Tavris1/AI-Toolkit-Easy-Install

One-click Portable Windows installation of 'AI-Toolkit by Ostris'

What it solves

Setting up a diffusion model training environment is notoriously fiddly: you need matching versions of Python, PyTorch, CUDA, FlashAttention, FFmpeg, and more. This project packages those dependencies into a single downloadable ZIP containing one .bat file. Running it installs or updates everything needed and launches the AI-Toolkit GUI/local server without touching your system Python or creating virtual environments.

How it works

You download the release ZIP, extract the batch file into a fresh folder, and double-click it. The installer checks for and installs Git, Node.js, FFmpeg, an embedded Python 3.12.10, PyTorch 2.13.0 with CUDA 13.0, Triton, FlashAttention, torchcodec, the huggingface_hub extension, and finally the latest AI-Toolkit itself. Once ready, the launcher starts the server, opens your default browser as soon as it is live, and checks for updates. A separate Update-AI-Toolkit script handles later upgrades.

Who it’s for

Windows users with NVIDIA GPUs who want to train or fine-tune image and video diffusion models without manually wrestling with package managers, CUDA versions, or virtual environments. It is aimed at both beginners and experienced users who prefer a portable, self-contained setup.

Highlights

  • One-click portable installer – no system Python, no VENV, just run the batch file.
  • Auto-provisions the whole stack – Git, Node.js, FFmpeg, Python, PyTorch, Triton, FlashAttention, torchcodec, and the AI-Toolkit itself.
  • Pinned compatible versions – FlashAttention 2.8.3, Triton 3.7.1.post27, torchcodec 0.15.0 for Torch 2.13.0 to avoid breakage.
  • Launcher convenience – opens the browser when the server is up and alerts you to updates.
  • Safe usage guidance – warns against running as Administrator, system folders, and spaces in paths.

Related

  • Project
    ostris/ai-toolkit

    Ostris AI Toolkit is an open‑source suite for training and running diffusion models (image, video, audio, and a multimodal LLM) on consumer‑grade GPUs. It offers a web UI, CLI, an experimental manager that auto‑installs dependencies, support for many Hugging Face models, LoRA/LoKr adapters, and cloud‑deployment guides (RunPod, Modal, Ostris Cloud).

  • Project
    easydiffusion/easydiffusion

    A one-click installer and user interface for Stable Diffusion that allows users to run powerful image generation AI locally without requiring technical knowledge.

  • Project
    Tavris1/ComfyUI-Easy-Install

    A portable, one-click installer for ComfyUI on Windows that includes a management dashboard for environments, packages, and hardware configurations.

  • Project
    YanWenKun/ComfyUI-Windows-Portable

    A ready‑to‑run Windows package that bundles ComfyUI (a node‑based UI for Stable Diffusion) with 40+ custom nodes and 300+ pre‑compiled Python packages, letting users launch AI image/video generation instantly on an NVIDIA GPU.

  • Project
    AkshitIreddy/AI-Powered-Video-Tutorial-Generator

    AI‑Powered Video Tutorial Generator is a Windows‑only desktop app that turns a question or topic into a fully editable video lesson. It handles research, script writing, storyboard creation, narration, illustration, presenter animation and final export, using either local diffusion models (ComfyUI/SDXL) or cloud LLM/image providers. The open‑source stack combines a React/Tauri UI, a Rust core, and a Python pipeline, and it ships with bundled runtimes (Python, Node, Chromium, FFmpeg).