.

Understanding AI art.

What is AI art?

Three eiffel towers in desert with river; photorealism

Prompt: Three eiffel towers in desert with river; photorealism

How does AI generate art?

pink fir tree
Tree with pink flowers
Prompt: (left) pink fir tree; (right) tree blooming with tropical flowers

Generative AI in the art world.

beautiful gallery oil painting, red, jade, orange and grey, sharp lines and blended tones

Prompt: a beautiful gallery oil painting, red, jade, orange and grey, sharp lines and blended tones

Get inspired by a few examples that showcase what you can create with generative AI art in Firefly.

  • Abstract and experimental art showing expressive shapes and textures.
  • Photorealistic visuals for realistic scenes, products and concepts.
  • Fantasy characters and environments created from descriptive prompts.
  • Design patterns and motifs useful for graphic and textile projects.
  • Style variations that transform the same idea into different artistic looks.

What technology is used to create AI-generated art?

Just like there are many tools in an artist’s physical toolbox — paints, pencils, inks — mulitple kinds of technology contribute to making AI artwork. We’ve already discussed large language models and diffusion models. Here are a few more technologies used in AI art generation.

Generative AI models

Generative adversarial networks (GANs): GANs are a set of two neural networks, trained on the same data, that work together. One generates a photorealistic image and the other tries to figure out if that image is real or created. For instance, the first may generate an image of a horse and the second would try to determine if the image was a photograph or digitally created. This helps the system make more realistic images. GANs are often used in experiments where highly realistic AI-generated artwork is required.

Variational autoencoders (VAEs): A variational autoencoder is made up of two neural networks working in tandem, each with a different job. One is an encoder, which takes in information and the other is a decoder, which is able to reinterpret that information into all new content. Like GANs, they produce photorealistic images. VAEs are useful for tasks that involve reconstructing or transforming images in creative ways.

Generative AI techniques

Image synthesis: Image synthesis describes the act of creating new images from large datasets of other images. This technique is central to how generative AI art is produced, allowing systems to blend patterns, styles and features into new visual results.

Creative coding: Artists who create the programmes that generate their artwork are described as creative coders. The intent of creative coding is not to produce a functional result, but an expressive one. This approach shows another side of AI in art where human programming choices drive creative outcomes.

Firefly generated infinite intricacy fractal pattern, hyper-realistic, science_fiction, 4k

Prompt: infinite intricacy fractal pattern, hyper-realistic, science_fiction, 4k

Unlock your creativity with Adobe Firefly and AI-generated art.

Questions about AI art? We have answers.

Dream Bigger with Adobe Firefly.

Imagine, experiment and create with generative AI in the Firefly web app. New to Creative Cloud, now available for commercial use.