Earlier quoted context omitted.
Look more closely: the cup has two handles.
haha I thought this was a funny example to use. On second thought we'll replace it with something better!
why is showing your algorithm doesn't work funny?
Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
61–70 of 84 posts
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#62Isn't this product kind of impossible? Like a compression program that compresses compressed files? If you have an algorithm for determining whether a generated image is good or bad couldn't the same logic be incorporated into the network so that it doesn't generate bad images?
Not impossible at all - classifier networks are much, much easier to train than generative networks. However you can’t directly integrate the logic into the generator, you’d have to train the generator against the discriminator network. This is essentially the principle of a GAN and although many tricks have been developed in recent years, they tend to be finicky and difficult to train.
Diffusion models like SD are trained with a very simple loss function instead, which is just the L2 loss of an iterative denoising process. This tends to result in stabler training than using GANs. However, you could fine tune SD with reinforcement learning using the deformity detector as the reward, but it’s not a panacea as it could lead to overfitting and performance degradation.
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#63Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#64I tried it out, the first result itself was wrong. I am sort of a potential customer for a product I am working on. The feature detection and scene description even was off. https://app.rubbrband.com/image/f2e1h.png
Hey! Feel free to shoot us an email at contact@rubbrband.com. Happy to set the record straight
[dead]
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#65Coming soon from YC: SpelCheck.
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#66Isn't this product kind of impossible? Like a compression program that compresses compressed files? If you have an algorithm for determining whether a generated image is good or bad couldn't the same logic be incorporated into the network so that it doesn't generate bad images?
Not impossible at all - classifier networks are much, much easier to train than generative networks. However you can’t directly integrate the logic into the generator, you’d have to train the generator against the discriminator network. This is essentially the principle of a GAN and although many tricks have been developed in recent years, they tend to be finicky and difficult to train. Diffusion models like SD are t…
> Not impossible at all - classifier networks are much, much easier to train than generative networks. However you can’t directly integrate the logic into the generator, you’d have to train the generator against the discriminator network.
Generative networks are ime not at all difficult to train because the amount of training data is typically orders of magnitudes larger. In this case, the idea is to train something to classify images as high or low quality, which I think is just as hard as generating images. Regardless, if you had such logic, I don't see why you couldn't incorporate that into the network's own loss function? That's how it is done for L1 and L2 regularization and many other techniques for "tempering" the training process.
The problem is that you want the model to be creative but not "too creative" (e.g eight finger hands). But preventing it from being too creative risks making it boring and bland (e.g only generating stock images). I don't think you can solve that with a post-processing filter. Generating say 100 images and picking the "best" one might just be the same as picking the most bland one.
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#67Earlier quoted context omitted.
haha I thought this was a funny example to use. On second thought we'll replace it with something better!
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!
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#68Every day I find AI creepier and creepier. Like a non-chemical hallucinogenic inducing stimuli.
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#69Congrats on the launch. It's an interesting idea.
What are your thoughts on DPPO[1] and if your model(s) could be integrated into that or a similar process to fine tune the original model? Could that potentially remove the need for this product?
Re: Launch HN: Rubbrband (YC W23) – Deformity detection for AI-generated images
#70Earlier quoted context omitted.
Is there any model that doesn't output deformed hands?
iirc midjourney has figured it out although its closed source if you were wondering.
Checked midjourney discord - it still generates weird hands from time to time, but it's much better than before.