guanjz20

skills. Skills for Real Engineers. Straight from my .claude directory.

superpowers. An agentic skills framework & software development methodology that works.

ONE-SHOT-code. the official implementation of "Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration"

awesome-openclaw-usecases. A community collection of OpenClaw use cases for making life easier.

Lance. A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

SAMA. Official inference code for SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing.

daily_stock_analysis. LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.

GestureHydra. Python

VeOmni. VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Bagel. Open-source unified multimodal model

JoyAI-Image. JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

LongLive. Long Video Gen Infrastructure

LiveAvatar. [ECCV 2026] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"

LightX2V. Lightweight Image Video Action Generation Inference Framework

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

finetrainers. Scalable and memory-optimized training of diffusion models

LivePortrait. Bring portraits to life!

EMOPortraits. Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

lightly. A python library for self-supervised learning on images.

fiftyone. Refine high-quality datasets and visual AI models

I2V-Adapter-repo. I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Make-Your-Anchor. [CVPR 2024] Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework.

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Open-AnimateAnyone. Unofficial Implementation of Animate Anyone

DWPose. "Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

Realtime_Multi-Person_Pose_Estimation. Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

ControlNet. Let us control diffusion models!

AnimateDiff. Official implementation of AnimateDiff.

stable-diffusion. A latent text-to-image diffusion model

FaceX.

MRFA. [NeurIPS 2023] Learning Motion Refinement for Unsupervised Face Animation

VividTalk. VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior

Deep3DFaceRecon_pytorch. Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Deep3DFaceReconstruction. Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)