AI painting tool Fooocus2.1 Chinese version

AI painting tool Fooocus 2.1 Chinese version + 100G model package

The reason why it can complete such high-quality image generation tasks is that it uses the latest SDXL 1.0 model, which can generate high-quality images of various styles through simple prompt words. Today I will share with you one+100G model package,I hope I canGive爱好者带来了新的创作可能。汉化作者是:B站大佬刁璐璐汉化。目前官方Fooocus版本已经更新到2.2.1,需要英文版可以去GitHub项目获取。


What is Fooocus

Fooocus is an image generation software (AI painting tool based onGradio).

Fooocus is a rethinking of Stable Diffusion and Midjourney designs:

  • Learn from Stable Diffusion, which is offline, open source, and free.

  • Learned from Midjourney that no manual adjustments are required, users just need to pay attention to the prompts and images.

Fooocus includes and automatesMany internal optimizations and quality improvements. Users can forget all those difficult technical parameters and just enjoy the interaction between humans and computers, "exploring new thinking media and expanding human imagination." .

Fooocus simplifies installation. The number of mouse clicks required between pressing "Download" and generating the first image is strictly limited to 3 times. Minimum GPU memory requirement is 4GB (Nvidia).

Fooocus official websiteGitHub:

Minimum requirements

The following are the minimum requirements for running Fooocus locally.If your device has capabilities below this specification, you may not be able to use Fooocus locally.(Anyway, if your device is less powerful and Fooocus still works, please let us know.)

operating systemgraphics processorMinimum GPU memoryMinimum system memorysystem exchangenotes
Windows/LinuxNVIDIA RTX 4XXX4GB8GBrequiredfastest
Windows/LinuxNVIDIA RTX 3XXX4GB8GBrequiredTypically faster than RTX 2XXX
Windows/LinuxNVIDIA RTX 2XXX4GB8GBrequiredTypically faster than GTX 1XXX
Windows/LinuxNVIDIA GTX 1XXX8GB (*6GB not sure)8GBrequiredOnly slightly faster than CPU
Windows/LinuxNVIDIA GTX 9XX8GB8GBrequiredFaster or slower than CPU
Windows/LinuxNVIDIA GTX < 9XXnot support///
WindowsAMD graphics card8GB (updated on December 30, 2023)8GBrequired~3x slower than Nvidia RTX 3XXX via DirectML (*ROCm reserved)
LinuxAMD graphics card8GB8GBrequiredAbout 1.5x slower than Nvidia RTX 3XXX via ROCm
appleM1/M2 MPSsharedsharedsharedAbout 9 times slower than Nvidia RTX 3XXX
Windows/Linux/MacOnly uses CPU0GB32GBrequiredAbout 17 times slower than Nvidia RTX 3XXX

Fooocus 2.1 Chinese version


Simple interface: Fooocus 2.1 inherits MJ's user-friendly interface, making the operation intuitive and simple, and even novices can get started quickly.
Local deployment: Unlike online tools that require server support, Fooocus 2.1 can be fully localized, ensuring the privacy and flexibility of artistic creation.
Image generation: Fooocus 2.1 is able to produce high-quality images, which makes it the best among AI painting toolsMuch attention.
Chinese translation support: This version specially provides Chinese translation, which greatly facilitates Chinese users. They can enjoy the fun of AI painting without worrying about language barriers.
One-click package for lazy people: In order to better serve users with different technical backgrounds, the Chinese version of Fooocus 2.1 provides one-click package for lazy people. The installation process only takes a few steps to quickly enter the creative state.


Baidu Netdisk:
Extract password: p2rp
Unzip password: muhou

The installation package size of the Chinese version of Fooocus 2.1 is 224G, and users can selectively download it according to their own needs. The installation package includes a one-click lazy package, which is recommended for users with low technical background. It can be used after downloading and unzipping, without the need for cumbersome configuration processes.

You can also download the latest English version of Fooocus directly from the Fooocus official website:

After downloading the file, unzip it and run "run.bat".


When you start the software for the first time, it will automatically download the model:

  1. It will be based on different presetsDefault modelDownload to the folder "Fooocus\models\checkpoints". If you don't want to download automatically, you can download it in advance.
  2. Note that if you use inpaint, the first time you repair the image, it willDownload Fooocus' own inpaint control model from here, the file is "Fooocus\models\inpaint\inpaint_v26.fooocus.patch" (the size of the file is 1.28 GB).

After Fooocus 2.1.60 you will also haverun_anime.batandrun_realistic.bat. They are different model presets (and require different models, but they are downloaded automatically).Please see here for more details.


If you already have these files, you can copy them to the above location to speed up the installation.

Please note that if you see"MetadataIncompleteBuffer" or "PytorchStreamReader", your model file is corrupted. Please download the model again.

Here's what's happening on a machine with 16GB of system RAMand6GB VRAMTested on a relatively low-end laptop (Nvidia 3060 laptop). The speed on this machine is about 1.35 seconds per iteration. Pretty impressive - 3060-equipped laptops these days are generally very affordable.


Additionally, many other software have recently reported that drivers above Nvidia 532 are sometimes up to 10 times slower than Nvidia driver 531. If your build takes a long time, consider downloadingNvidia Driver 531 LaptoporNvidia Driver 531 Desktop.

Please note that the minimum requirement is4GB Nvidia GPU memory (4GB VRAM)and8GB system memory (8GB RAM). This requires the use of Microsoft's Virtual Switching technology, which in most cases is automatically enabled by Windows installations, so you usually don't need to do anything about it. But if you're not sure, or you turn it off manually (does anyone really do that?), orIf you see any "RuntimeError: CPUAllocator", you can enable it here:


If you still see "RuntimeError: CPUAllocator", make sure you have at least 40GB of free space on each drive!

If you are using a similar device and still cannot achieve acceptable performance, please ask an issue.

Please note that different platformsMinimum requirementsis different.

Fooocus 2.1 Chinese versionDrawing test

Fooocus can be considered a simple version of Stable Diffusion or a free version of Mid Journey. It uses the SDXL core and has a simple interface similar to Mid Journey. It does not require high hardware conditions to run.

The basic operation of Fooocus is extremely simple. You only need to enter the prompt word and click to generate. Below are the different effects I generated using different prompt words.


Selfie POV, Cat taking selfie from top of Burj Khalifa, Cinematic, ultra-realistic, highly detailed

AI绘画工具 Fooocus2.1 汉化版-1


Fooocus is a free and open source AI image generator based on stable diffusion. It attempts to combine the advantages of stable diffusion and mid-term journey: open source, offline, free and easy to use. Fooocus optimizes the stabilization diffusion pipeline to provide excellent images. You can spend less time adjusting settings and more time creating the images you want.


Leave a Reply

Your email address will not be published. Required fields are marked *