Media Arts and Technology

continue a previous post Segmentation Model: Original img: Screenshot 2024-12-03 at 13.07.12.png Segmentation img: image (56).png Generation prompts: A breathtaking fantasy landscape with a vibrant sunset sky filled with swirling nebula clouds and sparkling stars, a shimmering river with crystal-cl...

In this final project I delved into the image generation using Stable Diffusion 1.5 and ControlNet models. Stable Diffusion 1.5 known for its ability to generate detailed and coherent visuals based on prompts. ControlNet is a neural network structure that allows us to control diffusion models like S...

My analysis in this project focuses on fidelity, creative reinterpretation, and the balance between cultural memory preservation and modern influence. A scene featuring artifacts from the Terracotta Army, with soldiers, horses, and chariots partially unearthed and showing the wear of centuries, set ...

My goal is to analyze how midjourney reinterprets cultural memory by filtering historical and cultural artifacts through its training data, creating new images based on selective patterns and cultural references. Through its process of learning from digitized works, AI shows some certain cultural as...

an ancient temple in a forest --no trees midjourney seems to have difficulty generating images that match contradictory descriptions. If I use the word “forest” but emphasize that there are no trees, then the '--no' parameter is useless. Here it is not difficult to see that midjourney generates ima...

I would like to analyze midjourney's performance in generating realistic photo style images compared to abstract style images. I first tried to generate some Polaroid double exposure style photos to see if they matched real photography. Prompt1: a vintage Polaroid photo combining the silhouettes of ...

Concept: My concept is to analyze the impact of specific music festivals in Seattle (such as Capitol Hill Block Party, Bumbershoot, Belltown Bloom Festival, Beyond Wonderland Seattle, and Northwest Folklife), on the popularity of various music genres in the Seattle Public Library's collection. Whil...

My first concept aims to visually explore and interpret how deep learning models(such as AlexNet), understand and process image data. Utilizing activation layer outputs extracted from the model for various images, I plan to create a 3D visualization that demonstrates the journey of image features th...

Visualization Concept: My 3D space is structured around time-based data columns: the X-axis denotes the year, the Y-axis is the month, and the Z-axis is the day. Within this space, nodes symbolize the daily checkout numbers of various music genres over an eight-year span. My visual concept of the n...

Concept: My concept is to analyze the impact of specific music festivals in Seattle (such as Capitol Hill Block Party, Bumbershoot, Belltown Bloom Festival, Beyond Wonderland Seattle and Northwest Folklife), on the popularity of various music genres in the Seattle Public Library's collection. While...