Have you ever had one ...
Have you ever had one of those moments – your mind is overflowing with images, you're desperate to draw them out, but the moment your hand touches the pen, what comes out is so embarrassing you can't even bear to look at it?
I have. And more often than I'd like.
A while ago, I wanted to create a cover image for my public account. I pictured a "cyberpunk kitten napping under neon lights" – lazy, trippy, with a futuristic vibe, damp neon streets outside the window, the kitten curled up next to an old air‑conditioning unit, its ears twitching slightly as if chasing fish in its dreams. Then I opened my drawing software, stared at it for ages, and what I produced looked like a glowing potato. Right then, I thought: am I just destined to be forever cut off from "visual expression"? I'm the kind of person who can turn a stick figure into a fracture patient, and you expect me to do design? Don't joke.
Then a friend who runs a self‑media account sent me a link, saying, "Try this – stop torturing us with your soul‑crushing masterpieces." The tone was full of disdain, but I honestly clicked on the link anyway.
I opened it –&nb...
I opened it – Wondershare MIAO – the name sounded like a studio run by some artsy romantic, all about "creating with love." But it turned out to be a serious AI painting platform, from Wondershare, already through quite a few iterations. To be honest, I signed up with the attitude of "let's see what AI can actually do," already mentally preparing some mocking lines like, "This is supposed to be art?"
Then I got schooled. Hard.
I typed in "cyberpunk kitten, neon lights, napping, futuristic city, rainy night," browsed the style section, picked one leaning towards "digital illustration," casually added a couple of weight keywords, and hit "Generate" – within ten seconds, an image appeared.
At that moment, I stared at the screen for three full seconds. The sheen of the kitten's fur, the reflection of neon lights on the wet ground, even the faint pink on the tip of its nose – everything was just right. It felt like you casually hummed an off‑key tune, and the other person immediately played back a fully arranged composition with harmonies. A person who can't even draw a proper circle just created a shareable, postable, even cover‑worthy image with a few lines of text.
Do you know what that ...
Do you know what that means? It means the wall between "I imagine" and "I present" has been torn down. That wall had stood in front of me for over twenty years, and finally, it collapsed.
Of course, there were also moments of epic failure – and I mean spectacular. For example, once I tried to generate a scene of "an ancient‑style swordsman practicing swordplay in a bamboo forest," carefully using keywords like "white robe, long hair, sword aura, bamboo grove, moonlight." What did the AI give me? An Ultraman in Hanfu, holding what was supposed to be a glowing stick – you could call it a sword, but it looked more like a cheerleading baton. The dissonance was like suddenly hearing heavy metal in a traditional tea house – and played on a suona, no less. Later I figured out that you need to be a bit more deliberate with your prompts – for example, use "!!" to emphasise key elements, or "((( )))" to give weight to certain keywords. The platform's "spell generator" has over 500 pre‑set tags, which is quite beginner‑friendly. In short, it's about learning to "speak human" to the AI, and the more specific you are, the better it understands.
Another thing that really reassured me – the copyright of the generated work belongs to you. That means you can use it for public account covers, e‑commerce images, PPT illustrations, or even commercial projects without any copyright worries. Haven't we seen enough cases of people being sued for using images grabbed from search engines? I've read more than one news story about a Taobao seller using a random image and ending up with a huge fine. Having a tool you can trust with confidence is better than anything else – at least you can sleep at night.
Let me share two little discoveries I made while playing around with it – consider them bonus surprises. The first is the "image‑to‑image" function – you can upload a sketch or photo and let the AI re‑create based on it. Once I uploaded a poorly composed street photo I had taken, and the AI turned it into a cyberpunk watercolour that instantly had "that work‑of‑art feel." The second is the "AI Combo" function, which generates multiple variants in different styles at once – like flipping through cards and picking your favourite. Every time, it feels like opening a mystery box, and more often than not, you won't be disappointed.
Now, you might be aski...
Now, you might be asking: does it cost money? Is it expensive?
Registered users get free daily credits – for light use, it's more than enough. I often just use those free credits to test whether a particular idea is worth exploring. If you need more, you can buy creation packs, which work out to about two cents per image at the lowest tier. I haven't calculated exactly, but the price of one cup of milk tea gets me dozens of images – no matter how you look at it, it's a good deal.
Finally, let me offer some honest advice, purely as a friend, not official guidance – if you're not a professional illustrator but often need images for social media, covers, inspiration, presentations, or even children's storybooks, or simply want to visualise your imagination, don't worry about your drawing skills – just dive in and try it. Start by using the ready‑made "quality prompt" templates to generate a few images and get a feel for it – those templates are tried‑and‑true combinations from others, essentially standing on the shoulders of giants. Then gradually learn to add weight, adjust parameters, and mix styles. The platform supports web, app, and mini‑program, so you can use it on both computer and phone. My own habit is to generate high‑res images on my computer and play around with smaller ideas on my phone – seamless switching.
The only thing I need to warn you about – don't get hooked late at night like I did, and end up watching the sunrise. I did that last week – I just wanted to "try a couple of images and go to bed," and before I knew it, the birds outside were chirping. I went to work with two big dark circles under my eyes, and when my colleague asked if I had been working overtime, I was too embarrassed to say I had been "painting all night" – and what's worse, it wasn't even me who painted them.
After all, imagination...
After all, imagination shouldn't be imprisoned by drawing skills. If you can't draw, it's not your brain's fault – it's just that you haven't found the right tool yet. You handle the big ideas, and leave the rest to the AI.
Don't overthink it – give it a try. You'll come back and thank me – or, you'll be staying up late with me.