Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
This work addresses the problem of real-time image generation for applications requiring fast inference, though it is incremental as it builds on prior methods like DiffusionGAN and Wavelet Diffusion.
The paper tackles the slow inference speed of diffusion models for image generation by introducing the Latent Denoising Diffusion GAN, which uses pre-trained autoencoders to compress images into a latent space, achieving state-of-the-art running speed among diffusion models with improvements in image quality and diversity.
Diffusion models are emerging as powerful solutions for generating high-fidelity and diverse images, often surpassing GANs under many circumstances. However, their slow inference speed hinders their potential for real-time applications. To address this, DiffusionGAN leveraged a conditional GAN to drastically reduce the denoising steps and speed up inference. Its advancement, Wavelet Diffusion, further accelerated the process by converting data into wavelet space, thus enhancing efficiency. Nonetheless, these models still fall short of GANs in terms of speed and image quality. To bridge these gaps, this paper introduces the Latent Denoising Diffusion GAN, which employs pre-trained autoencoders to compress images into a compact latent space, significantly improving inference speed and image quality. Furthermore, we propose a Weighted Learning strategy to enhance diversity and image quality. Experimental results on the CIFAR-10, CelebA-HQ, and LSUN-Church datasets prove that our model achieves state-of-the-art running speed among diffusion models. Compared to its predecessors, DiffusionGAN and Wavelet Diffusion, our model shows remarkable improvements in all evaluation metrics. Code and pre-trained checkpoints: \url{https://github.com/thanhluantrinh/LDDGAN.git}