Let us control diffusion models!

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Nightly release of ControlNet 1.1

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

SwinIR: Image Restoration Using Swin Transformer (official repository)

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

VRT: A Video Restoration Transformer (official repository)

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

Efficient & Generic Video Super-Resolution

[CVPR2023] Blind Video Deflickering by Neural Filtering with a Flawed Atlas

[CVPR 2024 Oral] Official repository of FMA-Net

PyTorch code for our ICCV 2023 paper "Dual Aggregation Transformer for Image Super-Resolution"

[NeurIPS 2020] Blind Video Temporal Consistency via Deep Video Prior

[CVPR 2024 Highlight] Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

[CVPR 2022] VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution

Official implementation of the paper “Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning”（SIGGRAPH 2022）

Swift Parameter-free Attention Network for Efficient Super-Resolution

PyTorch implementation of "Reference-based Image Super-Resolution with Deformable Attention Transformer (ECCV2022)"

CVPR2024 - Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

(NIPS 2022) Rethinking Alignment in Video Super-Resolution Transformers

Official PyTorch implementation of QuantArt (CVPR2023)

[CVPR 2024] CFAT: Unleashing Triangular Windows for Image Super-resolution

Official implementation of the paper "Z∗: Zero-shot Style Transfer via Attention Rearrangement" a.k.a. "Z∗: Zero-shot Style Transfer via Attention Reweighting" (CVPR2024)

use stable diffusion via ComfyUI inside Nuke

Puff-Net

Code for Learning to Generate Artistic Character Line Drawing