I can totally see some fluid simulation folks publishing an upcoming SIGGRAPH paper about ketchup splattering.
I can totally see some fluid simulation folks publishing an upcoming SIGGRAPH paper about ketchup splattering 👹https://t.co/wZP9WeiY1t
— Li-Yi Wei (@liyiwei) November 25, 2022
Writing is an important skill for not only publishing and communication but also other career tasks. If you cannot do it for whatever reason (language, habit, psychology, etc.) it is better to learn as soon as possible.
Nobody else knows your ideas and thoughts better than yourself. Writing by someone else is not very likely to accurately reflect what you have in mind.
If you find it difficult to express your thoughts, it can be a sign that the thinking is not clear enough and writing can help refine it.
Do whatever to come up with a first draft. Do not worry about nitty gritty details like grammar as long as your collaborators can understand what you are trying to say. We can iterate the paper draft together to improve the not only the writing but also our thinking and execution of the project.
Sometimes I watch presentation videos in double speed to save time and heighten focus (more attention is needed to parse narrations playing in faster speed).
Recently I realized that I have not spent enough time for deep thinking and I can notice that my ideas started to suffer. Some of the causes were self-inflicted, such as letting myself distracted by meetings, slacks, or emails.
Regaining self-control is in order.
This is an experiment to generate images directly from texts from the little cookie girl.
Each prompt below is appended with “oil painting by Rembrandt”.
On a freezing New Year’s Eve, a happy young girl, warm and well clothed, huddles in the alley between two houses, trying to sell cookies, which she eats one by one, to keep herself occupied.
In the sweetness of the cookies she sees a series of comforting visions: the warm iron stove, the lovely roast goose, the great glorious Christmas tree. Each vision disappears as a cookie was eaten.
In munching the next cookie she sees her grandmother, the only person that also made cookies with her. To keep the vision of her grandmother alive as long as possible, the girl consumes the entire pack of cookies.
When the cookies are gone the girl is full to the throat, and she takes Uber to carry her home.
The next morning, the father finds the girl sleeping on her bed with a smile on her face, and expresses joy. He does not know about the wonderful visions she had seen, or how happy she is with all the cookies in her belly.
I experimented with stable diffusion over some of my own manual drawings and here are the results.
The technology has finally reached the point for which content can start to be authored via natural language and gesture (including drawing) instead of unnatural WIMP (windows, icons, menus, pointer).
The state of art (e.g., DALL-E-2) can already be part of the content creation toolbox, and future advances may soon obsolete legacy tools.
With the same subject title, I created multiple outcomes via manual drawing and DALL-E-2 with different styles hints.
digital art
natural illustration
oil painting by Rembrandt
manual painting with Fresco (took about an hour)
Recent language-based image generators can output amazing results given the right kind of input prompts (e.g., book and market), which can be tricky to produce and rely on experiences. This led me to predict the emergence of a cottage industry of “image prompt optimization” analogous to search engine optimization, and research of machine learning modules (e.g., another network) that can learn translating ordinary natural language inputs to language-generator prompts that can lead to desired outcomes.
Theme: Rubric. Get a free blog at WordPress.com