The physics principle of diffusion inspired modern AI art
quantamagazine.org
The physics principle of diffusion inspired modern AI art
1–10 of 20 posts
Re: The physics principle of diffusion inspired modern AI art
#2Is this a submarine ad for Coca-Cola?
Re: The physics principle of diffusion inspired modern AI art
#3Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
Re: The physics principle of diffusion inspired modern AI art
#4Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
I think they refer to Gradient Descent: https://en.wikipedia.org/wiki/Gradient_descent
Re: The physics principle of diffusion inspired modern AI art
#5Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
They refer to score models, where the score is the density of the dataset at the input.
Imagine you have a huuuuge landscape, with peaks and valleys. This landscape defines the density of the distribution. Now, imagine that you have a bunch of samples drawn from the distribution, this is the dataset.
Sampling an image is a mixture of dirac delta functions (or a mixture of Gaussian with variance approaching zero).
We can increase the variance to smoothen the landscape. This sort of builds an empirical estimate of the true landscape.
The height of this landscape is “the score”.
It turns out that we can actually compute an approximation of the gradient of the score.
The gradient of the score always points towards where the score (aka density) will increase, and you essentially apply gradients to “walk” towards a high density region.
This idea is actually very similar to using gradients to create poisoned inputs that are falsely predicted.
I am being a bit handwavey here, we don’t just increase the variance, but this is a decent enough approximation of what’s happening and what the gradient refers to in this case.
For all intents and purposes, you can think of the gradient as a vector pointing towards the direction that the density of the dataset increases.
Re: The physics principle of diffusion inspired modern AI art
#6Is this a submarine ad for Coca-Cola?
Maybe an ad for Dall-e, since Stable Diffusion has taken the art world by storm by leaps and bounds.
This is made even more prominent by the lack of any mention of the competitors.
Re: The physics principle of diffusion inspired modern AI art
#7Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
I think they refer to Gradient Descent: https://en.wikipedia.org/wiki/Gradient_descent
Do engineers not take calculus anymore these days?
Gradient descent uses the gradient, but is itself not the gradient.
The gradient itself is just the vector of partial derivatives with respect to each parameter.
Gradient descent is just following the gradient "downwards" towards a minima.
The article even describes it pretty well in non-mathematical terms.
> the gradient of the distribution (think of it as the slope of the high-dimensional surface).
I always hear devs say they never use calculus but I suspect it's because you can't use what you don't understand.
Re: The physics principle of diffusion inspired modern AI art
#8Earlier quoted context omitted.
I think they refer to Gradient Descent: https://en.wikipedia.org/wiki/Gradient_descent
Do engineers not take calculus anymore these days? Gradient descent uses the gradient , but is itself not the gradient. The gradient itself is just the vector of partial derivatives with respect to each parameter. Gradient descent is just following the gradient "downwards" towards a minima. The article even describes it pretty well in non-mathematical terms. > the gradient of the distribution (think of it as the slop…
>Do engineers not take calculus anymore these days?
Yes, we do, like a decade ago at school when we were forced to learn it. Then the knowledge atrophies unless you're actively using it in real life.
The majority of engineers I know, including myself, work on some form of web services, mobile apps or FOTM UI frameworks, and you don't need calculus to style a progress bar or query a database
Re: The physics principle of diffusion inspired modern AI art
#9Is this a submarine ad for Coca-Cola?
Maybe an ad for Dall-e, since Stable Diffusion has taken the art world by storm by leaps and bounds. This is made even more prominent by the lack of any mention of the competitors.
> The key insight that makes DALL·E 2’s images possible — as well as those of its competitors Stable Diffusion and Imagen — comes from the world of physics.
Re: The physics principle of diffusion inspired modern AI art
#10Earlier quoted context omitted.
Do engineers not take calculus anymore these days? Gradient descent uses the gradient , but is itself not the gradient. The gradient itself is just the vector of partial derivatives with respect to each parameter. Gradient descent is just following the gradient "downwards" towards a minima. The article even describes it pretty well in non-mathematical terms. > the gradient of the distribution (think of it as the slop…
>Do engineers not take calculus anymore these days? Yes, we do, like a decade ago at school when we were forced to learn it. Then the knowledge atrophies unless you're actively using it in real life. The majority of engineers I know, including myself, work on some form of web services, mobile apps or FOTM UI frameworks, and you don't need calculus to style a progress bar or query a database
The rate of change of that progress bar would be the gradient of the progress with respect to time.
Could be a handy thing to have if, for example, you were designing some progress animation...