# Image-to-Image Translation

GenStereo is a model for open-world stereo image generation and unsupervised matching.

CLEAR is an image-to-image generation model based on diffusion transformers, accelerating the pretraining process through convolutional linearization techniques.

A diffusion model-based virtual try-on system capable of generating flattened garments from dressed individuals

StableNormal is a model that achieves stable and sharp normal map generation by reducing diffusion variance

OmniGen is a unified image generation model that supports multiple image generation tasks.

A surface normal map ControlNet model based on Flux.1-dev, developed by the Jasper research team for image-to-image translation tasks.

Stable Diffusion 1.5 is a high-resolution image generation model based on latent diffusion models, capable of generating high-quality images from text descriptions.

A high-resolution image generation model based on latent diffusion models, capable of producing high-quality artistic images from text descriptions.

A high-resolution image generation model based on latent diffusion models, supporting text-to-image and image-to-image translation.

A diffusion model based on the MNIST dataset for generating handwritten digit images.

ControlNet v1.1 is a neural network architecture based on line art image conditions, designed to control pre-trained diffusion models to support additional input conditions.

This is a QR code conditional control network model based on Stable Diffusion v2.1, capable of generating artistic images containing QR codes.

ControlNet v1.1 is an enhanced diffusion model structure based on Stable Diffusion, achieving precise image generation control through openpose pose conditions.

This is a segmentation map-based ControlNet model specifically designed for generating high-quality interior design images, allowing users to precisely control the layout of items within a room through segmentation maps.

ControlNet v1.1 is the successor model to ControlNet v1.0, controlling Stable Diffusion model generation by adding depth image conditions.

ControlNet v1.1 is a diffusion model control network based on line art image conditions, designed to enhance the generative control capabilities of models like Stable Diffusion.

This model is used to predict the strain field distribution of porous microstructures under stress conditions.