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

CONSISTENCY

 

From comics and books to films and storyboards, the ability to create consistent and recognizable characters is a crucial part of producing visual media. However, this can be a challenge when working with generative AI art. Due to the complex nature of AI models, the images generated by algorithms are inherently unique and they can vary greatly from one generation to the next. This can be beneficial for creating unique images, but it can be a problem when trying to maintain a consistent representation of a character across multiple different scenes and situations.

Uploading images of an existing subject as part of your prompt with the intention of replicating it may seem like an obvious approach, but it's not always guaranteed to deliver the desired outcome. Even with the use of a seed number, which few AI software solutions (excluding Midjourney) currently offer, the results are not guaranteed (seed numbers are designed for replicating the same image and not...