mishu2

Over the holidays I built a simple website which lets children (of all ages) easily draw something and then bring the sketch to life using AI and a prompt.

https://funsketch.kigun.org/

Only shared it via Show HN so far, and am still regularly getting some creative submissions. Will be sharing it at an art festival later this year so kids can have a more active role when visiting.

Thank you everyone for taking a look. The website had around 1,200 visitors and received over 90 sketches over the past 24 hours, and I'm happy to say I could approve almost all of them (all except 2 'rocket' sketches which were starting to look a bit dubious, but all in good fun).

The results look very interesting to me, and I think as a next step I will look into adjusting the prompts (both positive and negative). On the one hand, I'd like to keep the sketch/drawing look rather than going full photorealism as some of the videos do, on the other hand I don't want to restrict the users' creativity too much.

I plan to simplify this further and optimize it for tablets. Some friends said they'd like to have their kids try it out it and I like the idea, as by having to sketch it keeps the user in a more active role.

Please let me know if you have any other suggestions.

I'm actually trying to reduce the 'funkyness', initially the idea was to start from a child's sketch and bring it to life (so kids can safely use it as part of an exhibit at an art festival) :)

There's a world of possibilities though, I hadn't even thought of combining color channels.

I think the main reason is that the model has a lot of training material with Chinese text in it (I'm assuming, since the research group who released it is from China), but having the negative prompt in Chinese might also play a role.

What I've found interesting so far is that sometimes the image plays a big part in the final video, but other times it gets discarded almost immediately after the first few frames. It really depends on the prompt, so prompt engineering is (at least for this model) even more important than I expected. I'm now thinking of adding a 'system' positive prompt and appending the user prompt to it.

Once you set up a pipeline, sure. They'd need a lot of bandwidth to ensure the combined output makes any kind of sense, not unlike the GPU I guess.

Otherwise it's similar to the way nine women can make a baby in a month. :)

Thank you. I've noticed that too, and also that it has a tendency to introduce garbled text when not given a prompt (or a short one).

This is using the default parameters for the ComfyUI workflow (including a negative prompt written in Chinese), so there is a lot of room for adjustments.

Thank you. I'm running it locally on a 4090 (24 GB).

I was running into OOM issues with Wan 2.2 before, but I found the latest version of ComfyUI can now run it (using about 17 GB of VRAM for what I assume is a quantized model?).

Having the ability to do real-time video generation on a single workstation GPU is mind blowing.

I'm currently hosting a video generation website, also on a single GPU (with a queue), which is also something I didn't even think possible a few years ago (my show HN from earlier today, coincidentally: https://news.ycombinator.com/item?id=46388819). Interesting times.

Started working on a case discussion platform for students almost two years ago. Mostly for dentistry and medicine, but it's template-based so works well for other purposes (e.g. teachers, social workers, etc.). It's going well and is being used by three universities right now.

On the way, I developed lightweight image editor and 3D model viewer components, which I've open sourced [1].

[1]: https://github.com/kigun-org/

Started working on a case discussion platform for students around 18 months ago. Mostly for dentistry and medicine, but it's template-based so works well for other purposes (e.g. teachers, social workers, etc.). It's going well and is being used by three universities right now.

On the way, I developed lightweight image editor and 3D model viewer components, which I've open sourced [1].

[1]: https://github.com/kigun-org/

Author here, I forgot to mention the project is written using Svelte 5 and daisyUI, because I wanted to try the tech stack out.

I have to say I quite like it for more complex interactive components like this one, but still much prefer django with some htmx + Stimulus JS sprinkled in for the rest of the website.

Photography is a hobby of mine. After putting it off for years, I finally decided to start sharing my photo collection with friends and family.

This resulted in another side project, https://mishmash.photos/ -- a website to organize, share and collaborate on albums (because I always lose photos when going on trips with friends). There are better apps out there for this, but this one is mine.

Sample album: https://mishmash.photos/share/84f83b09-0a24-4d13-b436-8131ee...

Tech stack is django, htmx, bootstrap and a Stripe integration, to keep things simple.

(There's no free tier; from reading this website I know offering free image upload usually ends badly.)

Thank you for the feedback, that's a point that several commenters have brought up.

The problem with the interdental brushing video specifically is that we can't show how to use larger brushes on young healthy patients, as they don't have the spaces for it. But I will think about how we can improve that video (the comment above suggested moving it down in the page, to start with the 'gentler' videos).

I'm glad they were useful to you.

Thank you for the feedback, I'm glad you found them helpful!

I wanted the interdental cleaning part to come first, because it usually gets neglected and it's just as important as tooth brushing.

