Repo AI đang lênCập nhật hằng ngày từ GitHub

A web-based video editing tool implemented with WebCodecs, similar to CapCut Web.使用webcodecs实现的Web端视频编辑工具，类似剪映Web版。

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

Fast and Accurate One-Stage Space-Time Video Super-Resolution (accepted in CVPR 2020)

[ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

High-performance and flexible video editing and effects framework, based on AVFoundation and Metal.

Open data and scalable training for long-horizon video world models.

Video generation from text&image, 1st-gen

CCExtractor - Official version maintained by the core team

Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an acting system, Cinema Studio 2.5/3.0/3.5, MCSLA, Soul ID consistency, Kling 3.0 Motion Control, the DISCIPLINE framework, and 18 templates.

YumCut - free AI video generator to turn a prompt into ready vertical videos for TikTok, Reels and YouTube Shorts. Auto script, scenes, voiceover, subtitles and watermark. Built with Next.js. Local-first pipeline + templates, batch rendering and API hooks for creators and indie makers. Self-hosted, FFmpeg-ready, multi-language output. Low cost fast

[NeurIPS 2024] A Generalizable World Model for Autonomous Driving

Self-hosted torrent video streaming service compatible with Chromecast, AppleTV & Kodi deployable in the cloud

[AAAI 2025] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"

🍜 Adds mpv keybindings to create Anki cards from movies and TV shows.

Unified Codebase for Advanced World Models.

SOMA: Unifying Parametric Human Body Models

Diffusion-based Portrait and Animal Animation

Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)

Community-driven, simple, yet powerful framework for fast, cost-effective distributed Compute over Data.

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

Free open-source downloader for YouTube and 2000+ sites on Windows, macOS, and Linux. Up to 8K HDR 60fps, Dolby audio, MP3, Shorts, playlists, channels, subtitles, SponsorBlock, and just part of a video. Built-in browser: sign in to download private, members-only, and age-restricted videos. No ads. 50 languages.

Rip, extract and convert subtitles to .srt closed captions from .xml/dfxp/ttml and .vtt/WebVTT (e.g. Netflix, YouTube)

Flatkey media generation CLI for images, videos, audio, text, credits, and model discovery.

把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio.

[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

🎞 Hardware-accelerated video transcoding using Android MediaCodec APIs. Supports cropping, concatenation, clipping, audio processing, video speed and much more.

赛博小雅直播版 · 组件版数字人（Vidu s2）· 免费开源 AGPL-3.0 · 作者：天工开帧（抖音/B站/YouTube 同名）

字幕查找器

[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Papers, code and datasets about deep learning and multi-modal learning for video analysis

Kandinsky 5.0: A family of diffusion models for Video & Image generation

A free, local desktop app to extract subtitles (SRT) from video and translate them into any language — unlimited use, no signup, no cloud.

一站式全自动字幕生成软件，下载、转录、翻译、压制全流程覆盖，无需人工介入 / One-stop automated subtitle generator. Handles downloading, transcription, translation, and hardcoding—zero human intervention required.

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

Video Editor for AI agents, built on the belief that open source can beat commercial tools

An open-weight 11B model series for long-form and real-time video understanding

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

This application can translate text captured from any application running on your computer.

Video Frame Interpolation & Super Resolution using NVIDIA's TensorRT & Tencent's NCNN inference, beautifully crafted and packaged into a single app

Official mirror of libplacebo

Real-time 3D face tracking and reconstruction from 2D video

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

A self-hosted platform to use HandBrake on your headless devices via a bespoke web interface. Harness the processing power of multiple devices to work on a single queue.

将参考声音和中文文案自动生成白板动画视频的本地 AI 工具。

Libva is an implementation for VA-API (Video Acceleration API)