This article has been contributed by Dr. Sairaj Patki, Assistant Professor, Psychology, FLAME University.
The Sony World Photography Awards unveiled the winning entry in their creative photo category in March: PSEUDOMNESIA: The Electrician, a black-and-white image of an older woman embracing a younger one. The shot is described in the press release as “haunting” and “reminiscent of the visual language of 1940s family portraits.”
However, the artist, Berlin-based Boris Eldagsen, declined the medal. He declared that his photograph was not a real photograph. To everyone’s shock, the image had been created using DALL-E 2, an AI image generator.
Owing to incidences like these, the creative world has been buzzing with chatter about AI taking over and about the seemingly morbid future of artists. Some artists, on the other hand, are embracing the new technology and exploring incorporating AI in creating artwork that traditional means do not allow.
The burning question, however, is about human creativity. Is it the end of real creativity? Or is it just a nudge for us to reconsider and redefine human creativity?
AI art generators make digital graphics from short lines of text, or ‘prompts’. They can develop a variety of art mediums, including music, collages, digital art, and others. They analyze existing art styles and compositions using neural networks and machine learning to develop new digital artworks. AI art generators may now be used to make logos, flyers, 3D representations, and more. MidJourney, Jasper, DALL-E, BlueWillow, and Leonardo AI are some AI art generators that have gained immense popularity in recent times.
You need not know any programming language or have any hands-on artistic skills yourself. With these tools, anyone can create images (maybe it cannot all be called “art” yet) with a few clicks and within a few seconds. The image below, for instance, was created using the AI art generator, Leonardo AI, by providing the AI model with a brief series of prompts.
Image Created by Prof. Sairaj Patki Using Leonardo AI
The ‘Human’ Contribution to AI-Generated Art
Let us first understand how AI generates art. Data (in this case, photos) is collected by AI art generators and utilized to train the AI using a deep learning model. Imagine how your drawing teacher in school would show you samples of artwork and ask you to recreate them. Machine learning goes through this same process but with millions of images available on the web or those uploaded by the art creator.
Patterns, such as the style of specific pieces of art, are recognized by the ML model. The AI then uses these patterns to generate unique graphics in response to a user’s prompts. These prompts are the most crucial part of the process.
The more detailed the prompt you give, the better the results generated by the AI. Iterative processes often also allow you to fine-tune your intended outcome by making several images. Some platforms even allow you to provide ‘negative prompts’, which help the model exclude things that must not appear in the final creation.
Keeping Real Creativity Alive
Any creative process begins with creative thoughts. A photographer, a cinematographer, a choreographer, a painter, or a writer, all go through a similar process. They visualize the final creation in their minds. They make keen observations of the world around them and seek inspiration from nature and earlier creators.
Cognitive Psychologists describe and measure creativity using the concepts of divergent thinking and remote connections. While the AI has the advantage of having access to millions of ‘inspiring’ images, it still fails to make meaningful associations on some occasions. The most common example of the limitations of current AI art generators is the likelihood of creating human figures with six fingers or four toes.
Can we revisit our traditional definitions of creativity? Can we train the younger generation of artists to use AI as a tool to boost their creations? The core training of keen observations, critical evaluation of existing work, and visualization will remain crucial even in the near future. The ways of assessing and judging creativity would change. For instance, an individual generating more complex and intricate prompts leading to a more realistic and flawless image may be termed more creative than one who cannot.
In short, we will have to become more creative about defining, measuring, and executing human creativity if we do not wish to feel obsolete before the competition given by AI.
In this digital era of technology, AI is emerging as a way to make work easier and faster. Companies are adopting AI to build software with advanced capabilities. Text-to-image is a feature of software powered by AI to convert natural language inputs into visually appealing images.
An image is a great way to express something in a way that positively hits the viewer’s mind. You might be amazed to know the fact that the Human mind can process images almost 60,000 times faster than normal text. This is one of the reasons why companies prefer images over text for advertisements and marketing campaigns on social media.
Thanks to AI, we have opportunities to create visually appealing images from text input. In simple words, you can use a text-to-image generator to create images. So for the sake of your convenience, we have provided the list of the best text-to-image generators along with their salient features, pros, cons, and pricing.
Text-to-image generator is a software that generates images based on the input you provide. For example, If you want an image of a red car flying in the air, you can easily create that image just by typing this input into the search field.
