INDEPENDENT GUIDE
Covers the original lllyasviel/stable-diffusion-webui-forge repository
Evidence checked
24 Aug 2026
LOCAL IMAGE WEBUI · ORIGINAL REPOSITORY

Stable Diffusion WebUI Forge, explained.

Forge is a local, browser-based image-generation interface built on AUTOMATIC1111’s Stable Diffusion WebUI. It keeps the familiar tabs and direct controls while adding its own model-loading, memory-management, and integration layer.

This site covers the original project by lllyasviel—not Forge Neo, reForge, or Forge Classic.

STALE SNAPSHOTPUBLIC · NOT ARCHIVEDLast repository push: 31 Jul 2025 · 01:33 UTC. That fact alone does not prove active maintenance.
VERIFIED CONTROL MAPORIGINAL REPOSITORY CODE · dfdcbab
UIsdxlfluxall
CHECKPOINTModel selection⌄
VAE / TEXT ENCODERAutomatic⌄
DIFFUSION IN LOW BITSAutomatic⌄
PROMPTDescribe the image to generate…
GPU WEIGHTS (MB)AUTO
SWAP METHODQueue / AsyncSWAP LOCATIONCPU / Shared
LOCAL OUTPUT
PRODUCT CAPTURE
NOT YET AVAILABLE
Explanatory map built from verified labels in original Forge source ↗. It is not a product screenshot. A current, rights-cleared capture is not available in this workspace.
RESOURCE RAILCONCEPTUAL · NOT A BENCHMARK
  1. 01Model weightWhat is loaded
  2. 02Inference headroomSpace to generate
  3. 03OffloadWhat moves outside GPU memory
01 · Product definition

What Forge is—and what it is not

Forge is a WebUI platform. It is not a Stable Diffusion model, a hosted image service, or a renamed copy of ComfyUI.

01

A familiar WebUI workflow

You work with prompts, checkpoints, samplers, seeds, image dimensions, txt2img, and img2img in the form-and-tab interface inherited from A1111.

Source: original README ↗
Txt2imgImg2imgExtrasPNG InfoSettings
02

A different resource layer

Forge adds its own controls for model storage precision, GPU weight allocation, swap method, and swap location. These settings change how a workload fits; they do not guarantee a speed increase on every machine.

Source: current UI construction code ↗
GPU WEIGHTS (MB)DIFFUSION IN LOW BITSSWAP METHOD · QUEUE / ASYNCSWAP LOCATION · CPU / SHARED
03

Not ComfyUI as a backend

Forge uses selected ideas and attributed code from ComfyUI, but the maintainer explicitly states that Forge does not use ComfyUI as its backend. The two products also present very different workflows.

Source: maintainer’s architecture clarification ↗
A1111 WEBUI BASEFORGE RESOURCE LAYERCOMFYUI BACKEND
04

The interface does not include a model

Forge runs the WebUI, but you still need compatible model files. The model family, precision, and supporting files determine what the interface can load and how much memory the job needs.

See what first run needs →
Forge processmodel fileslocal output
02 · Everyday work

What you can do in Forge

The exact model and feature compatibility depends on the Forge commit, model files, and extensions you run. These are the core jobs the interface is built around.

01 · GENERATE

Create images from text

Choose a checkpoint, enter a prompt, set dimensions and sampling controls, then generate directly from the txt2img tab.

02 · TRANSFORM

Edit an existing image

Use img2img and inpainting to change an image, repair a selected region, or guide how far the result moves from the source.

03 · CONTROL

Guide structure and composition

Forge includes ControlNet integration and related preprocessors in the inspected source. Support still varies by model family and revision.

04 · FIT

Manage local model resources

Load standard or low-bit model formats and decide how much GPU memory is reserved for weights versus inference work.

Feature boundary checked against the original repository, Forge UI code, and the inspected commit dfdcbab.

03 · Resource logic

Memory is a budget, not a GPU badge.

A “low VRAM” label is not enough to predict whether a job will work. The model, precision, resolution, batch size, extensions, and memory settings all change the result.

01
Load the model

Model weights take part of the available GPU or system memory.

02
Keep inference headroom

Generation needs working space beyond the memory occupied by weights.

03
Offload deliberately

Moving data to CPU or shared memory can make a job fit, but it can also make it slower.

Source: Forge memory-control guidance ↗
05 · Before installing

Questions worth answering first

These are the details that prevent most wrong downloads, mismatched expectations, and avoidable setup work.

Is this the official Forge website?

No. This is an independent guide. The original project lives at github.com/lllyasviel/stable-diffusion-webui-forge, and our download links keep you on that repository.

Does Forge include Stable Diffusion or FLUX models?

No. Forge is the interface and runtime. The inspected UI includes sd, xl, and flux presets, but a preset is not a guarantee that every model file will work. You obtain compatible checkpoints, UNets, VAEs, text encoders, and LoRAs separately when the model family requires them. Use the Original Forge UI glossary when those labels are unfamiliar, then start with the first-run guide before adding several models at once.

Does opening Forge in a browser make it a cloud service?

No. In the default setup, a local process starts the interface and your browser opens its localhost address. First run can still download dependencies, and model downloads come from their own providers. Do not expose the local server to a network unless you understand the security implications.

Is original Forge still maintained?

The repository was public and not archived when we checked it on 24 Aug 2026. Its latest inspected main commit is dfdcbab from 26 Jun 2025, while GitHub reports a later repository push on 31 Jul 2025 · 01:33 UTC. That is a dated status, not a promise of active support. See the full project-status timeline.

Will Forge be faster or use less VRAM on my GPU?

It may improve a particular workload, but there is no honest universal percentage. Compare the same model, seed, sampler, steps, dimensions, precision, extensions, commit, and warm-up state. The maintainer’s performance-reporting guidance requires this context for a useful comparison.

Which operating systems and GPUs can run Forge?

The clearest project-documented route is the Windows package built around NVIDIA CUDA. Community procedures and code paths exist for Linux, AMD/DirectML or ROCm, Intel, and Apple MPS, but a code path is not the same as current end-to-end support. Check the install-path guidance for the exact environment we can verify.

Is Stable Diffusion WebUI Forge open source?

Yes. The original Forge repository publishes its source under GNU AGPL Version 3. Use the Original Forge license guide to separate local use, modified network hosting, redistribution, generated output, models, and extensions.

Which Forge repository should I install?

This guide installs the original lllyasviel repository. Forge Neo, reForge, and Forge Classic are separate downstream projects with their own owners, files, features, and support state. Do not use instructions for one as if they applied to another.

06 · Verified Windows route

From GitHub to localhost.

The original README documents a Windows one-click package. The handoff is short, but each step has a distinct purpose.

  1. 01 · GITHUBDownload the 7z archive
  2. 02 · FILESExtract it locally
  3. 03 · PREPARERun update.bat
  4. 04 · LAUNCHRun run.bat
  5. 05 · BROWSEROpen localhost
Software files stay on the original repository.

We do not mirror installers, rename third-party bundles, or invent checksums that GitHub does not publish.

07 · Evidence boundary

A dated guide to one repository.

We separate verified project facts from community reports and keep stale information visibly dated.

Repository
lllyasviel/stable-diffusion-webui-forge
Inspected main
dfdcbab
26 Jun 2025
GitHub state
Not archived
checked 24 Aug 2026
Coverage
Original Forge only
forks kept separate