageNet and highly motivated by Lumina-T2X. Thanks for their awesome work!
- Task
- Unconditional Image Generation
- License
- mit
- Languages
- en
- Created
- May 18, 2024
- Updated
- Apr 15, 2025