Compressing Inside Generating: A Latent Domain Codec for AI-Generated Images
Yuxu Chen, Zhenhao Sun, Yuliang Huang, Lei Deng, Wei Han, Bo Bob Bai, Shiqi Wang · 2025
Latent diffusion models (LDMs) have emerged as a prominent framework for image generation, consisting of a diffusion model$\mathcal{M}$and a VAE decoder$\mathcal{D}$. High-quality image generation models are large and computationally intensive. As a result, image generation is typically performed on cloud servers, with the generated images then transmitted to edge devices.