Stars
A V2Ray client for Android, support Xray core and v2fly core
Official Implementation for CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning
[CVPR2025] Any-Resolution AI-Generated Image Detection by Spectral Learning
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video pro…
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
A script set that uses ffmpeg to implement various functions
[CVPR 2026] Official Implementation of PS-SR: Pseudo-Single-Step Video Super-Resolution via Speculative Diffusion
武术指导 Skill — 一句话需求生成 N 宫格武打分镜海报与视频提示词，覆盖武术、格斗、修真、戏曲、机甲等多类题材
[Official release ]This project provides the code for local video quality assessment with the MD-VQA CVPR 2023 version.
Enhancing Blind Video Quality Assessment with Rich Quality-aware Features
Fully Open Framework for Democratized Multimodal Training
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
Official Implementation of ICCV 2025 paper "ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection"
[CVPRW oral 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
code for our ECCV-2020 paper: Self-supervised Video Representation Learning by Pace Prediction
[SIGGRAPH 2026 Conditional Accept] VeraRetouch: A Lightweight Fully Differentiable Framework for Multi-Task Reasoning Photo Retouching
A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
[CVPR 2026] Official implementation of VITAL: Vision-Encoder centered pretraining for LMMs in visual quality assessment.
Turn any reference video into structured shot data + AI prompts — Claude Code skill
[ICML 2026] Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
CoTracker is a model for tracking any point (pixel) on a video.