How to create images from text with artificial intelligence

In recent months, the art world has been shocked by the advancement of programs that allow you to create images through artificial intelligence. In fact, many artists around the world began to ask whether this type of image can be considered art or not. Whether you agree with the argument or not, it's undeniable that the technology is impressive, and I'm sure you want to learn how to use it too, don't you?

But after all, how can artificial intelligence create the most unique works of art using just a text command?

Watch the video on the Channel showmetech:

How do AIs that create images from text work?

All the tools available for creating images through text use the Machine Learning (Machine Learning) to perform mathematical calculations without the need for human intervention. With this, the AI ​​can generate incredible images through any text written by the user, without requiring contact with external programs or any type of programming on the part of the user.

The program team GIVE HER is the pioneer in this revolutionary way of making art, and the explanation is surprisingly simple. the neural network GPT-3 da OpenAI was originally used to create texts, scripts, translations and even posts, but it didn't take long for engineers at OpenAI discovered that the network could also be used to create images based on text commands made by the user. In this way, some basic images of chairs, animals and signs were created by AI, starting a new era of art that would leave everyone on the internet in awe.

It is important to note that the GPT-3 is not a genius who simply generates images from scratch, but he was trained through a database with several images that already exist online to edit, morph, create, adjust and combine into a new image, no matter how crazy she is. Now, other companies (including Google) have also come up with their text-based image creation alternatives, but how can you be using them?

What are prompts and how to create them

Prompts are text commands that you send to artificial intelligence. As artificial intelligence needs instructions from humans to perform a task, you will find that, to create images, you will need to send a detailed description of what you want to receive. And this applies to practically all artificial intelligence: creating text, images, video, music and much more.

Creating a command prompt is simple: just imagine what you want to receive and write it as specifically as possible for the AI ​​to understand. For example: if you want to receive a photo of a dog, remember to detail the color of its hair, its size and even the possible accessory that will be in the photo you want the artificial intelligence to create. The same goes for the setting.

Remembering that everything created by a generative AI is based on what already exists on the internet, but it is worth being very detailed to avoid errors. See this example from bingchat, which features Dall-E 3:

See the image created by artificial intelligence Microsoft:

Top image creation tools from text

Several other tools with the same purpose have been created, and of course each one has a different purpose in creating these images. Check out the main tools for creating images from text:

From E 3

Currently in its third generation, it is necessary to have a paid account OpenAI to use this artificial intelligence directly in the Chat GPT, but you can also access the image creation tool from Bing ou via Microsoft Designers, which have this integrated AI and only require logging into your account. Microsoft.

After that, just go to the text bar in the center of the page and type whatever your imagination allows. Remember to use specific terms to help the AI ​​understand what you want, such as “High Definition, Anime, Realistic” among others.

O showmetech already made one Complete article on how to use this tool, be sure to access it!

midjourney

O midjourney is responsible for creating surreal images and is much more accurate than the Slab. To be able to use it, you will need to have an account and the app. Discord installed.

After installing the Discord and log into your account, you must:

1. Log in official website;
2. Click on the “Join the Beta” button;
3. So, connect your Discord account with the website;
4. When connecting, you will have entered the official channel of the site within Discord. In the app, look for one of the channels in the “newcomer rooms";
5. When entering a room, simply type the command “/Imagine” and continue with the text of your choice;
6. Within a few seconds, Discord will display 4 images based on what the user has written.

You will also have the opportunity to edit some parameters of the image to make it the way you want, just perform some commands that appear on the screen.

O showmetech also already made one complete article on how to use the midjourney and more information about plans and text commands so you can become a true expert in this tool, be sure to access it.

crayon

O crayon is based on technology OpenAI, and it is very simple to use. Unfortunately, the parameters of this tool do not allow it to provide such realistic images, but it is possible to generate some very unusual creations.

To generate images in crayon, just go to the official website and type as many keywords as your imagination allows. The website design is very simple and straightforward, so don't worry about getting lost in lots of information and technical jargon. As with previous tools, try to use terms to help the AI ​​understand what you want to see.

Leonardo.AI 

Created by developers JJ Fiasson, Peter Runham and Jachin Bhasme, this artificial intelligence is recommended for those who need to create drafts of videos and even games. It works in a similar way to the other artificial intelligence we mentioned in this text: just type a text command and wait for the photos to be created.

To be able to create images in this tool, you need:

1. Access Leonardo.AI website;
2. If this is your first use, you will need to create an account: you can choose to register your Google, Microsoft, Apple account or make a traditional registration via email and password;
3. Then simply create a username and password. The next screen will only require you to indicate your interest in using artificial intelligence.
4. Finally, on the home screen, simply enter the commands to receive an image never seen on the internet.

