Downloads · 30 days
0
VE-Loss
CVLUESTC/VE-Loss
VE-Loss is a text-to-image model from CVLUESTC. Use it when you need an image from a text prompt. The card lists the license as apache-2.0.
Access
Public
Updated Apr 3, 2026
Repo size
6.4 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt6.1 GB · 95%
At a glance
- Task
- Text-to-Image
- License
- apache-2.0
- Access
- Public
- Created
- Mar 9, 2026
- Updated
- Apr 3, 2026
- SHA
- 9bafc6c9
Model card
From the Hugging Face model README
Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models (CVPR 2026)
If you find our work useful, please consider citing:
@article{li2026taming,
title={Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models},
author={Li, Qifan and Zhou, Xingyu and Zhang, Jinhua and You, Weiyi and Gu, Shuhang},
journal={arXiv preprint arXiv:2603.21085},
year={2026}
}
- Task
- Text-to-Image
- License
- apache-2.0
- Created
- Mar 9, 2026
- Updated
- Apr 3, 2026