LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Sadat, Seyedmorteza, Buhmann, Jakob, Bradley, Derek, Hilliges, Otmar, Weber, Romann M.
–arXiv.org Artificial Intelligence
Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains underexplored. In this paper, we introduce LiteVAE, a family of autoencoders for LDMs that leverage the 2D discrete wavelet transform to enhance scalability and computational efficiency over standard variational autoencoders (VAEs) with no sacrifice in output quality. We also investigate the training methodologies and the decoder architecture of LiteVAE and propose several enhancements that improve the training dynamics and reconstruction quality. Our base LiteVAE model matches the quality of the established VAEs in current LDMs with a six-fold reduction in encoder parameters, leading to faster training and lower GPU memory requirements, while our larger model outperforms VAEs of comparable complexity across all evaluated metrics (rFID, LPIPS, PSNR, and SSIM).
arXiv.org Artificial Intelligence
May-23-2024
- Country:
- North America
- United States
- Washington > King County
- Seattle (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- California
- Los Angeles County > Long Beach (0.04)
- San Diego County > San Diego (0.04)
- Washington > King County
- Canada > British Columbia
- United States
- Europe
- Austria (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- Italy
- Veneto > Venice (0.04)
- Calabria > Catanzaro Province
- Catanzaro (0.04)
- France > Île-de-France
- Africa > Rwanda
- North America
- Genre:
- Research Report (1.00)
- Technology: