Final Project & Essay Description

Tommy O

My final project will be a visual narrative that leverages Generative Age technologies in its creation process. The current constraints include creating successive images that are cohesive. Three example strategies to work with this constraint are 1) maintaining overall style through detailed prompting/settings while crafting a narrative that does not rely on strict duplication of assets (like the same faces repeated throughout the work) and focusing on shot progression through other means, this is what I have termed a style based approach, 2) Incorporating the unexpected or errant output into the aesthetic of the narrative, embracing its randomness as a playful surreal element that is a tool-mark of Generative AI at this time, and 3) exploring the level of output constraint possible in achieving specific results. At this time consumer tools do not achieve the goal of example 3, but I expect rapid change iteration in generative tools will allow it in the near future for casual consumers at what will probably be a low cost.

At this time the essay is focused on generative tools for the creation of art in general and visual narrative in specific. I intend to include anecdotes about my exploration of various tools, which will include themes like the three example approaches to story cohesion in the previous paragraph. I will also approach other topics like the rapid development of tool features related to specificity and reproducible accuracy in what I hope will be as free of bias as possible. I intend to offer a report of experience rather than a value judgement on potential use/misuse.

When we first started thinking about final projects at the beginning of the year the first thing I thought about was making comics based off of lyrics from songs. I have already experimented with this idea and have gotten mixed results. I still want to continue down this path with different songs and different art styles.

If that does not work out, I want to try to make a music videos based on based on a song. I saw that Empire of the Sun released a music video that looks like it was generated by Ai. Maybe I would try something similar.

Here is a link to that song.

For my project, I want to bring together elements that we’ve worked on throughout the semester. I definitely want to include video, images, and music. I’ve struggled with getting some precise results from AI, and may want to focus on how to get better and better at prompting as part of my project.

I may want to make a music video. I haven’t pushed the boundaries enough on music and video, and would like to explore those channels more.

My essay will probably follow that same sort of guiding light, focusing on how AI music and videos are getting better and how to use them more efficiently in a workflow.

Nature’s Fury

I worked with Joeseph and Vincent for this project.

I contributed the tower designs and the map!

In the evolving landscape of digital media, artificial intelligence (AI) has emerged as a pivotal tool for creating dynamic and compelling content, particularly in the realm of video generation. My final project and accompanying essay aim to explore the intricate relationship between AI, art, and imagination, highlighting how these elements synergize to craft visually stunning narratives. The essay will delve into the mechanisms of AI video generation, underscoring the importance of artistic creativity and imaginative vision in pushing the boundaries of what AI can achieve. By examining cutting-edge techniques and the role of human creativity in guiding AI, the essay seeks to shed light on the future possibilities of digital storytelling.

For the practical component, my final project will be an innovative video that brings to life forgotten or fading memories through AI-generated images. These images will transition into moving visuals, creating a fluid, dream-like montage that captures the essence of nostalgia and the ephemeral nature of memory. This project will not only serve as a technical demonstration of AI’s capabilities in animating still images but also as an artistic exploration of how technology can evoke deep emotional responses. By focusing on personal memories, ranging from the profoundly nostalgic to the seemingly mundane, the video aims to resonate with viewers on a universal level, reminding them of their own forgotten moments.

The combination of theoretical insights and practical application in this project will contribute to a deeper understanding of the symbiotic relationship between AI and human creativity. It will demonstrate how art and imagination are not just supplementary to technological advancement but are fundamental in shaping the future of video generation and storytelling.

Here is my group’s slingshot game called Pumpkin Toss!

Are AI image-generation tools like Dall-E and Midjourney truly all-powerful and a threat to the livelihoods of trained artists?

In my experience, the tools themselves are somewhat repetitive and “dumb” with their generations unless you know how to work with them and create prompts that they can understand and emulate. This means that it isn’t as big of a threat to trained artists as I previously believed, but that doesn’t completely diminish artists’ fears. I will show examples of a bad prompt and its result vs. a good prompt. I’d also like to show an example of how AI can completely rip off a specific artist’s style to show how it can be threatening. Talking about how I had a hard time (and still do) speaking the AI tools’ languages will provide context to my experiences. It’s hard for me to make prompts with my existing, non-AI-related vocabulary. (The tools cannot always understand and produce work properly to the standards and quality of my vision.)

For the essay, I want to textually explain the creative question and my answer based on my experience with these tools and the class overall. For the final project, I’d like to heavily focus on how the quality of prompts is the difference between AI art generation tools being a threat to trained artists or not. I will give many examples, show how prompts evolve over time, and keep track of just how long (time-wise) it can take for an amateur like myself to generate the images that they envision. It might be cool to find an example online of an “expert” in these two tools and how their processes differ and how that affects the quality of their results as a comparison (if I’m allowed to do so, it will be properly cited and attributed, of course).  I’d like to present the final project as an edited video with my creative process narrated with the help of ElevenLabs. It will include photo generations, text prompts, and anything else that I think would be helpful to showcase the answer to my creative question.