Global AI market size from 2022 to 2026
A deep learning algorithm and technology like generative adversarial networks (GANs) work behind the scenes for the processing of each input. The GAN consists of a generator and discriminator, whenever you pass any input to the software, the generator synthesizes an image based on the query and sends it to the discriminator. The discriminator distinguishes the image and sends it to the generator for modification. The process goes on again and again until it creates a perfect image for you. The technology keeps updating with time and this text-to-image generator is becoming more powerful day by day with different updates.
List of Top 10 Text-to-Image Generators
Text-to-image generators allow usto generate images based on a text description. Text generation models can be used together with text-to-image models to create diverse text prompts. It helps to shape our imaginations and create beautiful images. Let us discuss some of the best AI-based Text-To-Image Generators.
Photosonic
Rating
3.4/5
Launched in
2020
Photosonic is an AI tool of the very popular AI-based content creation company Writesonic. It started its operation in October 2020, this company has raised more than 2.6 million in funding. Since Writesonic was already engaged in the development of AI to make content production easier for companies, Photosonic is a great addition to their list.
Photosonic
This tool has the capability to convert your imagination into digital art that you can use in your project. Varieties of options are available to give your art a texture, like painting, illustrator, 3-D, cartoon, fantasy, anime, etc. Whatever prompts you, type it in the search field, and it will provide you with the best results as per your requirement.
Square, vertical, and horizontal are the orientation of the image which you can choose to create the perfect fit for your image. It offers a free plan in which you will get 15 credits that you can utilize to generate images.
Pros:
Availability of free plan
Full right to use images commercially
Based on the latent diffusion model
Simple to use
Cons:
Images are sometimes blurry and distorted
Less credit in the free plan
Pricing:
Free: $0 /month (15 credits)
Basic: $10 /month
Unlimited: $30 /month
Jasper.ai Art
Rating
4.5/5
Launched in
2021
Jasper Art is an incredible tool to generate images using text prompts. The AI of this tool is well-trained and capable of identifying the difference between a sad dog and a happy dog. You can apply different styles, moods, and mediums to your imagination by selecting the appropriate option from the dropdown menu, which again enhances the quality of your images significantly.
Jasper.ai Art
The most interesting part of this tool is “No credit”, yes you’ve heard right, while other text-to-image generators use credit systems to generate images, this tool provides unlimited image generation facility with their plan ” Jasper Art Unlimited”. Although you are not provided with any separate free plan to test this tool, you get 5 days of free access to the tool in the paid plan at no additional cost.
The amazing part is that you can create up to 200 images in the 5-day free access with 2k resolution, and after that unlimited images with a paid plan. There is a separate knowledge base provided by the company to help you use their tool more effectively. This simple and powerful AI tool will skyrocket your productivity through realistic images of your imagination.
Pros:
2K high-resolution images
Very Simple to use interface
No credit limit
Variety of styles, moods, mediums, and keywords to choose from
Dall-E is a new AI system that can create realistic images from the description of natural language. It’s a very popular text-to-image generator created by Open.ai and has a separate craze in the market. No doubt! Creating images from text is an integral feature of this tool but on top of that, it can also edit the existing image according to your need so that looks damn real.
Dall-E
Launched in January 2021, Dall-E gathered so much popularity among the people, and soon after one year of launch, Open.ai released the updated version of Dall-E with the name Dall-E 2. Dall-E 2 is more efficient and capable than the previous version which can create images with 4X greater resolution.
Also, you can create different variations of the generated image and make them more unique. Keep in mind that every time you create an image, it will cost you one credit, and every time you try different variations, it will charge an additional credit. Overall, Dall-E is a great tool to consider for generating images from a text prompt.
Pros:
Availability of free 50 credits without a time limit
The image creation process is relatively fast
Image variations
Editor to edit the generated image
Filters violating, hateful, and sexual prompt
Cons:
Low art quality for some prompt
Don’t have the option to choose an art style
Pricing:
Free: 50 credits on first-time signup and 15 credit every month
Paid: 115 credits for $15 on top of the free credits
Fotor
Rating
4.4/5
Launched in
2009
The Fotor AI image generator is the most powerful yet underrated AI image generator that holds amazing capabilities to create high-resolution images from a text prompt. The most interesting part is that it is completely free to use, and you can create unlimited high-quality images. The more Description you provide in the search box, the more accurate result you’ll get.
