exdysa/dc-ae-f32c32-sana-1.1-diffusers

Original Model Link : https://huggingface.co/mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers

name: dc-ae-f32c32-sana-1.1-diffusers
base_model: mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers
license: mit
pipeline_tag: text-to-image
library_name: diffusers
tasks: feature-extraction
language: en
get_started_code: from diffusers import AutoencoderDC

dc-ae-f32c32-sana-1.1-diffusers includes the original Sana DC-VAE model and a half-precision variant, both moved into a typical diffusers folder layout.

@article{chen2024deep,
  title={Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models},
  author={Chen, Junyu and Cai, Han and Chen, Junsong and Xie, Enze and Yang, Shang and Tang, Haotian and Li, Muyang and Lu, Yao and Han, Song},
  journal={arXiv preprint arXiv:2410.10733},
  year={2024}
}