Live data from Hacker News

Stable Video Diffusion

stability.ai

61–70 of 316 posts

Re: Stable Video Diffusion

#61
post #14

Earlier quoted context omitted.

Very unusual comment. I do not think so as the chance of constructing a fleshy eldritch horror is quite high.

How is that not the first question to ask? Porn has proven to be a fantastic litmus test of fast market penetration when it comes to new technologies.

No pun intended?

Re: Stable Video Diffusion

#62
post #14

Earlier quoted context omitted.

Very unusual comment. I do not think so as the chance of constructing a fleshy eldritch horror is quite high.

How is that not the first question to ask? Porn has proven to be a fantastic litmus test of fast market penetration when it comes to new technologies.

Market what?

Re: Stable Video Diffusion

#64

A seemingly off topic question, but with enough compute and optimization, could you eventually simulate “reality”? Like, at this point, what are the technical counters to the assertion that our world is a simulation?

Why does it matter? Not trying to dismiss, but truly, what would it mean to you if you could somehow verify the "simulation"?

If it would mean something drastic to you, I would be very curious to hear your preexisting existential beliefs/commitments.

People say this sometimes and its kind of slowly revealed to me that its just a new kind of geocentrism: its not just a simulation people have in mind, but one where earth/humans are centered, and the rest of the universe is just for the benefit of "our" part of the simulation.

Which is a fine theory I guess, but is also just essentially wanting God to exist with extra steps!

Re: Stable Video Diffusion

#65

A seemingly off topic question, but with enough compute and optimization, could you eventually simulate “reality”? Like, at this point, what are the technical counters to the assertion that our world is a simulation?

The brain does simulate reality in the sense that what you experience isn't direct sensory input, but more like a dream being generated to predict what it thinks is happening based on conflicting and imperfect sensory input.

To illustrate your point, an easily accessible example of this is how the second hand on clocks appears to freeze for longer than a second when you quickly glance at it. The brain is predicting/interpolating what it expects to see, creating the illusion of a delay.

https://www.popsci.com/how-time-seems-to-stop/

Re: Stable Video Diffusion

#66
post #42

Earlier quoted context omitted.

I have seen them, the workflows to create those videos are extremely labor intensive. Control net lets you maintain poses between frames, it doesn’t solve the temporal consistency of small details.

People use animatediff’s motion module (or other models that have cross frame attention layers). Consistency is close to being solved.

Temporal consistency is improving, but “close to being solved” is very optimistic.

Re: Stable Video Diffusion

#67

Looks like I'm still good for my bet with some friends that before 2028 a team of 5-10 people will create a blockbuster style movie that today costs 100+ million USD on a shoestring budget and we won't be able to tell.

Definitely a big first for benchmarks. After that hyper personalized content/media generated on-demand

Re: Stable Video Diffusion

#68

A seemingly off topic question, but with enough compute and optimization, could you eventually simulate “reality”? Like, at this point, what are the technical counters to the assertion that our world is a simulation?

(disclaimer: worked in the sim industry for 25 years, still active in terms of physics-based rendering).

First off, there are zero technical proofs that we are in a sim, just a number of philosophical arguments.

In practical terms, we cannot yet simulate a single human cell at the molecular level, given the massive number of interactions that occur every microsecond. Simulating our entire universe is not technically possible within the lifetime of our universe, according to our current understanding of computation and physics. You either have to assume that ‘the sim’ is very narrowly focussed in scope and fidelity, and / or that the outer universe that hosts ‘the sim’ has laws of physics that are essentially magic from our perspective. In which case the simulation hypothesis is essentially a religious argument, where the creator typed 'let there be light' into his computer. If there isn't such a creator, the sim hypothesis 'merely' suggests that our universe, at its lowest levels, looks somewhat computational, which is an entirely different argument.

Re: Stable Video Diffusion

#69

In the video towards the bottom of the page, there are two birds (blue jays), but in the background there are two identical buildings (which look a lot like the CN Tower). CN Tower is the main landmark of Toronto, whose baseball team happens to be the Blue Jays. It's located near the main sportsball stadium downtown. I vaguely understand how text-to-image works, and so it makes sense that the vector space for "blue j…

> Has anyone come across a solution where model can iterate (eg, with prompts like "move the bicycle to the left side of the photo")? It feels like we're close. I feel like we're close too, but for another reason. For although I love SD and these video examples are great... It's a flawed method: they never get lighting correctly and there are many incoherent things just about everywhere. Any 3D artist or photographer…

Are you working on all that?
Post reply on HN