Software developers are keen to show off the latest in artificial intelligence, which is why you’ve probably seen an increase in articles and advertisements about various free AI tools anyone can access through a web browser.
Whether you want to generate weird and wonderful AI images from text prompts or create a musical composition in partnership with a computer, there are now plenty of cool AI websites to explore.
These apps are getting better with time, and they can give you a good idea as to what AI can do and where it might be headed in the future.
- Can be used as a creativity prompt
- Easy to save your drawings
- Can take some practice to get right
If there’s an artist inside you, Magic Sketchpad could help bring it out. This free AI tool is an experiment from a team at Google that gets a neural network to draw along with you. Every time you let go of a line, the platform will respond to your scribble by finishing the drawing according to a set category.
The neural network has been trained on millions of doodles mined from the also highly entertaining Quick, Draw! browser-based game. Start Magic Sketchpad by picking a category from the drop-down list at the top right of your screen—there are plenty available, from frogs to sandwiches. The tool knows the sorts of shapes and lines people tend to make when they’re trying to draw simple concepts like a bird, a ship, or a cat, so it can predict what you’ll draw next and finish the doodle for you.
Magic Sketchpad can also help artists augment their work or provide new prompts for creativity, and as far as AI websites go, it’s one of the most entertaining. Maybe one day we could see computers doodling as well as humans do.
- Not just for musicians
- You’ll get results quickly
- No export options
- Can struggle with rhythm
If you’re more of a musician than a sketcher, AI Duet might suit you better. Built by an engineer at Google, AI Duet puts a keyboard down at the bottom of your screen and produces an automatically generated response based on what you play on it. You can click the keys on your screen, hit them on your keyboard, or even connect a MIDI keyboard to your computer.
A traditional approach to a project like this would have involved a programmer coding in hundreds or even thousands of responses to specific patterns a user might play. But AI Duet comes up with its own responses based on a huge database of tunes it has trained on. This gives the program the ability to generate melodies that match a user’s input without any specific instructions.
This is another example of how AI can work with artists to produce new creations, whether that’s for movie soundtracks or background music in games. Theoretically, you could rework one riff an endless amount of times.
- Unlimited images
- Each prompt creates multiple responses
- Lots of flexibility
- Results can take a while
By now, there’s a high chance you’ve seen the creations of AI image generator Craiyon, formerly known as Dall-E Mini. Essentially, it’s a neural network that turns text inputs into images—you type what you want to see, and the system generates it.
It is as simple as typing out what you want to see in the box at the top and clicking Draw. As far as free AI tools go, it couldn’t be much more straightforward.
You can combine two of your favorite fictional characters in a setting of your choosing, or reimagine a famous work of art in a different style— you’ll soon figure out which prompts work best.
To generate images, Craiyon pulls in information from millions of photos online and their captions. That means it has a vast visual knowledge of everything from celebrities to national landmarks.
The results produced by Craiyon are a little rough around the edges for now, but it’s not difficult to see how we could eventually use this technology to generate highly realistic images from scratch using only a text prompt. For faster responses and no ads, you can pay from $5 a month for a paid plan.
Even Stranger Things
- No graphic design experience needed
- One of the quickest ways to experience AI
- Only really has one trick
Even Stranger Things is worth a look even if you’re not a fan of the Netflix show that inspired it. The platform lets you submit a photo of anything you like and turns it into a Stranger Things-style poster.
The site was built by creative technologist David Arcus, and it taps into the Google Cloud Vision API, a machine learning system trained to recognize images based on a vast database. So by processing thousands of pictures of dogs, for example, the AI learns to more accurately spot a dog in other photos.
Even Stranger Things will try to identify what’s in the picture you’ve submitted and incorporate it into the finished design, usually with broadly accurate results.
It’s quite a simple AI tool, but it shows how we can use databases to teach machines to spot new patterns that aren’t in their training materials. The platform is also a great example of how algorithms can apply a particular visual style to photos to create something new.
