Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

[TMM 2025] StableIdentity: Inserting Anybody into Anywhere at First Sight 🔥

[TIP 2025] CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models 🔥

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

[ICCV 2023] StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Scalable and memory-optimized training of diffusion models

[MM24] Official codes and datasets for ACM MM24 paper "Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models".

HandBrake's development repository

EasyPortrait - Face Parsing and Portrait Segmentation Dataset

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

[ICCV 2021 Oral] Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Infinite Photorealistic Worlds using Procedural Generation

Official Code for DragGAN (SIGGRAPH 2023)

Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation map.

Experiments w/ ChatGPT, LangChain, local LLMs

High-performance In-browser LLM Inference Engine

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

中文nlp解决方案(大模型、数据、模型、训练、推理)

Power CLI and Workflow manager for LLMs (core package)

文生图大模型训练工具箱 （完整封装stable diffusion全量微调训练流程， 可训练定制自己的独特风格、人物概念，开箱即用， 含自动图像标注、权重转换、训练参数配置等）

Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization

A simple face detect and alignment method, which is easy and stable.