The free plan offers 150 credits every 4 hours. For each image, 5 credits are required. If you need more, you can subscribe to one of the plans, which vary between US$ 10 a US $ 48. The website can also be accessed via the app, but for now, it is only available to who has Apple devices.

starryai

O starryai It's a little different from what we've seen so far. The platform (which is also available on cell phones Android e iOS) allows you to create images through three different AIs. Altair produces images similar to the “dreams” we have, that is, he creates abstract images. Orion produces more realistic images and Argo creates images with a more artistic touch.

To create an image, you will need:

1. Create an account using your email Google or Apple;
2. Select one of the three available AI;
3. Type in the text box what you want to see represented by the AI;
4. Select a style, ranging from “Pop Art” to “3D rendering”;
5. Click “Create” and wait a few minutes.

At the end of creation, the application will send a notification saying that your new image is ready. Access or install the application:

• StarryAI website;
• StarryAI application for Android;
• StarryAI iOS app.

Dream by WOMBO

O Dream was created by Wombo and is very similar to StarryAI. Like the previous tool, Dream also offers versions for the web and mobile phones Android e iOS, with the main difference being that images are generated in a few seconds. It also works on Discord, through a server.

To generate your artwork, simply click on the “Create” button and type in what your mind wants. No account is required for its use, but you can publish the image through your social networks. Access the website or install the application on your cell phone:

• Dream Wombo official website;
• Dream Wombo app for Android;
• Dream Wombo iOS app;
• Discord server.

adobe firefly

One of the great innovations of 2023, the adobe firefly can be accessed for free and also creates images completely and free of charge. Up to two photos can be created for free per day and, whoever uses the free plan, receives a photo with a watermark, but you can crop it in an editing application. And use the adobe firefly is quite simple:

1. Access Adobe Firefly website;
2. Log in or create an account through your gmail, Facebook ou Apple ID. You can also use the same account that subscribes to Adobe or Adobe Express services;
3. Then, just type the text commands (preferably in English) and wait for the images to be created.

Showmetech has also already made a complete article on how to use Adobe Firefly, be sure to check it out.

stable diffusion

Appearing on the internet in mid-August 2022, the stable diffusion stands out for being completely free and, in addition to its online version, it can also be installed on computers with a CPU with at least 8 GB of VRAM. If you prefer to do everything on your cell phone, the app Dreamer uses the image creation base of this artificial intelligence.

There is no need to pay anything to use the Stabble Diffusion and its use is very simple, in addition to not requiring any registration. The online platform is also very intuitive and can be used for free. See how:

1. Access Stable Diffusion website;
2. Please click Free AI Image Generator;
3. Enter the text command (preferably in English) on the photo you want to receive and click Generate.
4. Now, just wait for the photo to be created and the time may vary depending on the queue on the website. To save the photo, simply open it in a new tab and download it. See this photo created using the command: “a photo of a man running in the rain, wearing a suit and carrying a bag"

Go to the website or install the application that uses the stable diffusion:

• Stable Diffusion website;
• Dreamer app for iOS;
• Dreamer app for Android.

Microsoft Designers

Launched in 2023 as a complete image editing option reminiscent of Canva, Microsoft Designers It also has a tool that can create images using text commands. Here, DALL-E 3 has been integrated into the service and there is no additional payment required. The step-by-step process for using it is also simple:

1. Access Microsoft Designer website or open the app on your smartphone;
2. Please click Get Started for Free and log in with your account Microsoft;
3. Access the option Image Generator;
4. I typed the text command (preferably in English, but the Microsoft Designers also understands Portuguese) and click Generate.
5. To download the photo, simply click on one of the results and then press the purple button written Download.

See ways to access Microsoft Designers:

• Microsoft Designer website;
• Microsoft Designer app for Android;
• Abeta access for Microsoft Designer for iOS.

Bing Chat (Microsoft Copilot)

Finally, the tool that remembers the Chat GPT It can also generate images using a text command. The good news is that it has DALL-E3, without the need for additional payment and everything takes less than 1 minute to do. The step by step consists of:

1. Access Bing website;
2. Log in with your account Microsoft;
3. Now, just send the text command in Portuguese and wait for the photos to be created;
4. When you click on the photo, you will be directed to a new page and just click Download so that it is saved on your computer.

O bingchat, which is now called Copilot, can be accessed by:

• Bing website;
• Bing app for Android
• Bing app for iOS

Additionally, we bring Those who have the latest version of Windows 11 have already received Copilot integrated into the operating system and can request photo creation at no additional cost.

These were the main ways of creating digital art using texts that are available today! So, which one are you going to use? Tell us in the comments!

See also:

60 funny prompts for you to have fun on ChatGPT

60 funny prompts for you to have fun on ChatGPT

Source: Google, OpenAI, MakeUseOf