Trending AI reposUpdated daily from GitHub

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

A lightweight 2.5D character player for the web, with lip sync and webcam face tracking.

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

Text To Video Synthesis Colab

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Creates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.

Multi-backend whisper app. Blazing fast. Mac-arm optimized. Easy install. Input a local file or url and this service will transcribe it using Whisper AI. Completely private and Free 🤯🤯🤯

[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution

A browser-based video editor powered by ffmpeg.wasm. No uploads, no servers -- all processing happens locally in your browser using WebAssembly.

An open, scalable, online streaming setup. All-in-one toolkit from ingest to adaptive video playback. Built for developers in need of video tooling.

😎 The open-source, Haskell-built video editor for GIF makers.

DeepSeek Harness 本地视频制作与设计插件：多轨剪辑、模板与设计体系、原生预览画布和真实文件导出

Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

Using OpenAI's Whisper to automatically generate YouTube subtitles

[ICCV 2023] StableVideo: Text-driven Consistency-aware Diffusion Video Editing

移动版二次元 AI 老婆聊天器

Wav2Lip UHQ extension for Automatic1111

Subtitle Speech Synchronizer

开源AI漫剧、AI短剧、AI电影与AI漫画创作平台，支持剧本、角色场景、智能分镜、图片与视频生成、配音及成片预览，多模型接入，可自行部署。预：无限画布、导演台。

通用流媒体平台增强及双语字幕解决方案

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

The open-source alternative to Capcut、ChatCut. Drivable by any AI agent over MCP.

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

Play a finished motion-graphics ad in sync with the rough drafts it grew from, and export the breakdown as MP4.

Get Caption, start watching.

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

一款Android视频编辑项目，功能有视频拍摄，视频裁剪，视频滤镜，视频压缩

Your coding year in review

Your coding year in review #GitHubUnwrapped

Official code of Motus: A Unified Latent Action World Model

FFmpeg with async and zero-copy Rockchip MPP & RGA support

🎞 字幕文件批量改名和自动调轴工具 | Batch rename subtitle files to match video names with one-click.

抖音爆款Vibe知识大赏知识短片skill，深度拆解爆款视频，复刻画风，导演分镜表，自动配音效，一键出片

Code for Motion Representations for Articulated Animation paper

ClipForge（原『带货剪手』/ daihuo-jianshou）：开源 AI 带货短视频神器——上传一张商品图，AI 自动提炼卖点 + 写种草脚本 + 锁定商品原图不变形 + 配画面/配音/字幕，一键产出抖音小店 / 快手 / 小红书 / TikTok Shop 卖货短视频。0 成本批量出片、开源无水印、本地自部署。也支持一句话主题成片。Open-source AI e-commerce/UGC short-video generator.

[NeurIPS2026] We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

Automatic subtitle synchronization tool.

Cross-platform video editing (compositing) software.

AutoClip: AI-powered video clipping and highlight generation · 一款智能高光提取与剪辑的二创工具

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

The easiest way to add video in your Nextjs app.

Learning notes and tooling skills for AI video - AI 视频相关的学习与工具 skill

[ICML 2024 & TPAMI 2026] EvTexture & EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution

libass is a portable subtitle renderer for the ASS/SSA (Advanced Substation Alpha/Substation Alpha) subtitle format.