Stable Diffusion WebUI Forge
A platform built on the Stable Diffusion WebUI that aims for faster inference and leaner resource use.
One-click Windows package built on Gradio, syncing with the original WebUI every 90 days.
Forge is a platform on top of the Stable Diffusion WebUI, written by the author of Fooocus, aimed at easier development, better resource management and faster inference. It suits people who like the WebUI layout and want a one-click Windows install.
What it is
You download the one-click package, extract it, run update.bat and then run.bat. The README offers several CUDA and PyTorch builds, and says Forge syncs with the original WebUI every 90 days.
Who it's for
It suits Windows users with an Nvidia card who already know the WebUI style. It does not suit anyone who needs frequent releases; the latest commit on the default branch is from mid-2025.
Key features
One-click package
Git and Python are included; extract and run.
Resource management
Aims to optimise memory use and speed up inference.
Gradio interface
Built on Gradio like the original WebUI.
90-day syncs
Pulls in upstream WebUI changes every 90 days.
CUDA builds
Several CUDA and PyTorch combinations are offered.
Git branch install
Can also be installed as a branch of the WebUI.
Up and running in 3 steps
Our honest verdict
What's great
- The one-click package bundles git and Python, so there is no environment to build.
- AGPL-3.0 code with a familiar WebUI layout if you already use that style.
- It states a goal of faster inference and better resource handling than the base WebUI.
- Several CUDA and PyTorch builds are offered, so you can match your driver.
Where it falls short
- Needs a CUDA-capable GPU in practice; the README lists no VRAM minimum and no non-CUDA path.
- The latest commit on the default branch is 2025-06-26, so updates are slow.
- The README warns docs, UI and functionality may change because the project is under construction.
- AGPL-3.0 means sharing source changes if you run a modified copy as a network service.
Pricing & license
Free under AGPL-3.0. The only cost is the GPU hardware you run it on; the project shows no paid hosted plan.
Open remote AI-training roles
768 open remote AI-training roles, updated November 14, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
Use it, or have us set it up
FAQ
What is the difference between Forge and the Stable Diffusion WebUI?
Forge is built on top of the WebUI to optimise resource management and speed up inference, and the README says it syncs with the original every 90 days.
Is Forge still updated?
Its latest commit on the default branch is dated 2025-06-26, so check the repository for recent activity before depending on it.
Can I use Forge commercially?
The code is AGPL-3.0, which allows commercial use but requires sharing source changes if you offer it as a network service. Model licences are separate.