Fotor
Once you’ve generated your image, you can play with different styles and apply them to the newly generated image to get the desired result. It supports the length and width of images between 512 Px to 2048 Px. You can also select the orientation of the image from the square, landscape, or vertical.
Whenever you refresh the image, it will generate a different image from the same text prompt and whenever you choose from a different style it will refresh the image and apply the style in no time.
Midjourney is a text-to-image generator that is developed by an independent research lab. It is a self-funded initiative of some people to harmonize design with AI. To access this tool and create realistic high-quality images, you need an account on discord, because Midjourney is only accessible as a bot on the discord app.
Midjourney
Images generated by this tool are of high resolution and come with different variations. To generate an image, you need to first go to the Midjourney website and click on the button “Join the beta”, after that you’ll get a ship-like icon on your discord app. Just click on the icon and join any newbie room to start generating images. Use the command prompt and type your text description of whatever you want to create.
Midjourney creates four variations of each image and you can try different variations to get the appropriate result. Also, keep in mind that it doesn’t work on a credit system, it works on a minute session system. This means, whenever you type a prompt in the command field it takes some time to render the image, that time is deducted from your plan.
The process of generating an image takes GPU resources, hence it provides two options in their pricing plan, Fast GPU time and Relaxed GPU time. The simple difference between these two is, the Fast GPU time generates the image in priority and is faster than the relaxed GPU time.
Pros:
High-resolution images
Different variations
Personal bot chat
Reasonable pricing
Community gallery access
Cons:
Complex to use
Available only through discord
Private visibility feature at an additional cost of $20/month
Pricing:
Free: 25 min/Lifetime
Basic: $10/month and 200 min/month
Standard: $30/month and 15 hrs/month
Corporate: $600/month and 120 hrs/month
Nightcafe
Rating
5/5
Launched in
2019
Turn your imagination into reality by leveraging the benefits of Nightcafe, an AI-based tool. Headquartered in Cairn, Australia, it generated more than 35 million artworks till October 2022. Since it also generates images from the text prompt, there are some features that distinguish it from the rest. Let’s have a closer look at its unique features.
Nightcafe
Nightcafe offers different algorithms that work on the backend to create beautiful images like Stable diffusion, CLIP+Guided diffusion also known as coherent, VQGAN+CLIP also known as Artistic, and OpenAi Dall-e 2 algorithm. You can choose any of the following algorithms and also choose varieties of styles to create your masterpiece.
Apart from creating images from text, you can also make appropriate changes to the existing image. After uploading the image, you are required to enter the text description with the changes you want in your image. One drawback of Nightcafe is that you need to pay extra credits for higher-resolution images.
Pros:
Different algorithms to choose from
Varieties of styles
Advanced option
Your creation belongs to you
Cons:
Charge extra credits for high-resolution image
Only 5 credits available to try this tool
Pricing:
AI Hobbyist: $9.99 /month
AI Enthusiast: $19.99 /month
AI Artist: $49.99 /month
AI Professional: $79.99 /month
Canva
Rating
4.7/5
Launched in
2012
Canva is not a new name for designers and anyone who loves to design. Since Canva offers varieties of designing services and is the leader in this segment, then how can it lag behind in the race of text-to-image generation? Recently Canva has launched its text-to-image generation AI to empower designers to create unique pieces of images.
Canva
Because it is also evolving its technology like other AI tools, you might have to face some distortion in the image. One major plus point of the Canva text-to-image generating tool is that it is completely free to use, with no credit limit. You can directly use the generated image in the project you are working on.
Different styles like photo, drawing, 3-D, painting, pattern and concept art are available to give an image a different look and feel. After typing the text prompt and selecting the desired style, you only need to hit the generate button and boom! Your unique image is ready to use.
AI-based photo-realistic images are the trend nowadays and Stable Diffusion is fueling this ongoing trend with its robust text-to-image generator. The most fascinating thing is that it doesn’t charge a single penny from you for the generation of images. It generates images on Nvidia and AMD GPUs of more than 6GB RAM to provide high-quality images in a short period.
Stable Diffusion
To increase efficiency and help you generate more accurate images, it provides a prompt database of more than 9 million searches. You can utilize this database and learn how to enter the text prompt effectively to generate high-quality intended images with less distortion.