My final project will be a graphic novel which tells a story occurring in my own unique world. I have gotten really interested in using the generative storytelling and image creation together, to create a highly detailed and visual representation of my ideas. In a side project, which was inspired by this class, I began recreating a world and story from my childhood. Bringing a character and story back to life, based off my childhood imagination, is something I never thought I would get a chance to do, and its been really exciting. The biggest challenge I will face during this project is keeping all the content under a similar theme and style, which takes me to my research essay.

For my paper, I want to dive into how you can express a consistent theme. Ai seems to have the most trouble with keeping things consistent, unless it is given an extremely strict guideline to follow. I want to see how far I can stretch one consistent theme, and to figure out the best methods for maintaining consistency. This isn’t only for images either. I would like to explore the best ways to maintain consistent themes across multiple content types, as well as how to keep consistency when using multiple methods simultaneously.

I want my final project to focus on investigating various avenues of generative art. This is a part of the class that has captivated me, and I can relate it to my degree more closely. I want to try to attempt some sort of visualization using a real data set. I want to see if I can use some form of an analytical tool to process a data set to generate an interesting artwork. I haven’t figured out the data set or the medium in which I am going to display it yet.

My essay will revolve around a similar topic. I am interested in doing an investigation on the value of this type of art, and perhaps a comparison of different techniques, including the physical ones. In addition, I would love to explore how AI generative art can aid in data visualization.

https://dtc-wsuv.org/hgebhart23/interstellar-intruders/

Here is the game I created with Haili Kuanoni and Mercedes Rowland.

Since there may be some truth to most companies using AI, I may have to utilize AI if I want my business to survive in this problematic economic model we are forced to live under. If I had to use AI, I would use it for game design. That seems to be one of the least harmful ways of utilizing AI. I have picked up game design again by learning Unreal Engine 5 recently and after learning I can code in HTML5 using Chat GPT, I have realized it can do C## too! This will help me get farther in my gaming aspirations quickly. It will be less vital for me to hire other people and instead be able to have more agency and power over my projects without being forced to hire people I may not be able to afford. I would use AI to be able to code for me and then once I complete a project, I would get attention using Kickstarter. I don’t plan on publishing on console so I will go to Steam and pay a $100 fee to publish on their distribution platform.

I can use AI to make text outlines acting as plan so that it can provide me with a clearer picture of how I plan to pursue this project. I need an outline so I can focus on what I will need to complete. If I have any questions, Chat GPT will come to me like it would a person but be able to answer most questions I would need to ask to fulfill my projects.

If my business got hired to specialize in remakes, that is one way I can stand out. I am very passionate about bringing games back using modern technology. There are games like Half-Life, Resident Evil and Halo that got remasters or remakes because they are timeless classics. For better or for worse, I can take advantage of the love certain old games have and refresh it. Not by changing it but expanding it by adding more skins, weapons, maps and/or game modes. I would also have an option to toggle the new stuff off. Freedom of choice will bring in new and old players that satisfy as many people as possible without turning anyone off from feeling the game being too generic. Player configuration is part of what will make my business unique. Since my business will likely stay small, I will not require the games to be sold at the standard $60 but more likely $5-10 and take advantage of steam sales.

1. What stage of development does your company use AI the most?
2. In your opinion, how important will AI be in the development of art as a whole?
3. Where do you draw the line for what is an acceptable amount of AI used in any given project?

Team Members:

• Midori Davis – Visual and Concept Designer
• Manuel Sanches – Coder, Designer/Developer
• Amy Bennett – Coder, Designer/Developer

Game Type:  Puzzle

Genre: Mystery/Survival

Game Overview:

The game opens on a hallway with four doors facing the player. Each door will open once clicked, however, items must be collected from rooms in the proper order to advance. Collected items appear in the Inventory Panel.

The setting is an abandoned hotel with peeling wallpaper and ominous decay throughout. The player is trapped and must figure out how to escape. 

The first hotel room contains a crumpled note among a few useless clickable items, which informs the player the objective is to escape. 

Next, the player must enter the bathroom to find a hidden key. Once the key is obtained, the player exits the hallway and finds the room with the locked tool box within.

In the third room, the player will use the key to unlock the tool box. Upon opening, a crow bar is obtained and placed into the Inventory. 

In the final room, the player must use the crowbar to smash the window and escape to freedom.

Alternatively, if the rusty knife is chosen, the player’s game is over and they must begin again.

1.How much training time is usually required to apply and learn new AI technologies

2.Whether AI technology is a great threat to your position, or whether the competition for jobs that overlap with AI technology will be relatively large.

3.How much productivity do you think AI has improved, and whether relying on these tools will lead to a reduction in your salary?

1. It seems like you don’t really explicitly mention AI and how you use it, except for on some specific product/project pages. Why is that?
2. How do you screen for people who have skills in using AI when hiring? Is there a skills test of some sort? How much of a priority is it to find people with skills in AI?
3. Have you had any clients who were very skeptical or against the use of AI, who then changed their mind after talking with your firm and how you use it?

Questions for guest speaker:

1. During hiring, does someone’s experience working with AI impact the hiring process?  
2. Can you give some examples of how AI is used in a company like Happy Finish?  
3. With the integration of AI into a company like Happy finish, has AI reduced the number of positions available in the company or has it helped open more positions?  
4.  AI is constantly evolving and as you are working with it, how do you think AI will impact this field industry in the future? How has it impacted your company?