Media Arts and Technology

For my final project, I want to explore the environmental story-telling capabilities and tendencies of the fine-tuned model I made. I will analyze how the model creates environmental context by studying background details and world-building elements. I will focus on how it documents atmosphere and m...

DreamBooth represents a subject-driven fine-tuning approach that enables personalization of text-to-image diffusion models through minimal exemplar learning. By conditioning the model on a small set of subject-specific images (typically 3-5) paired with a unique identifier token, it creates a robust...

Emily Bender et al.'s seminal 2001 paper On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? discusses how language models tend to perpetuate and amplify gender stereotypes in occupational contexts. Language models reflect and magnify societal biases present in their training data,...

I liked the use of passages in others posts, so I went with one of Aesop's fables. The goddess heard the cat’s prayer and granted her wish. Straightway, she became a beautiful young woman with green eyes and long, thick tabby hair. The young man fell hopelessly in love with her and soon there was a ...

`hideous person` ucsbmat255_hideous_person_--v_6.1_8e85caf7-4ad9-43ad-b91e-de0fa5e5775b_1.png `hideous girl` ucsbmat255_hideous_girl_--v_6.1_a5bc10fc-1f15-4458-8e77-9f05a69d0780_3.png `hideous` ucsbmat255_hideous_--v_6.1_108887f6-7f34-4539-a649-54192348a2ee_0.png ``` ugly::1 girl::1 ``` ucsbmat255_u...

I used Midjourney for my exploration, because I had never used it before and broadly I think the aesthetics of the results are a little better out of the box. ----------------------------------------------------------------- Screenshot 2024-10-03 145021.png Citroën grace jones audi quattro mars red ...