Taming AI 1: Jjamppong Prompt Experiment
Hello everyone 😊
After writing a post about prompt engineering, I glanced at my blog homepage and noticed something funny - so many posts about jjamppong (Korean-style spicy seafood noodle soup).
It has been cloudy and drizzling all day here, and suddenly that rich, spicy broth came to mind. 😋
So for the first episode of Taming AI, I decided to ask AI to make an image of jjamppong.
Let us see how much the results change depending on the prompt.
Question 1: “Make an image of jjamppong.”
The AI starts spinning its little thinking wheel.
🧠💭
Ta-da!
Here it is - the most basic form of jjamppong: red broth, seafood, noodles.
Exactly what I had in mind. Nothing fancy, but still amazing to see AI recognize and visualize the concept of jjamppong.
Question 2: “Make an image of delicious jjamppong.”
And again, it starts thinking. About a minute later -
🍜✨
Now this is different!
The photo looks brighter, a pair of chopsticks appeared, and the whole image has more depth. The food shines with a glossy texture that really makes it look appetizing.
One simple word - delicious - made all that difference.
Question 3: “Generate an image of delicious jjamppong with noodles being lifted, showing realistic steam.”
Back to processing mode again - about 1 to 2 minutes per image.
This time, I gave a more detailed prompt - describing an action and a texture at the same time.
The result? Pretty close. I tried adjusting the height of the lifted noodles in new prompts, but most results looked similar.
It seems AI still struggles with concepts like motion or the passage of time.
I turned the generated images into a short GIF - and at first glance, it really looks like a steaming bowl of jjamppong.
Question 4: “Create an out of focus image of delicious jjamppong in a Chinese restaurant background.”
This time, I added a setting and an out of focus condition.
After about a minute -
🎉 Ta-da!
Now it is much more vivid - dim lighting, Chinese-style decor, tableware barely visible in the background.
Apparently, AI does not just learn taste but also atmosphere.
Question 5: “Create an image of delicious jjamppong with noodles being lifted, set in a Chinese restaurant background.”
Now we are combining everything: the background, the lifted noodles, and the steaming detail.
I tried asking the AI to adjust the noodle height several times. Instead of changing the height, it simply reduced the amount of noodles… 😅
Still, the results definitely looked more realistic and detailed than before - though you cannot quite shake the uncanny feeling when comparing them to a real photo.
Interestingly, one of the later images had a completely different restaurant in the background. Apparently, the AI is not perfectly consistent when regenerating similar prompts.
Here is the final animated GIF - our ultimate jjamppong creation. 🍜🔥
Prompt Engineering Is the Art of Talking to AI
This little experiment reminded me once again: AI does not draw what you say, it draws what it understands.
The clearer and more logical your prompt, the better the result. That is the essence of Prompt Engineering.
AI reacts sensitively to every single word and sentence structure, so to get what you truly want, you must first learn how to express your thoughts precisely in human language.
💡 Before you tell AI what to do, imagine it yourself first. Imagination is where every prompt begins.
☂️ Final conclusion:
Today’s lunch? Definitely real jjamppong.
Thanks for reading - and as always, stay happy. 😊
You can view the original blog post in Korean at the links below: