# Image Super-Resolution

HiT-SR is a general strategy for enhancing transformer-based super-resolution methods, improving existing model structures to achieve better super-resolution performance while reducing computational burden.

A ControlNet model developed by Jasper Research Team for low-resolution image upscaling

A ControlNet model developed by the Jasper research team for low-resolution image upscaling

GAN-based super-resolution technology for enhancing the quality of generated images

An image-to-image processing adapter based on the ControlNet architecture, specifically designed for the Stable Diffusion SD1.5 model to enable fine control over the image generation process.

Lightweight Swin2SR image super-resolution model that can upscale image resolution by 2 times

A compressed image super-resolution model based on Swin2SR architecture, capable of upscaling image resolution by 4 times

A classical image super-resolution model based on Swin2SR architecture, capable of upscaling image resolution by 4 times

A classical image super-resolution model based on Swin2SR architecture, capable of upscaling image resolution by 2 times

A text-guided latent super-resolution tool based on diffusion models, capable of upscaling low-resolution images by 4 times

ControlNet v1.1 is a neural network architecture based on diffusion models, designed to control pre-trained large diffusion models by adding additional conditions.