Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: A little side project, a watercolor art generator

brushify.art

Post reply on HN
Print view View original

31–40 of 83 posts

Re: Show HN: A little side project, a watercolor art generator

#31

Post by tfsh »

The example looks cool, but I'm currently in an 11 hour queue :(

Any chance of porting this to the web using WASM? I've used ImageMagick in the browser before, I've never used Gimp, but if there's enough overlap you could use the former. That's of course assuming two things:

1) you have the time

2) you're happy to port the closed source, source code to the client

Both of which are perfectly fine to answer with a "no" :)

Also, I think it would be prudent to terminate the request if the client instance is destroyed. Right now I assume there's a bunch of requests being processed for users who have closed the tab.

Re: Show HN: A little side project, a watercolor art generator

#32

Post by synapticpaint »

It sounds like your app turns photos into a watercolor style image? You can definitely do this faster with Stable Diffusion (~6s per image before optimization).

Here's how I would approach it: train a dreambooth model on watercolor style images, then run image-to-image using that model.

For examples of what dreambooth models can do see: https://synapticpaint.com/dreambooth/info/ (sample images here generated using a "modern disney" style model).

If you need help getting this set up feel free to email me! This stuff is probably not harder than getting gimp to run in a container.

Re: Show HN: A little side project, a watercolor art generator

#33

Post by wongarsu »

synapticpaint wrote: post #32

It sounds like your app turns photos into a watercolor style image? You can definitely do this faster with Stable Diffusion (~6s per image before optimization). Here's how I would approach it: train a dreambooth model on watercolor style images, then run image-to-image using that model. For examples of what dreambooth models can do see: https://synapticpaint.com/dreambooth/info/ (sample images here generated using a…

Stable Diffusion on beefy hardware is faster than OPs process in OPs docker container, but I don't think we can judge from this that OP uses a slower process. For all we know this is running on the equivalent of a $10 Digital Ocean droplet.

Re: Show HN: A little side project, a watercolor art generator

#34

Post by hackmiester »

I'm going to go against the grain here. If this were my project I would try to spin up render machines dynamically in response to load. (Similarly to how gitlab CI runners can be spun up automatically, for instance.) There is no need to replace a working technology stack to make it faster. 1 minute is a reasonable wait time, and if your wait time goes over 5 minutes, then spin up some more workers.

Plus we have to be real and say, is the only reason the queue so long, because you let a bunch of nerds on HN add to the queue for free? I'm guessing the answer is, "probably." No need to engineer a fix for a problem that will typically not exist.

Re: Show HN: A little side project, a watercolor art generator

#35

Post by wishinghand »

nfriend wrote: post #16

Sorry all for the long wait times! Was not expecting much interest. At the very least, I need to look into removing photos from the queue when people exit the page.

How is the image processing being done? In broad strokes, what're you doing with the Python API?

Re: Show HN: A little side project, a watercolor art generator

#37

Post by rlv-dan »

synapticpaint wrote: post #32

It sounds like your app turns photos into a watercolor style image? You can definitely do this faster with Stable Diffusion (~6s per image before optimization). Here's how I would approach it: train a dreambooth model on watercolor style images, then run image-to-image using that model. For examples of what dreambooth models can do see: https://synapticpaint.com/dreambooth/info/ (sample images here generated using a…

This comment make me sad. Replacing human creativity with "ai" is like we've reached the peak so no need to put any effort into life anymore..
Post reply on HN