#GAN Compression

GAN Compression efficiently reduces computational loads of popular conditional GANs like pix2pix and CycleGAN by up to 29 times while preserving visual quality. Supporting various architectures, including MUNIT, this method ensures broad applicability in image translation. Demos demonstrate models achieving 8FPS on Jetson Nano GPU. Comprehensive resources are available for optimized application.

The Spatially Incremental Generative Engine (SIGE) optimizes image editing by focusing computation on edited regions, thus decreasing computational workload for models like DDPM, Stable Diffusion, and GauGAN without compromising image quality. Featuring significant performance gains on NVIDIA RTX 3090 and Apple M1 hardware, SIGE leverages GAN Compression among other techniques. It offers broad application support, including Stable Diffusion compatibility and Mac MPS backend optimization, particularly benefiting the M1 MacBook Pro. The project provides accessible resources, enabling comprehensive experimentation and benchmarking on widely used platforms.