Open Source · Coming Soon

VULTUREAI

A fully offline, private AI creative studio — in one clean app.

Get started See what it does

100% local · offline · private · free · open source

It sees everything — nothing leaves your machine.

No cloud. No API keys. No subscriptions. Every model runs on your own hardware, and your data never goes anywhere. Just one clean window — no node spaghetti, no terminal.

What it does — all offline

One window.
Everything local.

Image Generation

FLUX + several SD models, with a built-in prompt optimizer that turns casual text into a proper prompt.

4K Upscaling

4x-UltraSharp + tiled Ultimate SD Upscale — real added detail, not just a resize.

Image → Image

Rework and reimagine any image with a prompt.

Image → 3D

Turn a photo into a 3D model (.obj) with TripoSR / Hunyuan3D.

Face-Swap

Swap faces between photos, fully offline.

Lip-Sync

Bring a still photo to life — expression, lips, head motion, with audio.

Local Chat

Ollama models (Qwen, DeepSeek-R1, vision) behind a clean dashboard.

Coding Agent

A local coding assistant with an auto test→repair loop and an auto-splitter for big tasks.

Code-RAG

Semantic search across your own projects with Qdrant + embeddings.

A look inside

One clean
window.

The Vulture AI studio dashboard: image generation, 4K upscaling, image-to-3D, face-swap, lip-sync, local chat and a coding agent, all in one window.
The dashboard — every tool in one window. No node graphs, no terminal.
The Create images window — a FLUX text-to-image generator with a built-in prompt optimizer, HD and 4K upscaling, and image-to-image.
Create images — FLUX + prompt optimizer, HD / 4K upscale, img2img.
The Image to 3D window — turn a photo into a textured 3D .obj model for Mixamo or Meshy.
Image → 3D — a photo becomes a textured 3D model.
The Face swap window — put your face onto a target image, 100 percent offline.
Face swap — your face onto any target, fully offline.
The Lip sync window — bring a photo to life with a driving video: expressions, lips and head motion.
Lip sync — a photo brought to life by a driving video.
The Setup and install window — a hardware check with per-GPU speed estimates and one-click model downloads.
Setup & install — hardware check, speed estimates, one-click install.

Still rough around the edges and in active development — more coming.

A vulture perched on a bare branch against a deep purple twilight sky with a faint aurora.

Local. Private. Yours.

The vulture angle

Runs on hardware
others threw away.

Most of this runs on a GTX 1060 6GB — an ancient card. It's slow on old hardware, but it works. More VRAM just makes it fly.


Like a vulture, it makes the most out of what everyone else discarded. A whole studio's worth of AI, on the machine already sitting under your desk.

How it works

How Vulture AI works

Vulture AI is the launcher and UI. The heavy AI models aren't bundled — they're downloaded onto your machine from their original sources during setup. That keeps it small, legal, and yours.


Built on the shoulders of ComfyUI, Ollama, Aider, FLUX, Stable Diffusion and many more open-source projects.

Privacy
100% offline · nothing leaves
Cost
Free · open source
GPU
6GB min · 12GB recommended
Platform
Windows · NVIDIA
License
MIT
Interface
One clean app · no terminal

Quickstart · Install

Up and running in
minutes.

The easy way — no terminal

  1. Install Python 3.11

    One-time, about two minutes. Grab the official installer↗ and tick "Add python.exe to PATH". It's the only thing you set up by hand.

  2. Download Vulture AI

    Get the ZIP from GitHub↗ and unzip it anywhere. It's tiny — just the launcher, no models yet.

  3. Double-click INSTALL.cmd

    That's it. It downloads ComfyUI, the models and everything else, then opens the app. Inside, ⚙ Setup shows your hardware, estimated speeds and one-click model downloads — and lets you pick which drive it all lives on.

You'll need Windows + an NVIDIA GPU (6 GB VRAM or more) and about 100 GB of free disk for the models.

Prefer the command line?

  1. Clone the repository

    Grab the launcher — it's tiny. No models yet, just the app.

    $ git clone https://github.com/ronnyplayplace-bot/vulture-ai.git
$ cd vulture-ai

  2. Run the installer

    One script does the rest: it downloads ComfyUI and the custom nodes, pulls every image / 3D model and the Ollama models, then writes your config. This is the long one (~100 GB) — grab a coffee.

    $ python setup/install.py

  3. Launch & create — fully offline

    Start Vulture AI: one clean window for generating, upscaling, face-swaps, chat and code. Pull the network cable if you like — nothing ever leaves your machine. (Or just double-click Overlkd-Studio.cmd.)

    $ python studio.py

Full requirements and troubleshooting live in the README on GitHub↗.

FAQ

Good
questions.

Is it really free?

Yes — free and open source under the MIT license. No subscriptions, no API keys, no paywalls. Donations are welcome but never required.

Does my data leave my machine?

Never. Every model runs locally on your own GPU. After the one-time setup download, Vulture AI works fully offline — no cloud, no telemetry, no trackers. Your prompts, images and files stay with you.

What hardware do I need?

A Windows PC with an NVIDIA GPU. 6 GB of VRAM is the minimum (a GTX 1060 works), 12 GB or more is recommended for speed. Keep about 100 GB of free disk space for the models.

Which models does it use?

Open models like FLUX and Stable Diffusion for images, TripoSR / Hunyuan3D for 3D, and Ollama models such as Qwen and DeepSeek-R1 for chat and coding. They're downloaded from their original sources during setup — not bundled with the app.

Can I use it commercially?

The Vulture AI app itself is MIT licensed, so yes. But some bundled models are released under non-commercial licenses. Always check the license of each individual model before using its output commercially.

Own your AI.

Open source, dropping soon. Star it on GitHub to follow along.

View on GitHub ↗ Overlkd Studio