[TOG 2026] LiveLight: This repo is the official implementation of "LiveLight : Real-time video relighting via interactive control"

Latent Bridge Matching for Fast Image-to-Image Translation (ICCV 2025 Highlight)

Industry leading face manipulation platform

[ICLR 2026] ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

[ECCV 2026] Generate high resolution videos with a custom voice and appearance, based on LTX-2/LTX-2.3 + Identity In-Context LoRA

Official implementation of "🍎APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping"

High-Resolution Image/Video Harmonization [ECCV 2022]

The official implementation of SIGGRAPH Asia 2026 paper "ID-V2V: Identity-preserving Video Restylization"

[SIGGRAPH Asia 2024 & IJCV 2025] Follow-Your-Emoji & Follow-Your-Emoji-Faster: This repo is the official implementation of "Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait An…

[ECCV 2026] MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer

Face Swap Magic - GPU-accelerated face-swap studio with a real-time visual editor — TensorRT inference, NVDEC/NVENC video I/O

ReSwapper aims to reproduce the implementation of inswapper. This repository provides code for training, inference, and includes pretrained weights.

Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

[SIGGRAPH 2026] Official code of the paper "Relit-LiVE: Relight Video by Jointly Learning Environment Video".

GFPGAN 1024

Official Repostitory of "FreeStyle: Free Control of Style Content Generation from Community LoRA Mining "

Official Pytorch implementation of AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising

AVTR-1: Avatars that listen back

official github code for "SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing"

FreeLighting: A Next-generation Image Relighting Model with Background Replica from Any Perspective Angle

[ECCV 2026] Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

AdaRefSR is a novel reference-based one-step diffusion super-resolution framework. Paper was accepted by ICLR2026.

[ECCV 2026 Oral] DreamID-V: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

[ICML 2026] DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation

The official code for paper: GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions (Accepted by AAAI 2025))

The Gaze Correction Camera project is an advanced real-time gaze correction system designed to enhance video communication by improving eye contact. Leveraging state-of-the-art computer vision and …

pytorch implementation of the different DeepGaze models

Unsupervised High-Resolution Portrait Gaze Correction and Animation (TIP 2022)