The most important thing is that it takes care of your privacy seriously, it never stores any of your personal information, text prompts, or images. Even if you want to share your design, there is a separate button for it to share with the community, otherwise, it will remain private for you.
Since it is open source, you can install it locally on your computer and start creating AI images at no cost. Their AI community will help you with all the setup. Make sure you have an Nvidia GPU with more than 6 GB of ram for quick image generation.
Pros:
Easy-to-use interface
Doesn’t store any data about text and images
A huge database of text prompts
Advanced setting option
High-quality images
Free to use
Can install it locally
Cons:
Doesn’t have an option for styling and variations
Pricing:
Free of cost
Dreamstudio
Rating
4.5/5
Launched in
2006
Dreamstudio beta is an image generation AI powered by stability.ai. Don’t be confused between Dreamstudio beta and Stable Diffusion because both are powered by stability.ai, the only difference is that Stable Diffusion is open source and Dreamstudio is paid one. Dreamstudio provides free 100 credits to test the product and if you like to continue then you can purchase additional credits.
Dreamstudio
There is flexibility to utilize the credits based on the size and resolution of the image and it costs somewhere between 0.5 credits to 9.5 credits per image. The higher the resolution, the higher credit it will charge. It is empowered to create realistic images, art, portraits, paintings, and as many things as you can imagine and write in the text prompt properly.
Numerous options are available to choose from and get the desired result that best suits your imagination. Additionally, you have the flexibility to choose the different versions of the Stable Diffusion algorithm.
Pros:
Cheaper than competitor
Simple to use UI
Vast styling option
Ability to choose from different stable diffusion versions
High-resolution images
Cons:
Need to pay high credit for high-resolution images
Pricing:
100 free credits
StarryAI
Rating
4.4/5
Launched in
2021
StarryAI is another AI art generation tool that is also available in the form of iOS and Android mobile apps. To turn your imagination into reality and make images from natural language descriptions, this tool provides 5 free credits every day. It means you can leverage the benefit of AI image generation every day at no cost if you don’t want so many images.
Starryai
Just like other text-to-image generation tools, it also offers varieties of styles to choose from, and on top of that, you can create your own collection of art images. There is an explore tab in which you can see the images of other creators who’ve published their art in the community, you can take inspiration and make your own.
The most fascinating thing is that you can earn credits for image and video creation after completing certain tasks, like sharing the artwork on social media, watching ads, etc.
Pros:
Easy to use
Different styles
Availability of iOS and Android app
Cheaper alternative
Credits Top-up everyday
Cons:
So many distortions
Creation is not always perfect
Pricing:
5 free credits every day
Conclusion
AI has made text-to-image generation easier and faster without any prior experience in designing. These tools will empower you to turn your imagination into realistic images with so many styling options. So choose the tool and figure out the best one that suits your needs.
FAQ
How do AI image generators work?
The technology can vary but most AI image generators use diffusion models. These work by destroying their training data through the addition of Gaussian noise, and then reversing the process to remove noise from the image.
Is DALL-E free to use?
Dall-E is not entirely free. The service runs on “credits”.You get 50 free credits at signup, and then 15 credits free per month after that.
What is the AI image generator?
The AI image generator is a tool that can be used to generate realistic images from text.
AI is no longer a future concept, it is happening now. Technology has evolved a lot and is still growing rapidly. AI has fueled growth by making tasks easier and faster. Dall-E and MidJourney, both are AI-based text-to-image generators that hold the capability to generate mind-blowing digital images just by taking input from you.
Isn’t it fascinating that you’re just typing something and AI is providing you with the desired images? Actually, it’s really cool stuff to explore and learn.
Both Dall-E and MidJourney do the same thing which is to generate images from the user query, but certain factors differentiate these two. Here in this article, we will compare Dall-E and MidJourney, so read the whole article and update your knowledge with the latest technology.
AI Image Generators have become the next big thing on the internet. As both are best-known and arguably the most advanced image generators, both of them have the potential to provide you with great results.
Let us look into the different aspects such as their development, pricing, art quality and others. of MidJourney and DALL-E to compare and decide which one is the best among these two.
Development Journey
Dall-E is an AI system developed by OpenAI, a research laboratory headquartered in san-Fransisco. OpenAI was started by Sam Altman and others in late 2015 to develop AI-based solutions that solve different tasks and make human life much easier. Dall-E is one of the AI solutions by OpenAI that renders services for image creation.
