Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images • Hacker News Board

Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images

#81

Post by michaelt » Fri, Aug 11, 2023, 2:51 PM UTC

atentaten wrote: post #55

I have an app that needs to generate hundreds and eventually thousands of images. What tools can I use to generate these images at scale. After I figure that out, then I will be looking at Rubbrband for quality control.

If you've got an nvidia graphics card with 8GB of vram made in the last decade, AUTOMATIC1111's stable diffusion web ui [1] will crank out a few thousand images every 24 hours. Depending on settings and how fast your card is, naturally.

And there's a large ecosystem of downloadable models available online for specific looks and concepts, like models trained for photorealism.

[1] https://github.com/AUTOMATIC1111/stable-diffusion-webui

Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images

#82

Post by michaelt » Fri, Aug 11, 2023, 3:20 PM UTC

toddmorey wrote: post #21

Question: what’s a use case for generating so many images in a batch at scale?

The majority of AI art you see online is actually cherrypicked best results after someone tried 20 different seeds and prompts until they got something they really liked.

Far better UX if you can show a grid of 20 images, and let the user choose.

Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images

#83

Post by jrmylee » Fri, Aug 11, 2023, 7:37 PM UTC

alecbell wrote: post #46

This is a brilliant idea. Whenever I look at an image these days that has the "texture" of a generated image, I immediately start looking at certain features such as "more than 5 fingers" to determine whether it's real or not. If you could immediately detect those features and block the generated image from making it to production, that'd be a huge value gain.

appreciate it :)

Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images

#84

Post by RadiozRadioz » Sat, Aug 12, 2023, 4:06 PM UTC

abhinavgopal wrote: post #67

wentin wrote: post #61

Earlier quoted context omitted.

why is showing your algorithm doesn't work funny?

That example actually wasn't meant to be related to the hands/deformity algorithm-- it was meant to talk about the prompt alignment. Regardless, it does make sense for us to change up that image to avoid confusion!

Bad way to advertise your product. It's entirely reasonable to make the conclusion that your product only does one thing at a time, also that the team lacks attention to detail (for a product that's all about attention to detail)