{"id":49,"date":"2025-11-15T17:05:50","date_gmt":"2025-11-16T00:05:50","guid":{"rendered":"https:\/\/blogs.ubc.ca\/mcafuta\/?page_id=49"},"modified":"2025-11-15T17:05:50","modified_gmt":"2025-11-16T00:05:50","slug":"task-11-text-to-image-using-sora","status":"publish","type":"page","link":"https:\/\/blogs.ubc.ca\/mcafuta\/task-11-text-to-image-using-sora\/","title":{"rendered":"Task 11: Text-to-Image Using Sora"},"content":{"rendered":"

For this activity, I used Sora<\/strong> to generate three images based on memories from Japan.<\/p>\n

Picture 1: <\/strong><\/p>\n

My first prompt described \u201ca realistic nighttime cityscape viewe<\/em>d from the 20th floor of a building in Umeda, Osaka, Japan, facing south at 10 p.m.\u201d\"\"<\/em><\/p>\n

The result felt surprisingly accurate and deeply nostalgic. My prompt wasn\u2019t very detailed, but Sora captured the atmosphere well. The glow of the city, the quiet hum below, and that reflective feeling of looking out over Osaka at night looked quite familiar.<\/p>\n

\n

Picture 2:<\/strong><\/p>\n

The second image, \u201can underwater view of a family of four snorkeling near the Blue Cave in Okinawa,\u201d<\/em> didn\u2019t turn out the way I imagined.<\/p>\n

\"\"<\/p>\n

It reminded me how specific I needed to be when describing what I wanted. The people looked a little strange, and the faces had that odd AI look. It also added things I hadn\u2019t pictured, like bright life jackets underwater. Wouldn’t they be floating? I realized that Sora wasn\u2019t really recreating my memory, but it was guessing what a \u201csnorkeling family\u201d might look like based on other examples. Next time, I\u2019d try adding more details to guide it better.<\/p>\n

\n

Picture 3:<\/strong><\/p>\n

My final prompt was \u201ca young Japanese woman riding her mamachari bicycle with a salmon-colored dog backpack, along a street lined with cherry blossoms and Osaka Castle in the distance. The dog is a long haired chihuahua and is poking its head out of the back.\u201d<\/em> This one came out beautifully.<\/p>\n

\"\"<\/p>\n

I spent more time crafting the description, learning from the earlier attempts, and the result closely matched my memory.<\/p>\n

\n

Reflection:<\/strong><\/p>\n

Overall, I noticed how the level of detail in my language directly shaped the quality of Sora\u2019s output. It almost felt like collaborating with memory itself…rebuilding moments that once existed, but now filtered through AI\u2019s imagination. It reminded me of Cathy O\u2019Neil\u2019s article \u201cJustice in the Age of Big Data,\u201d<\/em> where she describes how algorithms reflect and amplify the data they\u2019re given. Like predictive models that unintentionally learn human bias, Sora\u2019s interpretations depend on what I provide. In both cases, technology doesn\u2019t just process information, it mirrors our choices, our gaps, and sometimes, our misunderstandings.<\/p>\n

\n

References:<\/p>\n

O\u2019Neil, C. (2017, April 6).\u00a0Justice in the age of big dataLinks to an external site.<\/span><\/span><\/a><\/em>. TED. Retrieved August 12, 2022.<\/p>\n

OpenAI. (2025). Sora<\/em> [Generative AI text-to-video model]. https:\/\/openai.com\/sora<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

For this activity, I used Sora to generate three images based on memories from Japan. Picture 1: My first prompt described \u201ca realistic nighttime cityscape viewed from the 20th floor of a building in Umeda, Osaka, Japan, facing south at 10 p.m.\u201d The result felt surprisingly accurate and deeply nostalgic. My prompt wasn\u2019t very detailed, […]<\/p>\n","protected":false},"author":105884,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-49","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/pages\/49","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/users\/105884"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/comments?post=49"}],"version-history":[{"count":1,"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/pages\/49\/revisions"}],"predecessor-version":[{"id":53,"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/pages\/49\/revisions\/53"}],"wp:attachment":[{"href":"https:\/\/blogs.ubc.ca\/mcafuta\/wp-json\/wp\/v2\/media?parent=49"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}