Talk To Books
- Good for existential questions
- Very simple to use
- Offers multiple answers
- Prompts need to be carefully worded
Talk To Books is yet another artificial intelligence tool created by engineers at Google. In this case, the platform uses the words from more than 100,000 books to automatically respond to a question or text prompt.
While you can’t really hold a conversation with the site, you can ask questions like “How can I fall asleep?” and “How did you meet your partner?” to get answers that generally make sense. Type your prompt, then press Go to see the results, and you can filter by literary genre if needed.
This is another example of how machine learning enables AI to predict a good response to a question or prompt by analyzing patterns in text. It’s perhaps a glimpse into how free AI software could change web searches in the future.
- Fast results
- Offers helpful tips along the way
- Ability to use random prompts
- Limited number of image styles
As the name suggests, Pix2Pix is an AI image generator that takes one picture and turns it into another. In this case, the tool shows you a photograph based on something you’ve doodled.
Scroll down the page and you’ll see there are four different examples to try out: cats, buildings, shoes, and handbags. Sketch out your drawing in the window on the left, and click Process to see what the AI makes of it.
This is another engine based on a GAN, where two neural networks work in tandem to produce realistic results, and even figure out where the edges of objects in images should be.
Turning sketches into realistic photos can be useful in all kinds of areas, from building construction to video game design. And the quality of the results is only likely to improve as these neural networks get smarter.
- Sounds natural
- Will chat about almost any topic
- Responds to feedback
- Not always accurate
- Requires you to create an account
ChatGPT has attracted plenty of attention for the way it can generate natural-sounding text on just about any kind of topic, and it feels like a watershed moment in artificial intelligence.
This is what’s called a Large Language Model, which, as the name suggests, is trained on large volumes of sample text. Very, very, large, in fact. It’s then able to predict which words should go together and in which order, and it can improve its own algorithms as human beings rank its responses in terms of quality and appropriateness.
ChatGPT is somewhat like a sophisticated autocorrect engine, and you can try it out for free (though you’ll need to create an account and might find it’s unavailable at busy times). Test its knowledge on a topic you know a lot about, and feel free to offer feedback.
Deep Dream Generator
- Wide range of picture styles
- Can work with a base image
- Images can be refined
- Limited number of free generations
- Requires you to create an account
Fire up the Deep Dream Generator in your web browser, and you’ll be asked for a text prompt to create an image—it works like Craiyon in that respect, though you’ll get extra options in terms of image generation and refinement.
You can, for example, specify a particular style, such as photorealistic or fantasy. You can also add artists you want to mimic, or even digital camera models you’d like the AI engine to try to emulate. Another option is to supply your own base image for Deep Dream Generator to work with.
Underpinning Deep Dream Generator is a neural network trained on a huge database of images that the engine is trying to replicate, and it’s impressive in terms of the breadth and speed of the results that can be achieved. The platform requires users to spend “energy” to generate images, though, and the less you’re paying them, the fewer pictures you’ll be able to make at a time.
- Vast number of AI tools
- Simple interface
- You can train your own AI models
- The best features require payment
- You’ll need to create an account
Runway is an AI playground with a lot of different tools you can experiment with: create images from text prompts, create new images from existing images, erase parts of images, quickly remove backgrounds, generate a transcript from a video, and more.
For the text-to-image generator, for example, just type out a few words—such as “artistic painting of a solitary figure in an open meadow filled with flowers”—and Runway will go to work. You can choose from artistic styles, mediums (like chalk or ink), and even moods to refine a picture.
Other tools, like the one that colorizes black and white photos, require even fewer clicks. You can use Runway for free, but you’re limited in terms of export resolutions, storage space, and image generations—paid plans start at $15 a month.
It’s all based on advanced machine learning models that can recognize and repeat patterns. You can even use Runway to train your own AI models, making it suitable for advanced users: You might want to train it on photos of your face, for instance, and then generate endless portrait images of yourself in all kinds of styles and settings.
This story has been updated. It was originally published on June 23, 2022.