Havuz

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

A self-hosted studio for generating images, video, and audio with diffusion models.

Your KiCad board, as a launch film. silk reel turns a .kicad_pcb into a 12-second film of its real copper and parts.

Turn one prompt into a finished MP4. An AI agent skill for Claude Code, Cursor, Codex & Windsurf that generates TikTok/Reels/Shorts, YouTube

Self-hosted MiniMax H3 video with native audio and Qwen Image. Adaptive ComfyUI workflows, character references, storyboards and saved scene

Faceless YouTube videos, made on your own PC with Claude Code. The open production engine of Nichebend Studio, by DamaizLabs.

Editable launch films and product ads. Local HTML-to-video rendering, a keyless demo, and optional image, video and audio generation with Ra

Open-source node-based AI media studio — generate image, video & music on an infinite canvas, or let an AI agent build a whole short film fr

Self-hosted studio that turns a story into a consistent AI-illustrated comic, webtoon or narrated video. Bring your own provider key, local

基于 Remotion 的配置驱动纸片分层视频流水线与 Codex 插件，支持人工审批、断点恢复、预览渲染和技术验收。

Open-source desktop app for content creation, with an agent runtime and standalone CLI.

Desktop multicam recorder for macOS: records your screen and webcam in sync, then Claude Code or Codex edits the final video — shot selectio

Local music analysis and deterministic video tooling for creators and coding agents.

Marketing Studio is a self-hostable AI video ad studio for e-commerce: UGC product ads, reference-ad remakes, AI drama ads, and ad skits, po

Codex skill for transcript-driven MiniMax-H3 B-roll planning, T01-T21 motion templates, approval-gated generation, and balanced typography c

Find the best AI models you can run

AI 驱动的短视频制作系统。给它一个想法，它帮你写稿、配音、做画面、出成片。9 阶段 DAG 管线 + 自进化评分，支持每日自动执行。基于 Claude Code + HyperFrames。

Turn ideas into ad videos

Pure MLX MiniMax-H3 text-to-video-and-audio inference for Apple Silicon.

🎬 泡泡猫的影视工具 — AI 影视创作工作站：文生图、图生图、文生视频、图生视频、短剧剧本拆解与提示词专家。支持 Agnes / DeepSeek / Qwen / 豆包 / MiniMax / Ollama 六大厂商，全局浮层不堵对话框。

中文 VOX 纸张拼贴 AI 视频工作流：风格板、图片提示词与视频提示词

Clean, high-taste motion graphics videos made by your AI agent with Remotion. One-command Agent Skill: npx skills add ahmdd4vd/motioncraft

Codex / WorkBuddy 短剧带货 Skill：salpx 生成分镜首帧，salpx Wan 3.0 直出 2–30 秒视频（多图/视频/音频参考、原生音轨、口型同步），支持美国市场本地化与剧本保真。

连镜：开源 AI 视频创作工作台：用无限画布连接图片、视频和音频生成流程，支持多模型、AI Agent 和私有部署。

AI Storyboard Director v5.2: open-source director-grade AIGC storyboard skill for turning scripts into executable cinematic shot chains.

A self-hosted studio for pictures, videos and timelines, in front of your own ComfyUI.

Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

Seedance 2.5 视频分镜提示词生成 Skill for Agent | 把商业意图+素材转成可直接用的视频脚本prompt | Turn business intent + assets into ready-to-use Seedance 2.5 storyboard

Write one HTML page, get an mp4. Open-source HTML to video framework for coding agents like Claude Code and Codex. A free Remotion alternati

Google Flow Prompt Guide: Veo Character Consistency, Storyboarding and Continuity

Open-source Agent Skill that turns a website, phone clips or a CSV into a finished short video: launch videos, promo reels and narrated expl

Open Source Desktop for video & image creators. Create your own videos & images with the advanced AI model: Seedance 2.5, Wan 3.0, Flux 3, G

[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent vi

Unified World Model Inference & Evaluation Infrastructure

YoLuster Shorts 釉光影：An independently developed AI short-drama creation workspace — from initial ideas to storyboard scripts, images, videos,

Create product launch assets with Remotion, then review and distribute them through guarded, dry-run-first workflows.

Wonda CLI — AI-powered content creation from your terminal

Topic + template → short vertical video from your own B-roll: AI script, voice, scene plan, captions, FFmpeg render. Multi-persona, AI shot

AI-powered screen recording with auto-captions, smart trimming, narration, and one-click professional output. Free and open source.

Turn a GitHub repository or Hugging Face model into a finished vertical reel: video, cover art and per-platform copy.

使用Agnes模型免费生成图片和视频/Generate images and videos for free using the Agnes model.

AI Agent skill for continuous, editable Remotion explainers — created by Bingo

MiniMax H3 全域提示词工程 Skill v1.8.1｜AIMixer Director 导演台生产规则 + 武打/兵器/枪斗编排｜T2VA / I2VA / FL2VA / L2VA / Ref2VA｜Subject 与 Picture 语义分离、跨镜头因果桥、人物一致

AI-powered pre-production canvas for filmmakers. Flagship models, infinite canvas, auto-export.

Explainer videos from HTML (HyperFrames → MP4) with AI narrator, music and mixing — Claude Code / Codex skills on NeuralDeep models

Building an Image-to-Video (I2V) Model from Scratch

AI agent skill for creating cinematic product launch videos with Remotion

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

[NeurIPS 2026 E&D]WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors