Repo AI đang lênCập nhật hằng ngày từ GitHub

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

Provider-neutral Codex Skill for producing verified AI presenter videos from a script and an authorized presenter image.

Open-source, self-hosted file-processing tool. Convert, compress, OCR, transcribe & run local AI across image, video, audio, PDF & documents, via UI, REST API & pipelines. Your files never leave your network.

Create professional demos and 3D mockups in seconds, directly in your browser

Matrix-Game 4.0: Streaming Neural Rendering for Playable Games

Open-source, ad-free Android multimedia recorder with background video recording, screen recording, live streaming, and remote camera control

Long Video Gen / World Model / World Action Model (Embodied) Infrastructure

保留视频内嵌字幕，精确取帧并生成 3:4 社交长图的 Agent Skill

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

Rhubarb Lip Sync is a command-line tool that automatically creates 2D mouth animation from voice recordings. You can use it for characters in computer games, in animated cartoons, or in any other project that requires animating mouths based on existing recordings.

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

全能翻译 AGENT Harness · 音频 视频 游戏 电子书 · PDF EPUB RPG ASMR GALGAME 等 · 一键 · 高质量 · 全格式

Support for https://www.gyan.dev/ffmpeg

使用AI大模型，一键生成高清故事短视频。Generate high-definition story short videos with one click using AI large models.

Make videos with Claude Code: script, AI voiceover, music, video clips and render, on open-source models that cost cents

🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 840+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 79 installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.

Android上基于FFmpeg开发的视频处理框架，简单易用，体积小，帮助使用者快速实现视频处理功能。包含以下功能：剪辑，裁剪，旋转，镜像，合并，分离，变速，添加LOGO，添加滤镜，添加背景音乐，加速减速视频，倒放音视频。 The video processing framework based on FFmpeg developed on Android is simple, easy to use, and small in size, helping users quickly realize video processing functions. Contains the following functions: editing, cropping, rotating, mirroring, merging, separating, variable speed, adding LOGO, adding filters, adding background music, accelerating and decelerating video, rewinding audio and video.

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

Screenshot, screen recording, and video editor for macOS. Native SwiftUI app with capture deck, 75+ customizable shortcuts, URL scheme automation, and self-hosted cloud sharing. Open-source alternative to CleanShot X and Loom.

BigBanana AI Director是一个工业级一站式 AI 短剧，AI 漫剧,AI 导演平台，面向创作者，实现从灵感到成片的高效生产。 它摇弃了传统的“抽卡式”生成，采用 "Script-to-Asset-to-Keyframe" 的工业化工作流。实现 “一句话生成完整短剧，从剧本到成片全自动化”，同时精准控制角色一致性、场景连续性与镜头运动。

JS Expert Week 8.0 - 🎥Pre processing videos before uploading in the browser 😏

🎬 seedance2接入 开源本地 AI 短剧 & 漫剧生成工具 —— 从故事到成片一站式完成，数据不出本机，短剧工作流管理平台，高灵活度，AI真人剧，AI漫剧本地搞定。 Open-source local AI short drama maker: story → storyboard → video, fully offline, your data stays yours. 纳米流水线

High-performance · Lightweight · AI Native Video workspace. 面向 AI 时代的视频创作工作台。 在画布中，和Agent一起自由连接创意和素材。

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

[ICML 2026] Video generation via code

Automated YouTube Shorts pipeline: news → script → AI visuals → voiceover → captions → upload

Render Anything Engine: tell your AI what to make. Videos, motion graphics, 3D and games as React and TypeScript, rendered on your own GPU. Rust + Bevy, macOS, Linux and Windows.

[CSUR] A Survey on Video Diffusion Models

FreeCut is a professional-grade video editor that runs entirely in your browser. Professional video editing, zero installation. Create stunning videos with multi-track editing, keyframe animations, real-time preview, and high-quality exports.

Automatically generate and overlay subtitles for any video.

Your Creative Copilot for Video Editing

A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness

[TPAMI 2026🔥] Helios: Real Real-Time Long Video Generation Model

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

🎬 2000+ curated Seedance 2.0 video generation prompts — cinematic, anime, UGC, ads, meme styles. Includes Seedance API guides, character consistency tips, and advanced video workflows.

知了 Cicada · 任何会议和直播的实时字幕、同声传译、AI 会议纪要，Mac、Windows、Linux、Android 免费开源。Live subtitles, interpreting and meeting notes for any call or stream, on Mac, Windows, Linux and Android.

A GPU accelerated image and video processing framework built on Metal.

The open-source studio for making games with AI. Your own one-person game studio. Everything you need to make games with AI, in one app. Game canvas. Bring your own key.

V- Modal AI: Visual Video / Image Search - Flutter Video SDK

Powerful & Easy-to-Use Video Face Swapping and Editing Software

A web-based Video Editing SDK built on WebCodecs. 基于 WebCodecs 构建的网页视频编辑 SDK。

Open Source API and interchange format for editorial timeline information.

AI视频, AI动漫,AI 短剧,AI漫剧自动化生成工具

A high performance anime upscaler

[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"

Digital Human Resource: 2D/3D/4D Human Modeling, Avatar Generation & Animation, Clothed People Digitalization, Virtual Try-On, etc.

A modern yet simple multi-platform video cutter and joiner.