Skip to content

How-ToGPU

How to Generate AI Images with Fooocus

How to generate images locally with official Fooocus: download the Windows package from the lllyasviel/Fooocus GitHub Releases page, extract it to a short path with plenty of free disk, run the official launch script and wait for the first model download. Check the official README for current GPU and RAM requirements. It sits between Amuse and ComfyUI as a prompt-first local app.

By , Editorial team

3 min read

How to Generate AI Images with Fooocus

Fooocus is a local, offline-friendly image generator from the same developer as ControlNet, built so that you can focus on the prompt instead of a node graph. Officially you download the Windows package from the project's GitHub Releases page, extract it, and run the included launch script. The first start pulls model files, so you need a fair amount of free disk as well as a supported GPU.

Forge PC has not tested Fooocus's image quality, speed or installer on a lab bench. The setup path below follows the official lllyasviel/Fooocus GitHub project. Always download the package from that official repository, not from a random "Fooocus download" site.

How it differs from Amuse and ComfyUI

If you already followed our Amuse guide or our ComfyUI install, Fooocus sits in between: less of a node workshop than ComfyUI, and more of a traditional, download-and-run desktop app than some of the store-front tools. We compared ComfyUI with Amuse in a separate versus piece. Fooocus is worth trying if you want a local prompt box without first learning a graph. It is not a hosted website, and it is not a reason to skip Stability Matrix if you already like that manager; our Stability Matrix guide remains the better starting point if you want several UIs under one installer.

What you need

Check the official README on the GitHub repository for the current hardware list before you download, because requirements can change between releases. The project's documented baseline has been an NVIDIA GPU with modest VRAM and a reasonable amount of system RAM, with a separate, higher-VRAM path for AMD via DirectML, plus tens of gigabytes of free disk for the application and the first model downloads. If your GPU already struggles with other local image tools, read that README rather than assuming Fooocus will be lighter.

A spare NVMe drive helps when the first launch starts pulling model weights. Our SSD guide and the disk-space how-to are useful if the boot volume is already tight.

Install and launch

  1. Open the official repository at github.com/lllyasviel/Fooocus and go to Releases.

  2. Download the official Windows package attached to the current release. Do not use a third-party "one-click" fork unless you already trust that project; this guide is about the official build.

  3. Extract the archive to a short path on a drive with plenty of free space, for example C:\Fooocus. Avoid unpacking it into a cloud-synced folder or a path so long that Windows hits path limits.

  4. Run the official Windows launch script in that folder (the repository ships a .bat file for this). The first launch can take a long time while models download, and it needs a working internet connection for that step.

  5. When the UI appears in your browser or window, type a prompt and generate. That is the intended loop: describe the image, generate, then adjust the prompt or the official style presets if the project offers them in your build.

If Windows Defender or SmartScreen flags a freshly extracted script, confirm you came from the official GitHub release before you continue. If the first download stalls, check the README and the project's troubleshooting notes rather than deleting random files in the model folder.

Practical use

  • Be specific in the prompt (subject, setting, lighting, lens style) rather than stacking dozens of quality buzzwords.

  • Keep generations you like in a folder you control. Local tools still write files to disk; they do not automatically back them up.

  • Stay on the legal and sensible side of image generation: do not use it for images of real people who have not agreed, and do not try to make unlawful content.

  • When you want more control later, ComfyUI or a managed stack such as Stability Matrix may be the better next step. You can keep Fooocus for quick prompts.

Our verdict

Download Fooocus only from its official GitHub Releases page, extract it to a short path with plenty of free disk, run the official launch script, and wait for the first model download to finish before you judge it. It is a local, prompt-first alternative to ComfyUI and Amuse, not a cloud app. Check the official README for current GPU and RAM requirements rather than relying on a remembered VRAM number. Forge PC has not tested Fooocus; this guide follows the official project.

The bottom line

Download Fooocus only from its official GitHub Releases page, extract it to a short path with plenty of free disk, run the official launch script, and wait for the first model download to finish before you judge it. It is a local, prompt-first alternative to ComfyUI and Amuse, not a cloud app. Check the official README for current GPU and RAM requirements rather than relying on a remembered VRAM number. Forge PC has not tested Fooocus; this guide follows the official project.

Sources

  1. 01lllyasviel, Fooocus official GitHub repository

About the author

Forge PC Staff

Editorial team

The shared byline for articles researched, written and edited by the Forge PC editorial team. How we source, check and correct our work is set out in our editorial policy.

More from Forge PC Staff

Read next

How to Enable AMD Fluid Motion Frames (AFMF 2.1) on a Radeon Graphics Card

How-To

How to Enable AMD Fluid Motion Frames (AFMF 2.1) on a Radeon Graphics Card

To enable AMD Fluid Motion Frames, install Adrenalin 25.3.1 or newer, then select the HYPR-RX profile (RX 7000 and newer) or turn on AMD Fluid Motion Frames under Gaming > Graphics, globally or per game. AFMF 2.1 works on RX 6000 cards and newer in DirectX 11, DirectX 12, Vulkan and OpenGL games, with VSync off; RX 6000 cards need exclusive full screen.

Forge PC Staff2 min

AMD's FSR 4.1.2 Unreal Engine 5 Plugin Brings ML Upscaling to RX 6000 Cards

News

AMD's FSR 4.1.2 Unreal Engine 5 Plugin Brings ML Upscaling to RX 6000 Cards

AMD's FSR Unreal Engine 5 plugin now uses FSR Upscaling 4.1.2, bringing ML-based upscaling to Radeon RX 6000 cards and select Ryzen integrated graphics as well as RX 7000 and RX 9000, in UE 5.3 to 5.8 games that adopt it. It's DirectX 12 only for now and adds Frame Generation 4.0.2 with driver-assisted frame pacing on RX 9000 cards.

Forge PC Staff2 min

NVIDIA's DGX Spark HPC Developer Kit Links Four Sparks Into a 512GB Desk-Side Cluster

News

NVIDIA's DGX Spark HPC Developer Kit Links Four Sparks Into a 512GB Desk-Side Cluster

NVIDIA's DGX Spark HPC Developer Kit, announced at SC26 on 16 November 2026, links four DGX Spark systems in a ring over ConnectX-7 with no network switch, for 512GB of combined memory and 20TB of NVMe storage. NVIDIA says it can spread models of up to 700B parameters across the nodes with NVFP4. No UK kit price yet; Scan sells two-Spark bundles at about £12,845.

Forge PC Staff3 min

Best Free Benchmark Software for PC in 2026: CPU, GPU, SSD and AI Tests

Best Picks

Best Free Benchmark Software for PC in 2026: CPU, GPU, SSD and AI Tests

The best free PC benchmarks in 2026: Cinebench 2026 for CPUs, Unigine Superposition Basic or 3DMark's free Steel Nomad test for graphics cards, CrystalDiskMark for SSDs, Geekbench 7 for cross-platform scores, Geekbench AI for NPUs, Blender Benchmark for creators and OCCT for stability. Run each test twice and download only from official sites.

Forge PC Staff5 min