Stars
- All languages
- Assembly
- Astro
- C
- C#
- C++
- CSS
- ChucK
- Clojure
- Cuda
- Cython
- Dart
- Emacs Lisp
- Fortran
- Go
- HTML
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lua
- MATLAB
- MDX
- MLIR
- Macaulay2
- Makefile
- Markdown
- Mathematica
- PHP
- Perl
- PostScript
- Python
- Rich Text Format
- Ruby
- Rust
- Scala
- Shell
- Swift
- TeX
- TypeScript
- Vim Script
- Visual Basic .NET
- Vue
- XSLT
[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
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.
awesome video-based self-supervised learning methods in recently years
A unified framework for easy reinforcement learning in Flow-Matching models
[CVPR2026] Official implementation of our paper “Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation”
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
The ultimate collection of high-fidelity Seedance 2.0 prompts and Seedance AI resources. Discover Seedance 2.0 how to use for cinematic film, anime, UGC, social media, meme and advertising. Include…
Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0