banner banner banner
Incredible artificial intelligence Easy Diffusion 3.0. The Middle and High School Guide
Incredible artificial intelligence Easy Diffusion 3.0. The Middle and High School Guide
Оценить:
 Рейтинг: 0

Incredible artificial intelligence Easy Diffusion 3.0. The Middle and High School Guide


https://www.python.org/downloads/windows/

https://git-scm.com/download/win

https://Stablediffusionweb.com/#demo

– Stablecog is a very easy to use, but at the same time very interesting web service. Unfortunately, it’s paid. However, you can create twenty free images per day. I liked it because out of ten models you can choose two created by our compatriots. These models are called Kandinsky and Kandinsky 2.2. In addition, you can increase the resolution of the created image four times (for example, from 1248x832 to 4992x3328).

Program website:

https://stablecog.com/generate

– Easy Diffusion is a completely free Artificial Intelligence system that combines the capabilities of using Midjourney and Stable Diffusion. Easy Diffusion offers you a convenient and simple web interface that allows you not only to create very beautiful images, but also to connect various additional modules and models to its work. By default, the program already has the well-known Stable Diffusion model preinstalled. Additionally, you can download many other models from www.civitai.com, including the «Openjourney» model, which will allow you to replace the use of Midjourney. Another advantage of the program is that it is very easy to install on a computer or laptop and works with not very powerful video cards. The only drawback of the program is the time it takes you to create images. For example, if an image in “Dreamstudio.ai” is created in 20 seconds, then in Easy Diffusion it can take up to 120 seconds to create.

Once again, I would like to draw your attention to the fact that Easy Diffusion is an easy-to-install assembly of software packages (or, in other words, a distribution kit) of the Stable Diffusion Artificial Intelligence system for various operating systems. Here and further, I will not talk about Stable Diffusion, but rather Easy Diffusion due to the fact that it is with this distribution and program that we will work.

Program website (program distribution):

https://github.com/easydiffusion/easydiffusion

Step 2. Install Easy Diffusion

In order for us to install the Easy Diffusion program, follow the following link and download the required distribution for your operating system (MS Windows, Linux or MacOS):

https://github.com/easydiffusion/easydiffusion

There are three distributions on the program page:

• For MS Windows operating system.

• For the Linux operating system.

• For the MacOS operating system.

Before installing the program, please pay attention to the minimum requirements for your computer. You must have:

– Video card from NVIDIA with 2 GB of RAM (better with 4 GB). A laptop video card will do, but keep in mind that you must have the latest drivers installed not only for the video card, but also for all components of the MS Windows system.

– The minimum amount of computer RAM is 8 Gigabytes.

– The minimum amount of disk space (either on the «C:\” drive or on any other drive) is 40 Gigabytes (25 for Easy Diffusion and 15 for models). I recommend installing the program on a computer flash drive (not an external drive, but an internal drive of a computer or laptop). It will make image creation faster.

Next, we will consider installing Easy Diffusion on a computer with the MS Windows operating system.

Before installing, you need to make sure that everything is in order on your MS Windows system. To do this, you need to right-click on the «My Computer» icon and select the «Manage» command from the context menu. The Computer Management program will open, and in the Device Manager section you will see not only all the devices on your computer, but also their operating status. If there is a malfunction of any of the devices, you need to install new drivers for this device. You can find them on the Internet.

Next, download the Easy-Diffusion-Windows program.

After downloading the file named Easy-Diffusion-Windows, launch the installation and click the «Next» button:

We agree to the license agreement and click the «I Agree» button:

Click the «I Agree» button again:

Select the disk on which the program will be installed. The main recommendation is that the program should be located in the root of the disk, that is, it should be installed on the disk, but not inside other folders, but only in its own.

For example, on the drive C:\EasyDiffusion\, as shown in the image below:

Or on drive D:\EasyDiffusion\, as shown in the image below:

Select the disk you need and click the «Install» button.

The process of installing and unpacking the files on your computer has begun:

The installation process takes some time.

During this process, the program will install all the necessary files and models for work, including installing the Stable Diffusion model (version 1.5), with which you will create your first works of computer art:

The program will install other auxiliary models (for example, GFPGAN model, Real-ESRGAN model, etc.), which are used by Easy Diffusion to improve the images you create.

At the end of the process, a CLIP model will be established, which allows you to determine how well the generated image matches the query you wrote.

After installation is complete, the following window will appear:

But don’t rush to click the «Finish» button.

Be sure to check the «Create Desktop Shortcut» box and uncheck the «Run Easy Diffusion 3.0» box.

And only now click the «Finish» button.

After completing all the steps, the program will be completely installed on your computer.

Why didn’t we launch the program immediately after installation?

All this is necessary because before we start working with the Easy Diffusion generative Artificial Intelligence system, we need to download and install a few more additional model files that will allow us to create incredibly beautiful images.

What is a model?

A model is a file containing a set of parameters of a trained neural network. The file size can be small or it can be several GB in size. It depends on what a particular model is created and used for.

Each model is trained on a large number of thematic images. A set of images or data is called a «dataset».

There are a large number of different models for creating photorealistic images in various artistic styles. Some models work better for creating anime images, while others work better for imitating famous artists.

To continue working, we need to follow the following links and download the latest versions of the model files with which we will work:

– Realistic Vision версия 5.1

(https://civitai.com/models/4201/realistic-vision-v51);