But I like your suggestion to change the order, as that would indeed give a gentler introduction.

I'm sorry to hear that. Like you correctly mention, genetics play a big role and are unfortunately (currently?) not modifiable, and there is plenty of evidence that a restored tooth is at higher risk of further issues/loss, so prevention is the best thing you can do.

Good job with your daughter! FYI, we are working on expanding the instructions to children, so watch this space ;)

> Dentists seem to be about 5-10 years behind the research on this topic.

Generalizations are usually not helpful, I think it really depends on the dentist. I'm not sure there are proven benefits to oral microbiome testing, except in some very specific cases.

> The most significant cause for caries is S. mutans.

The 'Beyond Streptococcus mutans' section in TFA explains that the situation is much more complex than this; even if it is, good oral hygiene and reduced sugar intake (both in quantity and frequency) are still the best way to reduce the amount of biofilm present on teeth (which is a requirement for caries formation, whether S. mutans is there or not).

> Diet is the most significant way to affect gum disease.

The current clinical treatment guidelines for periodontitis[1,2] only mention that the benefit of weight-reducing diet and lifestyle changes is unclear (for treating periodontitis, obviously), and that oral hygiene is still the most important thing you can do yourself for the prevention, and, once established, to assist in the treatment of the disease.

[1] Infographic: https://www.efp.org/fileadmin/uploads/efp/Photos/Continuing_...

[2] Source article: https://onlinelibrary.wiley.com/doi/10.1111/jcpe.13290

While there are indeed many factors (genetics, the specifics of the microbiome in your mouth, probably some we don't even understand at the moment) at play, oral hygiene (and diet for caries, but not gum disease) is currently considered by far the most important modifiable risk factor.

Thank you all very much for the feedback, it gives me a new perspective on things. We wanted to show a real case, rather than animations, because we thought it would be clearer for our patients; but we are probably desensitized to watching stuff like this. Would you prefer to see a 3D animation instead, or something else?

It may still take us some time to reach that goal, but the good news is that we have an effective solution available right now: keeping good oral hygiene is known to prevent both caries and gum disease, and takes less than 10 minutes a day for the average person.

If you need more information, we recently developed a free website to get you started: https://lifelongsmiles.hk/

Professionally, I recently founded a startup focusing on education in dentistry. I've developed a platform to discuss and interact with cases online which I use for my own teaching, and thought other might also be interested. I've made some of the custom components (image editor, 3D viewer) freely available: https://kigun.org/

Personally, I'm building a website which lets you quickly setup personal online dashboards, because I wanted to have an overview of all the sites I refresh often on one page: https://frankendash.com/

Playwright is basically necessary for scraping nowadays, as the browser needs to do a lot of work before the web page becomes useful/readable. I remember scraping with HTTrack back in high school and most of the sites kept working...

For my project (https://frankendash.com/), I also ran into issues with dynamically generated class names which change on every site update, so in the end I just went with saving a crop area from the website as an image and showing that.

Thank you for the comment, glad to hear it might be useful for you.

1. There's a bit more going on behind the scenes. The back-end opens the web page using Playwright (headless Chromium) and takes a screenshot. It's this image that gets displayed in the dashboard.

2. I also first thought about implementing most of the functionality client-side, using the user's browser to make requests, but like you suspect this quickly runs into CORS issues. Using the server to make requests avoids this, as it's a plain browser request and I then have full access to the rendered page.

3. It's being hosted on a remote server now; the back-end makes all the requests for you. Potential issues:

  - I'm not sure how much load the server will be under (although I suspect HN might help me test this out)
  - You can only use it for public web pages (e.g., nothing behind a login/paywall), as the user's cookies are not used
  - Where the server is may affect the responses you get (blacklists for cheaper VPS, more GDPR cookie banners if you're hosting in Europe, etc.)

I'd also like to join.

Using something like this, which I would personally make illegal: https://fingerprint.com/

I also tried setting privacy.resistFingerprinting = true in Firefox, but it's sad to see that most websites become unusable (most sites using canvas just render a green/purple mess), zooming in Google Maps is basically broken (skips several levels at a time), and like others have mentioned dark mode and time zones also stop working.

What a mess the (somewhat private) web is nowadays. The more I think about it, the more I am convinced legislating privacy is the only way out of this arms race we seem to be losing.

EDIT: Sorry, the parent post already included fingerprinting, missed that. Rant still stands though :)

I still use search but am concerned about the day when all results will just be SEO AI-generated garbage (for some searches that is already the case).

So I recently started https://cstdn.org/ and am sharing all good links I can find there. I created a Show HN but didn't make the front page, but anyone who wants to try it out is more than welcome to do so.