(CVPR 2022) HairMapper: Removing Hair from Portraits Using GANs.

Stable-Hair: Real-World Hair Transfer via Diffusion Model

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Kolors Team

ComfyUI nodes for LivePortrait

LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Bring portraits to life!

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

ComfyUI BrushNet nodes

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

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

DeepFaceLab is the leading software for creating deepfakes.

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

Next generation face swapper and enhancer

Next generation face swapper and enhancer

Wav2Lip UHQ extension for Automatic1111

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

SeetaFace 2: open source, full stack face recognization toolkit.

Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Character Animation (AnimateAnyone, Face Reenactment)

Official implementations for paper: Anydoor: zero-shot object-level image customization

[CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On