Interesting note, I am using chat gpt to generate amazing images of the mnemonic descriptions. I did have to upgrade to the paid chat gpt version.
5 Likes
Interesting 
I tried the free DALL-E plan and didn’t really get much of anything out of it.
Is the paid version that much better at generation?
I think that was an earlier version but this is much better than when it first came out
1 Like
I am experimenting a bit and built a google sheet to generate promts for the story of characters that in a style I want. I define what the scenes and locations look like.
Shi1: teacher:
ke4: lesson
mang4: busy
I use sora for the image generation, and free gemini API to optimize my prompt. For example promts for those images were:
"Highly detailed fantasy illustration in the style of an illuminated manuscript or vintage storybook. Keywords: parchment texture, textured like ancient parchment, hand-inked linework, fantasy mood, storybook illustration.
Scene: An old, two-story house with a well-kept lawn and a sidewalk in front. Shrek, acting as a 师 teacher, sits on a 巾 towel spread out on the lawn. A group of neighborhood children surrounds him, watching intently as he waves a 刂 saber, giving a lesson on how to become an ugly ogre. The children, mimicking their 师 teacher, gleefully cover themselves with mud and brandish their own toy 刂 sabers."
"Highly detailed fantasy illustration in the style of a illuminated manuscript or vintage storybook. Keywords: parchment texture, textured like ancient parchment, hand-inked linework, fantasy mood, storybook illustration.
Scene: Inside the bathroom of a surreal electricity plant, Kermit the Frog, dressed as an electric repairman, is surrounded by bizarre fruit-shaped speakers hanging from the ceiling's electricity lines. The bathroom has a bare floor, and beyond the open door, fire-powered generators line the walls. The fruit-speakers are animated, their word bubbles bombarding Kermit as they deliver an unusual history lesson about electric fruit."
5 Likes
Wow, I’m surprised at the amount of fidelity! Do you find it more helpful or less helpful when it comes to remembering the character?
what do you do / plan on doing with those images?
I dont know if this will work, maybe its missing the point of memonics. Memonics being personal stories linked to personal spaces. But since HH does not have personal stories or spaces perhaps it fits. I feel I have a hard time being consistent with my pictures in my head and I often forget a lot of details. E.g I find it very hard to differentiate bathrooms in various different rooms. They all blend together for me.
But yes quite neat!
xue2 (study)
dong4 (move)
bang1 (to help)
leng3 (cold)
zhan4 (fortune)
etc…
1 Like
i think visual aid like this would work amazingly well, the question is where to store it, add it somehow to HH?
just opened this question here yesterday. Right now i just store the image link in the notes. I do download the images too, thinking to upload it to Google Drive and the link it there.
Personally, I’d rather not see AI art used on this site for various reasons and I’m sure many others will agree with me.
This has nothing to do with you or the website its a personal work flow being discussed here . Notes are personal and non mandatory you can always continue to use it the way you want. I agree something this experimental without proof of function should not be the defacto way.
My bad, I misunderstood what you said. But yes, this should not be the defacto way.
Excellent use of Chat gpt! I wish I had thought of it as well!it would have saved me a lot of time while creating my own mnemonic images for the last few months!! Too much time consuming! Interestingly enough, after 3 months away from hanzi, my recall process was very bad, with the exception of the few hanzi whose images I created from scratch. (By the way, I included the Hanzi characters in those images, as well as the radicals in the form of labels for props included in the image. I think that is what is missing in your images. It may help to better relate the image to the hanzi).
So, do I understand correctly that only the paid version of chat Gpt can create the images?
Free version can also create images but limited to 5 per day
You can also ask it to create in a four panel comic to have four hanzi mnemonic in one image
1 Like
Yeah its pretty limited. So far i like sora the most, gives about 4 *3 images a day. But can also generated them in copilot but it sometimes complains about copyright related to disney and nitendo figures. In GPT it self it seems quite flexible too. For generating a prompt I build a google sheet who is optimizing the prompt with Gemini API.
1 Like