Repo AI đang lênCập nhật hằng ngày từ GitHub

Implementation of MagViT2 Tokenizer in Pytorch

[ICLR 2025] Autoregressive Video Generation without Vector Quantization

[SIGGRAPH ASIA 2024 TCS] AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data

Wav2Lip version 288 and pipeline to train

[CSUR 2026] A Survey on Deepfake Generation and Detection

Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds.

Vibe 知识大赏：一个知识点 → 一条有旁白、每句有出处的精品知识短片（Claude Code skill · 44 套风格 · 代码逐帧成片）

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generation, editable first cut on a real timeline. Local-first: projects, prompts, and keys stay on your machine. No account, no telemetry.

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

temporal action detection with SSN

[🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

全自动短视频搬运工具，支持自动下载、去重、AI生成标题+标签、上传，可二开扩展至多平台，例如：TikTok->视频号/抖音/小红书、抖音->TikTok/视频号/小红书......video-processing, automation, tiktok, selenium, pyqt5, ffmpeg, bot, data-scraping, video-deduplication.

Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding

[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Torrent Web Client

Desktop implementation of Remote Photoplethysmography – Measuring heart rate using facial video.

用 ChatGPT／Codex 安裝 AI 剪輯環境，並依八大步驟完成可驗證的短影音剪輯。

[IJCAI'24] Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer

GPT Image 2 to Seedance 2.5 Early Access workflow guide.

「来剪」轻量级视频编辑器。网页版、桌面版等均可免费使用，功能灵感源自 CapCut 等编辑器。A Lightweight Video Editor. Free for the web, desktop, and more, with features inspired by editors like CapCut.

Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling

A shadcn registry of Remotion components for product demo videos. Install a text reveal, device frame, terminal session, logo sting or a whole scene with a command.

[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

A cross-platform real-time subtitle display software. 一个跨平台的实时字幕显示软件。

A list of resources for video enhancement, including video super-resolutio, interpolation, denoising, compression artifact removal et al..

Console Interface and Library to remove silent parts of a media file 🔈

Create 💎 beautiful animations from boring screen recordings within ⏳ seconds

UI and Automation to cut, filter and join high quality webms, mp4s or gifs.

Auto search for movie/series on torrent, usenet, ddl, subtitles, streaming, predb and other sites. Adds links to IMDb pages from hundreds various sites. Adds movies/series to Radarr/Sonarr. Adds external ratings from Metacritic, Rotten Tomatoes, Letterboxd, Douban, Allocine. Media Server indicators for Plex, Jellyfin, Emby. Dark theme/style for Reference View. Adds/Removes to/from Trakt's watchlist. Removes ads

Automatic 3D Character animation using Pose Estimation and Landmark Generation techniques

Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.

Checkrr Scans your library files for corrupt media and optionally replaces the files via sonarr and radarr

A curated list of papers on reinforcement learning for video generation

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

Refacer: One-Click Deepfake Multi-Face Swap Tool

The open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

OpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具)

Code release for ActionFormer (ECCV 2022)

PyTorch implementation of two-stream networks for video action recognition

🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk.

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

Video editor that runs in the browser: timeline, text, image, video and audio layers, animations, filters, export with sound. Fabric.js + React + Next.js.

Workflow Enhancements for Creatives

A Collection of Google Colab Notebooks for various projects

Clips AI is an open-source Python library that automatically converts long videos into clips.

Livekeys - Automation Platform with support for live scripting.

A Repository for Diffusion-Model-related Papers in Low-level Vision

Industry leading face manipulation platform