Blog Prompt: Have a Chat in your Research GPT about creating an HTML5 (browser-based) game with a team of 3-4 students. Given your skills and interests in using AI tools, discuss what types or genres of game you would like to work on and what role you would like to play in its design/development. A text game, narrative game, exploratory game (world-building) or physics game (jumping, dodging shooting at obstacles).

In a blog post, share the type/genre, your role (coder, designer, writer) and a general description for a game you would like to collaborate on.

My group and I will be working on a physics game. I will personally be taking more of a designer role, however, in class I was taking more of the coding role. I would like to worry about the functionality of the game first before making it pretty. We would like to make a game that is a Pumpkin toss game that you need to make into a bucket under a certain amount of time. Sort of like the game angry birds, however, we are tossing the pumpkins instead of birds. It would be nice to have a pumpkin splatter, but that will be part of the later design if we can make it.

https://dtc-wsuv.org/mcasas22/world-website/

https://dtc-wsuv.org/zma23/future/index.html

this is my website.

1. When AI work is generated, how many revisions does it go through before a final design is chosen?
2. How much of human ideas are considered into a design?And are they even the first to be thought of? Or is is a joint collaboration with human ideas starting and using AI to generate them?
3. What happens when using AI to come up with ideas doesn’t work out?

In my group with Miryssa, Andrew, and Pamela, we are planning to do slingshot game with a pumpkin kind of inspired by Angry Birds. As of right now we are working on the technical stuff of the game and slowly adding the design elements. I have begun adding the visual elements to the game and will continue to do so so that it looks aesthetically pleasing.

https://dtc-wsuv.org/mcruz21/world-site.html

https://dtc-wsuv.org/idumbuya22/world/

This is my world-building website.

https://dtc-wsuv.org/hkuanoni24/synthetica/

During the process of creating an AI generated video, out of AI generated images, I experienced both frustration and enjoyment out of the whole process. I found it to be frustrating when trying to get the video to do what I wanted or needed it to do at times. For example, when trying to make figures walk, it would constantly morph and distort the figures, or turn them in the opposite direction, making the figures walk away. Some of the enjoyment came from when generating a video did something that was unexpected or was just overall visually pleasing. I also found it easy to have AI voice generation to be simpler than recording your own voice, as it is a one take process. Making the background music for the video was also fun as it is always interesting what AI music generators will spit out. Overall, the process of creating this video was new, fun and sometimes frustrating. It is something that I will try and delve more into in the future.

The type of game that we went with was a collision game with shooting mechanics and minimal player controls (left and right arrow keys to move the gun and spacebar to shoot.) It has a sci-fi theme and the objective is to shoot UFOs out of the sky, while avoiding airplanes. As expected, I have mostly worked on the artistic side of the game, writing prompts to generate pixel-art images and for the electronic background music track. Chat-GPT had minimal input on the type of game that I wanted to work on because I already had a general idea of what I’d like to do, but it has helped every step of the way in producing the resulting product.

https://dtc-wsuv.org/mrowland24/ecliptix-website/

In this article, I have learned a lot of knowledge about generative art, and there are many parts I am interested in. Amy Goodchild unfolds a broad spectrum of information, showcasing the multifaceted expressions of generative art. Whether it’s the interplay between randomness and rules or the fusion of art and technology, I have developed a great interest in generative art.

1. Randomness, in particular, strikes me as immensely enjoyable, offering a rich vein of creative inspiration. This process resembles brain development, where our subjective consciousness might be “misunderstood,” yet it operates within certain boundaries. It’s this balance between control and spontaneity in randomness that captivates me.
2. The concept of pseudorandomness is equally intriguing—utilizing an algorithm with “seeds” to generate outcomes. The capabilities of p5.js code, from drawing and animating to experimenting with randomness, were revelations to me. Discovering the pseudorandom number generator (prng) opened my eyes to blending control with unpredictability, letting artists navigate creativity amidst structured chaos. The idea that “When the algorithm is given the same seed, it produces the same results each time” is something I’m eager to explore further, hoping to verify Goodchild’s observations in practice.
3. True Randomness sounds interesting too, simulating a natural phenomenon (like rain falling on a window), and hopefully I can try this technique in the future.

I appreciate that she quotes many creative concepts and examples of artists, and vividly analyzes the connection between generative art, traditional art and reality. It’s very educational. For example, she mentions how the Proposal in Sol LeWitt’s Wall Drawing interacts with humans, as if the relationship between an artist and a computer algorithm is so similar. Another example is Studio Moniker’s project, which connects many interesting thoughts. The image of uncertainty in a computer program is like the interaction between people in a game, and at that moment I seemed to feel that the code is not cold, they can follow instructions like humans can ignore it. Goodchild’s Simulated Ecosystems are also interesting. Those elements simulate the phenomena of reproduction and extinction in the biological chain, and are presented in a way that breaks the grid, making the generative art more meaningful.

