REDS

The proposed StableVSR is built upon a pre-trained Latent Diffusion Model (LDM) for single image super-resolution (SISR). We use Stable Diffusion ×4 Upscaler (SD×4Upscaler)2. It follows the LDM framework [31], which performs the iterative refinement process into a latent space and uses the VAE decoder D [11] to decode latents into RGB images.