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 ↗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.
Forge is a WebUI platform. It is not a Stable Diffusion model, a hosted image service, or a renamed copy of ComfyUI.
You work with prompts, checkpoints, samplers, seeds, image dimensions, txt2img, and img2img in the form-and-tab interface inherited from A1111.
Source: original README ↗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 ↗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 ↗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 →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.
Choose a checkpoint, enter a prompt, set dimensions and sampling controls, then generate directly from the txt2img tab.
Use img2img and inpainting to change an image, repair a selected region, or guide how far the result moves from the source.
Forge includes ControlNet integration and related preprocessors in the inspected source. Support still varies by model family and revision.
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.
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.
Model weights take part of the available GPU or system memory.
Generation needs working space beyond the memory occupied by weights.
Moving data to CPU or shared memory can make a job fit, but it can also make it slower.
CONCEPTUAL ONLY · ACTUAL BEHAVIOR VARIES BY MODEL, PRECISION, GPU, CONFIGURATION, AND COMMIT.
Forge has a lot of controls, but you do not need to learn them all at once. Choose the route that matches your current state.
Choose between the documented Windows archive and the advanced Git route before downloading anything.
Choose an install path02ALREADY INSTALLEDUnderstand the console, localhost, model files, and the clean baseline to establish before adding extensions.
Open the first-run guide03CHOOSING A UIDecide between a form-and-tab WebUI, a node graph, a canvas-first app, or a multi-UI manager.
Compare local image UIs04RETURNING USERSee the dated state of the original repository and keep Forge Neo, reForge, and Forge Classic separate.
Read the status snapshotThese are the details that prevent most wrong downloads, mismatched expectations, and avoidable setup work.
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.
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.
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.
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.
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.
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.
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.
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.
The original README documents a Windows one-click package. The handoff is short, but each step has a distinct purpose.
We do not mirror installers, rename third-party bundles, or invent checksums that GitHub does not publish.
We separate verified project facts from community reports and keep stale information visibly dated.