It is a large language model that was trained on a dataset of text and images, which can generate images from text descriptions, a process known as image generation or image synthesis. It is a 12-billion-parameter version that uses text-image data sets to generate an image from text.
On the other hand, MidJourney is also an AI-based solution developed by an independent research lab that renders the same services as Dall-E does. Since the intention behind the development of AI is the same, which is to train the AI and make them capable of solving complex real-life problems with ease.
MidJourney has emerged as a solution that creates realistic images of any input you provide. It is in the beta phase and continuously learning and upgrading with new features and capabilities. To save the interest of Artists, MidJourney also included DMCA takedown policy in their terms of service. This will empower the artists to request the removal of any art piece if they feel it is violating copyright.
Performance and Capabilities
Dall-E
A lot of training with datasets undergoes to train the system to consistently improve the performance and capabilities. Dall-E uses text descriptions in natural language to create high-resolution images and art pieces. Different attributes, concepts, and styles are mixed and matched to deliver the best results and performance.
Dall-E edit
On the 6th of April 2022, OpenAI launched the upgraded form of Dall-E with the name Dall-E 2. The concept of photorealism became more advanced and efficient with Dall-E 2 which can create realistic art using the data in the caption. The functionality of creating an image is general in Dall-E 2, but on top of that, it can also add some extra information on the existing image and also create different variations of the given images on the basis of the input you provide.
Dall-E uses a technology called Clip (Contrastive language image pre-training) for digital photosynthesis, which is developed by OpenAI. It helps to match the images with their corresponding caption in the best possible way, in simple words it works on text and image pairs. The process of text embedding and image embedding takes place to produce the best result from the given caption.
MidJourney
On the other hand, MidJourney also offers great performance and provides high-quality realistic art from natural language commands. By continuously upgrading the technology and removing the flaws in the system, MidJourney has evolved its capabilities a lot from Version 1 to Version 4.
Every week and month, it releases some updates in the system that further improves the efficiency of the AI. If you compare the results produced by the previous version with the latest version, the image details in the latest version are top-notch with more clarity.
In the previous version if you search “Alien spaceship over the futuristic city”, you’ll find the image with the spaceship but the placement of the spaceship was not well, even the futuristic city was also looking somehow messy. The latest version improved these flaws, now if you search for the same query, you’ll find a picture in which the spaceship is hovering over the city and even the city also looks much more realistic.
Hence, the performance and capabilities of both AI-based systems are pretty much similar and deliver the best result in creating high-quality images.
Quality of Art
Creating an image undoubtedly becomes easy with Dall-E and MidJourney, both deliver exceptional quality and still improving with different updates. Here we have compared the quality of Art created by Dall-E and MidJourney. We have passed the same input which is ” ships sailing in a stormy sea” and get the below result.
Comparison in Art Quality of Dall-E and MidJourney
The left-hand image is created by MidJourney which looks clear and detailed, it recognizes the query very well and renders each keyword efficiently to provide the result. A stormy sea looks cool in the first image with every minute detail like the atmosphere is harmonized with the image providing a look of stormy weather.
On the other hand, Dall-E has also generated the image of ships in stormy weather, but the image looks simple compared to the MidJourney image. The weather is normal and there is not much effect of the storm visible. It looks like ships in the sea and nothing more.
Hence, we can say that MidJourney is more precise and accurate in creating images compared to Dall-E. But still, they are in the beta phase and continuously evolving, so it’s too early to judge the quality.
User Interface and Accessibility
Dall-E
In order to use the Dall-E you need to create an account with OpenAI by visiting their official website and clicking on the signup button. You can choose your email address and password to create an account or simply use your existing Gmail account to create an account with OpenAI. After that, you also need to verify your mobile number to continue further.
Once you complete your signup process, you will get 50 credits for free in your account in the first month and also get 15 credits every month, which you can use for creating an image in Dall-E. Now you’re ready to generate images from a description of natural language.
In the search bar, you can input your imagination via query and the algorithm automatically generates the best outcome based on your search query. Mix and match the images and try different variations to get the best result from your search. You can also upload an image and suggest any changes to it through your command to create a unique piece of art.
