Store

An all-in-one, 100% local AI video, image & music studio. Its Director mode turns a single prompt into a full music video or short film — LLM-planned, shot by shot. Built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). Requires an NVIDIA GPU (6GB+ VRAM).

Generate editable Ideogram JSON prompts from uploaded images.

A privacy-respecting metasearch engine that runs locally.

Launcher for Stable Audio 3 Small Music, Small SFX, and NVIDIA Medium using public cocktailpeanut Hugging Face mirrors. https://github.com/Stability-AI/stable-audio-3

Self-hosted, open-source video and audio downloader with a clean web UI. Supports YouTube, TikTok, Instagram, X, and 1000+ other sites via yt-dlp.

[NVIDIA GPU required] Unified S^3 fields for animatable 3D asset generation from a single image. 6GB VRAM needed (Low VRAM option)

Organize the Pinokio home screen with nested categories, drag-and-drop folders, per-category sorting, grid/list views, and reversible installation.

Run and train AI models with a unified local interface. https://github.com/unslothai/unsloth

Local-first voice synthesis studio powered by Qwen3-TTS.

Professional-grade browser-based video editor with multi-track editing, keyframe animations, real-time preview, and high-quality exports. No uploads — everything runs locally.

High-quality text-to-speech with Beautiful Web UI & API, optimized for Apple Silicon using MLX. Features include Custom Voice (preset speakers), Voice Design (natural language), and Voice Cloning. With enhanced features for saving custom voices and long-form / endless TTS streaming.

Browser-based 3D avatar head and mouth controller with keyboard and gamepad support. https://github.com/promptpirate-x/discord-id-bypass-tool

Unified AI VFX pipeline with CPE prompt engineering, storyboard canvas, and multi-node orchestrator. https://github.com/NickPittas/DirectorsConsole

State-of-the-art 1B OCR model (83.2% on OlmOCR-Bench). Local version of the HuggingFace demo. Created by Claude Code, orchestrated by TheAwakenOne.

World Model - Image to Video (4-bit Quantized, ~20GB VRAM)

Crop/trim any media

Open source UI for ACE-Step 1.5 music generation.

The most powerful local music generation model that outperforms most commercial alternatives.

Local web UI for orchestrating AI coding agents and tasks (BloopAI/vibe-kanban).

Secure Workflow Automation for Technical Teams