Book Image

Generative AI Art

By : Oliver Theobald
Book Image

Generative AI Art

By: Oliver Theobald

Overview of this book

The course introduces the basic concepts of artificial intelligence and its application in art, making it accessible even to those without a technical background. This foundation paves the way for exploring the nuances of effective prompt crafting, a critical skill for generating bespoke AI artwork. The course focuses on hands-on demonstrations with leading AI art software, including Craiyon and Midjourney, offering step-by-step guides to harness these tools effectively. Through practical examples, learners will understand how to navigate image prompts, masking techniques, framing, and lighting to enhance the visual appeal of their creations. The significance of navigating these elements is underscored, highlighting their role in achieving consistency and originality in AI-generated art. The course wraps up by delving into the remixing of popular art styles, the art of creating compelling text prompts, and the critical aspects of image rights, ethics, privacy, and originality in the digital art space. By concluding with recommended resources, learners are equipped to continue their journey in AI art, fueled by inspiration and a solid understanding of the field's possibilities and responsibilities.
Table of Contents (17 chapters)
Free Chapter
1
INTRODUCTION
2
A GENTLE INTRODUCTION TO AI
3
THE ART OF THE PROMPT
4
AI ART SOFTWARE
5
CRAIYON DEMONSTRATION
6
MIDJOURNEY DEMONSTRATION
7
AI-GENERATED PROMPTS
8
IMAGE PROMPTS & MASKING
9
FRAMING & LIGHTING
10
PARAMETERS
11
CONSISTENCY
12
REMIXING POPULAR STYLES OF ART
13
USEFUL TEXT PROMPTS
14
IMAGE RIGHTS
15
ETHICS, PRIVACY & ORIGINALITY
16
CONCLUSION
17
RECOMMENDED RESOURCES

ETHICS, PRIVACY & ORIGINALITY

 

As a new technology, we are still grappling to understand the extent and nature of bias and privacy risks associated with text-to-image models. While we know the capabilities of these models are impressive, it's important to recognize that they could be magnifying and mirroring societal biases on a global scale. With AI art models trained on private datasets or data crawled from the Internet, there's a possibility that they could produce images embodying or purporting harmful stereotypes.

As an example, the project thispersondoesnotexist.com, which generates a hyper-realistic portrait of a person who never existed, has been widely criticized for failing to generate people with black skin color, which alludes to issues with the training data used to create the model. (It’s worth noting that the project was spun up as an online stunt and demonstration to build awareness regarding the powerful capabilities of AI rather than as...