This case study investigates if the AI text-to-image generator Midjourney can generate visual game character idea images for Dota 2 that meet the game’s art guidelines. The author defined the term “visual game character ideas” as the idea images at the early stage of visual character design process to help artists get inspiration. To achieve this, an experiment was designed and conducted where three new Dota 2 heroes’ backgrounds were developed by the author, and 32 images per hero were generated with Midjourney bot. These 96 images were evaluated to examine Midjourney’s performance based on seven aspects: accurate content, readability and identifiability, value gradient, value patterning, the number of colors, areas of rest and detail, and directionality. “YES” was given to each criterion if they meet the requirement. The value of this case study is to present the strength and weakness of the text-to-image generators for visual character design ideas, which can potentially show game artists when and how to use them in visual character design process. The result suggested that Midjourney could be used to generate visual character design ideas for Dota 2 unstably, and this instability was mainly caused by its identified flaw: content accuracy. Furthermore, it performed better for non-color-related aspects, while the performance for color-related items was significantly worse than others.

This project explores the role of GANs (Generative Adversarial Networks) in the process of art creation with a focus on traditional art and craft of Saudi Arabia. It introduces a concept for participatory museum experience where visitors are able to interact with an Artificial Intelligence (AI)  generative tool to create their own piece of traditional Saudi Arabia art.  This study investigates different types of GANs models that can be used to make the traditional art creation more accessible and attractive to the younger generation by introducing the possibilities of emerging technology. At the same time, it analyzes potential limitations and concerns that such fast developing technology carries. Within the big scope of this project including technology research, cultural studies regarding Saudi Arabia art and craft, training AI models and iterative prototyping, the research focuses on looking at the AI-powered services through the lenses of User Experience (UX). UX studies and corresponding methodologies from the field are used to explore the quality of the interactions between the user (visitor) and the AI system. Based on the performed design process, the outcome proposes a screen based image generation tool which utilizes a visual programming approach to interface by visualizing the generation path along with the data flow and allowing the user to connect generated images in order to create new content. Presented solution introduces an alternative approach to the design of image generators where users can follow the creation path from the first prompt to the final image.

Data augmentation is a technique that acquires more training data by augmenting available samples, where the training data is used to fit model parameters. Data augmentation is utilized due to a shortage of training data in certain domains and to reduce overfitting. Augmenting a training dataset for image classification with a Generative Adversarial Network (GAN) has been shown to increase classification accuracy. This report investigates if transfer learning within a GAN can further increase classification accuracy when utilizing the augmented training dataset. The method section describes a specific GAN architecture for the experiments that includes a label condition. When using transfer learning within the specific GAN architecture, a statistical analysis shows a statistically significant increase in classification accuracy for a classification problem with the EMNIST dataset, which consists of images of handwritten alphanumeric characters. In the discussion section, the authors analyze the results and motivates other use cases for the proposed GAN architecture. / Datautökning är en metod som skapar mer träningsdata genom att utöka befintlig träningsdata, där träningsdatan används för att anpassa modellers parametrar. Datautökning används på grund av en brist på träningsdata inom vissa områden samt för att minska overfitting. Att utöka ett träningsdataset för att genomföra bildklassificering med ett generativt adversarialt nätverk (GAN) har visats kunna öka precisionen av klassificering av bilder. Denna rapport undersöker om transferlärande inom en GAN kan vidare öka klassificeringsprecisionen när ett utökat träningsdataset används. Metoden beskriver en specific GANarkitektur som innehåller ett etikettvillkor. När transferlärande används inom den utvalda GAN-arkitekturen visar en statistisk analys en statistiskt säkerställd ökning av klassificeringsprecisionen för ett klassificeringsproblem med EMNIST datasetet, som innehåller bilder på handskrivna bokstäver och siffror. I diskussionen diskuteras orsakerna bakom resultaten och fler användningsområden nämns.

Tools using artificial intelligence are being developed at a rapid pace. One of these tools is the text-to-image generator DALL·E 2 which has been developed by OPEN-AI and is meant to generate images solely through text input. One of the problems with tools like these is that they are not as good at generating material as AI generators for speech or text are. As DALL·E 2 has been made available to be used for commercial purposes there is a need to evaluate whether the tool is good enough to be used for that purpose. The study was conducted through 3 focus groups with a total of 15 participants. The participants were 20 to 25 years old. During the focus groups, already generated images were discussed and they were allowed to test use of the tool themselves. The theoretical framework Technology Acceptance Model 2(TAM-2) was used to analyze the qualitative data according to its already established determining factors. The result of the study presents area of usage as a new extending factor for the perceived usefulness when using TAM-2 in a qualitative study. The conclusion is drawn that visual material created by DALL·E is not seen as accepted for use in a commercial purpose but its application within certain areas of usage could raise the perceived usefulness, and thereby acceptance. / Verktyg som bygger på artificiell intelligens utvecklas i snabb takt. Ett av dessa verktyg är text-till-bild-generatorn DALL·E 2 som utvecklats av OPEN-AI och är menat att generera bilder utifrån text. Ett problem med verktyg som DALL-E 2 är att de inte är lika bra på att skapa visuellt material som generatorer är för ljud eller text. I och med att verktygen börjat göras tillgängliga kommersiellt så finns det ett behov att undersöka huruvida verktygen är tillräckligt bra för att kunna användas till det. Studien genomfördes med tre fokusgrupper med totalt 15 deltagare. Deltagarna hade en ålder mellan 20 och 25 och man diskuterade acceptans till tidigare genererat bildmaterial samt upplevelsen av att använda verktyget själva. Technology Acceptance Model 2 (TAM-2) användes som teoretiskt ramverk för analys av den kvalitativa datan och för påverkande faktorer. Resultatet presenterar sammanhang som en ny påverkande faktor för den uppfattade användbarheten i användningen av TAM-2 i kvalitativa studier. Slutsatsen dras att bildmaterial skapat av DALL·E 2 inte anses accepterat för användning i ett kommersiellt sammanhang men tillämpning i specifika sammanhang skulle kunna höja den uppfattade användbarheten och därmed acceptansen.