MidJourney
MidJourney is currently operating on the discord server only, so to use MidJourney you need an account on the discord. First of all, you need to visit the website of MidJourney and click on the join beta program. After this, you need to accept an invite to the discord server from MidJourney. Now open your discord app and click on the boat shape icon of MidJourney, you can join any newcomer room with the name “newbie”.
Use the prompt /imagine and start creating images from your imagination and get the result from MidJourney. The more precisely you give the input into the command the more accurate result you’ll get. You can also upload your image and apply different variations to it, this will change your existing image to a new modified image based on the changes you want.
Price Comparison
Dall-E
When you just signup in OpenAI, you’ll get 50 credits for free to generate images in Dall-E and also get 15 credits every month. On top of that, you can purchase additional 115 credits for $15 if you are out of credit. This credit will get utilized every time you hit a search prompt and try different variations.
Suppose you enter a search query “A girl looking at the moon at night” and hit the generate button. This will create some pictures for you, if you select any picture and try out different variations of the picture then also your credit will get utilized. In this example, one credit is used when you generated an image and one credit is used when you tried out a variation, hence you consumed two credits from your account.
MidJourney
The pricing plan for MidJourney is a little bit confusing for beginners as compared to Dall-E because it contains several plans and uses algorithms. Let’s compare each of them one by one, but before comparing the plan you need to be clear about certain terminologies like fast GPU time, relaxed GPU time, and private visibility.
Fast GPU time: Whenever you enter any prompt for an image creation it will take GPU resources to render the image, the time taken by the GPU to render the image depends on the complexity, details, quality, and more. So fast GPU mode reduces the time to render the images and gives the output as fast as possible.
Relaxed GPU time: In relaxed mode, GPU doesn’t take your work as a priority and takes its time to render the image.
Private Visibility: your created images are visible to the public unless you put them into private. Your images will be on the server but visible only to you.
Free trial: when you sign up in MidJourney for the first time you will get 25 min/Lifetime fast GPU time. If one image generation takes around 1 minute of time then you can generate 25 images for free with this plan. Keep in mind that every time you generate an image or variation, it will take GPU, hence you’ll be charged minutes while generating a new image and also while creating a variation.
Relaxed GPU time and private visibility are not provided in the free plan.
Basic: You’ll charge $10/month when you opt for this plan. In this plan, you will get 200 min per month of fast GPU time and a personal bot Chat. Relaxed GPU time is still not available in this plan but you can opt for a private visibility feature by paying $20/month additional.
Standard:In this plan, you’ll get 15 hrs/month at $30/month inclusive of relaxed GPU time. But in this plan also you need to purchase the private visibility for $20/month if you want.
Also, for both the Basic and Standard plans you can purchase additional time if you are out for the given time in your plan. It will charge $4 for 60 minutes.
Corporate:This plan is best suited for big design companies that need to generate many art pieces and images. For $600/year, you’ll get 120 hrs/year of fast GPU time and unlimited relaxed GPU time, additionally you’ll get private visibility and a personal bot at no extra cost.
Comparison of Features
Features of Dall-E
Quick edit of the uploaded image based on the changes you want.
Different variations to explore and choose from.
Dedicated collection to store generated images in public or private folders.
Full usage right to commercialize the created image.
Already ensured safety before launching the beta version of Dall-E.
Features of MidJourney
Anyone can join the beta program by using the discord link.
Different variations and high-quality images.
Diversified pricing plans.
Availability of Fast and relaxed mode.
Can upload an image and make changes.
Conclusion
AI has made work easier and effortless, but still, this technology is evolving and developing. Dall-E and MidJourney both of them are outstanding AI tools that help to generate realistic images through natural language. So, join their beta program and explore the new height of AI.
FAQ
Which is better DALL-E or MidJourney?
DALL-E creates more real-looking images whereas MidJourney is more on different art styles.
Can you use DALL-E images for free?
DALL-E 2 is currently free to use, but there is a catch. For the first month, you are allotted 50 free credits to use and 15 free credits after that.
What type of AI is MidJourney?
MidJourney is an independent research lab that produces a proprietary artificial intelligence program under the same name that creates images from textual descriptions, similar to OpenAI’s DALL-E and Stable Diffusion.
How does MidJourney actually work?
MidJourney is currently only accessible through a Discord bot on their official Discord, by direct messaging the bot, or by inviting the bot to a third-party server.
Abira Dutta
