Pinokio is a free, open source launcher that installs and runs AI projects with one click. It has a Discover page listing hundreds of scripts: image apps like ComfyUI, Forge and Fooocus, video tools like Wan2GP and FramePack, speech, music and LLM tools. Each install gets its own Python environment, so projects never break each other, and Pinokio can share model folders between them.

Pinokio is for people who want to try many different AI tools, especially new research projects that have no installer of their own, without learning the command line. It runs on Windows, Mac and Linux.

No install required - run AI models on the cloud

BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).

Try BitVector

What you need

Windows 10 or 11, macOS (Apple Silicon or Intel) or Linux. Each app you install has its own GPU needs; most image and video tools expect an NVIDIA card with 8 GB or more VRAM, while Mac support depends on the project. Plenty of disk space, since every app downloads its own models.

How to get and install Pinokio

Download Pinokio for your system from pinokio.co (Windows installer, Mac .dmg or Linux package) and install it.
Open Pinokio, pick a home folder with plenty of space (the apps and models go there) and let it finish the first-time setup (it installs Git, Conda and other tools it needs).
Open Discover, find an app such as ComfyUI, Forge or Wan2GP and press Download, then Install. Pinokio shows each step as it runs.
Press Start when the install finishes, then Open to see the app's interface inside Pinokio or in your browser.

Download only from the official links on this page. Installers found elsewhere may be out of date or tampered with. ModelTrends.ai hosts no files.

No install required - run AI models on the cloud

PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.

Try PirateDiffusion

How to use Pinokio

Each installed app appears on the home screen; press Start, wait for the terminal to show the local address, then Open.
Use the app as you normally would; see the pages here for ComfyUI, Forge, Wan2GP and FramePack for what to do inside them.
Pinokio keeps every app's models in its own folder; many scripts offer a shared drive option so one Stable Diffusion model serves several apps.
Stop an app from its page when you are done to free the GPU for another one.
Update an app from its page (Update button) when the script author publishes a new version.

Tips and common problems

The terminal tab on each app page shows what is happening; read it when something fails, most problems are a download that did not finish.
Install only the scripts from the verified list or from authors you trust; scripts can run any command on your machine.
Running two GPU apps at once will exhaust your VRAM; stop one before starting another.
If disk space runs low, delete an app from its page; this removes its environment and models.

Models you can run in Pinokio

Pinokio does not run models itself; the apps it installs do. Through ComfyUI, Forge, Wan2GP and FramePack you can run the Flux, SDXL, Wan, Hunyuan and LTX models in this catalog.

Flux Models

Wan Models

Stable Diffusion XL 1.0 Models

Hunyuan Models

Ltx2 Models

No install required - run AI models on the cloud

No GPU, no downloads, no Python. These services run the same open source models on their own servers, so you can start generating from a browser, Discord or Telegram in a minute.

Try BitVector

Try PirateDiffusion

Links

These links go to the makers' own sites. ModelTrends.ai is not affiliated with them and does not host any software.

Other local apps

How to install ComfyUI

The node-based powerhouse for Stable Diffusion, Flux, Wan video and almost every new open source model. Free, open source, for Windows, Mac and Linux.