Forge UI Neo (also called Forge Classic Neo) is a community-driven fork of the popular Stable Diffusion WebUI Forge — a fast, memory-efficient frontend for local AI image and video generation on Windows. After the original Forge slowed down, Neo picked it up and added support for the newest models. This guide answers the most common Forge Neo questions in one place: how to install it, which models it supports, extensions, updating, requirements, and how it stacks up against ComfyUI.
What is Forge UI Neo?
The original Forge WebUI was one of the most popular AUTOMATIC1111-based interfaces, adding big speed and VRAM optimizations on top of the classic Stable Diffusion UI. Forge Neo is the community fork that continues that work and extends it to the latest generation of models — including video. It keeps the familiar Forge/A1111 workflow while adding modern model support and performance backends.
Which models does Forge Neo support?
One of the biggest reasons people switch to Neo is its breadth of model support. Here's what it handles:
| Model | What it does | One-click setup |
|---|---|---|
| WAN 2.2 (T2V / I2V) | AI video — text-to-video and image-to-video, right inside Forge Neo | WAN 2.2 in Forge Neo installer |
| Z-Image Turbo | Fast, high-quality image generation | Z-Image Turbo in Forge Neo installer |
| Flux (incl. Nunchaku) | State-of-the-art image generation; Nunchaku for faster Flux | Built into the base Forge Neo installer |
| SDXL / SD 1.5 | Classic Stable Diffusion checkpoints & LoRAs | Supported natively |
How to install Forge Neo (Windows)
Option A — One-click installer (easiest)
The Forge Neo one-click installer downloads and configures everything for you: the Forge Neo build, an isolated Python environment, and the performance stack (Sage Attention, Flash Attention 2, Triton). You double-click and it runs — no command line, no dependency hunting. It's also available free with Local Lab Pro.
Option B — Manual install
If you prefer to set it up yourself: clone the Forge Classic Neo repository, create a Python 3.11 environment, install the requirements, and (optionally) add Flash Attention + Triton for a speed boost. This route works but is finicky on Windows — matching the right PyTorch, CUDA, Triton, and attention versions is the part most people get stuck on.
How to update Forge Neo
Forge Neo is updated frequently. To stay current without reinstalling, use the
Forge Neo update file —
drop it into your existing install folder and run the included .bat to pull the latest version. If you installed manually, a git pull in your Forge Neo folder will also update it.
Extensions
Because Forge Neo descends from the Forge/AUTOMATIC1111 lineage, it's broadly compatible with the existing ecosystem of A1111/Forge extensions — ControlNet, prompt helpers, and more. Install them the same way you would in A1111 (Extensions tab → install from URL), and check an extension's notes if you hit a compatibility issue, since Neo tracks newer model formats.
System requirements
- GPU: an NVIDIA GPU is recommended for the attention/Triton acceleration.
- VRAM: image generation runs comfortably on 6–8 GB; WAN 2.2 video also targets low-VRAM cards via GGUF. See the Local AI VRAM Requirements 2026 guide for model-by-model numbers.
- Python: 3.11 for manual installs (the one-click installer bundles its own environment).
- Disk: budget 30 GB+ of free space for the app plus models.
Forge Neo vs ComfyUI vs original Forge
- vs original Forge: Neo is the actively-maintained continuation — it adds support for newer models (WAN 2.2, Z-Image, modern Flux) the original never received.
- vs ComfyUI: ComfyUI is a node-based, maximally-flexible interface; Forge Neo is a simpler, form-based UI that's faster to learn and great for straightforward image (and now video) generation. Many people run both — Forge Neo for quick generations, ComfyUI for complex custom pipelines.
FAQ
Is Forge Neo free? Yes — it's open-source. Our one-click installer is a convenience that pre-configures everything for you.
Does Forge Neo support WAN 2.2 video? Yes, both text-to-video and image-to-video — see the WAN 2.2 in Forge Neo installer.
Does it support Flux and Z-Image Turbo? Yes to both, including Flux Nunchaku for faster Flux and a dedicated Z-Image Turbo setup.
What Python version does Forge Neo need? Python 3.11 for manual installs.
How do I update it? Use the update file, or git pull if you installed manually.