Amy Goodchild’s discussion on the relationship between generative art and abstract art is also interesting. Her exploration of generative art is not just about how technology creates art, but also explores the philosophy of art and how much control the artist has over the final work. Generative art blurs the boundaries between artist, tool and observer, so generative art is not just a set of code, behind it is also under the control of the artist and generated with the help of digital tools.

Interestingly, my first encounter with generative art was over a decade ago, though it was merely a fleeting moment then. At the time, I wasn’t aware that the images I admired were known as generative art. This semester, the term ‘Generative Art’ rekindled that dormant memory, offering me a long-awaited introduction to the concept. Thank you Will for sharing in the AI class.

My Video:

https://youtu.be/12tiLp4LQAY?si=5OI7GUGSa7oZdPSH

Compose a brief reflection to accompany your video (in the blog post), discussing your creative process, the challenges of maintaining consistency, and how you utilized AI tools to generate, refine, and audibly enhance your world and its narrative.

Imagery: Custom Chatgpt

Animation: RunwayML

Audio FX / Ambience / Vocal FX: Audiogen.co

Reese Bass / Some ambience: Me

This was a very challenging project that I ended up having to scale back on in order to reach completion.
Maintaining consistent imagery was a monumental task when trying to work with unique generations that adhered to a user chosen art style over “going with the flow” of whatever the AI generated.
Morphing and other inherent flaws of RunwayML prompted me to delve quite deep into the realm of generating unique content through AI.

Using a data-set of images generated using a custom GPT, I was soon able to slowly generate frames using RunwayML that provided smooth animation without morphing, however I was unable to get farther then basic arm movements and facial movement in the time I spent.

While I was unable to fully flesh out my idea, I feel like I am well on my way to understanding the basics of some of the advanced concepts used in some very impressive generations and am very keen to continue working on projects in my own time.

Many of the processes I found for completing high level projects involved running videos and images through several different AI-based programs in order to reach a profound level of control and manipulation of the content, instead of remaining at the whim of vague generations arbitrarily based on prompts.

Some interesting generations I found during the process:

Solid art style with basic animation, editing, and fx. Audio is great but would have been cool to see lipsync through Runway or Pikalabs.
https://youtu.be/EsbpCV0vWlM?si=mg504HDTEcsldGf9

Open Source AI animation is moving forward as well:
https://civitai.com/models/331718/bubbling-rings-or-animatediff-motion-lora

https://civitai.com/models/335070/simple-lcm-img2vid-workflow-or-comfyui

An amazing rendition of Zelda as a 1950s trailer:
https://www.youtube.com/watch?v=TNdvRHq8Hs8

Open Source AI datasets:
https://www.openml.org/

Example of how to build a dataset in order to generate unique content using Stable Diffusion.
https://www.youtube.com/watch?v=-qmnGSjvWII

In a blog post, share the type/genre, your role (coder, designer, writer) and a general description for a game you would like to collaborate on.

Type/Genre: RPG / Exploratory/Platformer

Preferred role: Designer / Coder

While I am open to any type of game to collaborate on, I think a simple RPG or platformer would be a great way to become familiar with the basics of a html/js browser-based game. An rpg gives opportunity to work with a variety of javascript functions including arrays and animations as well as providing ample room to incorporate AI into more dynamic storytelling and dialogue.

There are also a couple of extra elements that I think would help make this kind of project unique and easy.
A first thought involved adding responsive AI dialogue options through incorporating queries into a custom gpt that is linked to dialogue options via API-integration to focus on a unique experience for individual users.
I also would like to explore animation effects and other tools available through JS libraries available online such as https://phaser.io/

However at the end of the day, I am happy to work in whatever role and direction the group as a whole wants to move in.
Looking forward to seeing everyone’s projects and ideas reach fruition.

This is a link to my online exhibition for my world building website https://dtc-wsuv.org/dtc338-luers/vlam-world/

Overall I think that my website does a good job of providing information about the culture and society of my world. It mentions different aspects like the integration of AI, the beliefs, and even food. I tried to have a variety of images so that you could get a good sense for what this world is truly like, and introduce it with my video from visual 3. Everything is function but I added minimal JavaScript because I wanted to be able to grasp the concept but think the interaction works well. I think the design is where my website has the best execution I think it represents the style of Ethereal very well.

https://dtc-wsuv.org/pjauregui23/world/index.html