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

Wonder Studio: this AI-powered tool might be a preview of the future of VFX

3dvf.com

Post reply on HN
Print view View original

21–30 of 37 posts

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#21

Post by achow »

Melatonic wrote: post #10

All of the examples are extremely easy shots. Anything complicated is likely still going to need real mocap type work. Also look at the faces of all of the characters - they have very little facial movement. Lipsync is much easier to visually match than something like subtle facial expressions. What this may do well is automate the low hanging fruit (easy shots) and provide a nice starting point. It also very well mi…

Not a VFX artist, but know lot of amateur weekend movie makers, also in the circle where 'concept videos' gets made for some or other tech proposals.

This could be a disruptor for above two scenarios.

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#22

Post by trollied »

Solano wrote: post #11
Melatonic wrote: post #10

All of the examples are extremely easy shots. Anything complicated is likely still going to need real mocap type work. Also look at the faces of all of the characters - they have very little facial movement. Lipsync is much easier to visually match than something like subtle facial expressions. What this may do well is automate the low hanging fruit (easy shots) and provide a nice starting point. It also very well mi…

jeah they really shouldn't exist because their product may not be 110% perfect. have you even used it even?

That is not what the parent poster was inferring.

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#23

Post by KaoruAoiShiho »

Melatonic wrote: post #10

All of the examples are extremely easy shots. Anything complicated is likely still going to need real mocap type work. Also look at the faces of all of the characters - they have very little facial movement. Lipsync is much easier to visually match than something like subtle facial expressions. What this may do well is automate the low hanging fruit (easy shots) and provide a nice starting point. It also very well mi…

AI facial animations is just a half step away from this.

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#24

Post by tikkun »

achow wrote: post #21
Melatonic wrote: post #10

All of the examples are extremely easy shots. Anything complicated is likely still going to need real mocap type work. Also look at the faces of all of the characters - they have very little facial movement. Lipsync is much easier to visually match than something like subtle facial expressions. What this may do well is automate the low hanging fruit (easy shots) and provide a nice starting point. It also very well mi…

Not a VFX artist, but know lot of amateur weekend movie makers, also in the circle where 'concept videos' gets made for some or other tech proposals. This could be a disruptor for above two scenarios.

> also in the circle where 'concept videos' gets made for some or other tech proposals.

What do you mean by this?

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#25

Post by TheRealPomax »

Melatonic wrote: post #10

All of the examples are extremely easy shots. Anything complicated is likely still going to need real mocap type work. Also look at the faces of all of the characters - they have very little facial movement. Lipsync is much easier to visually match than something like subtle facial expressions. What this may do well is automate the low hanging fruit (easy shots) and provide a nice starting point. It also very well mi…

Judging any AI "this will disrupt X" claims based on what you're being shown right now is missing the point of the claim. Is there enough here to cause disruption with continued development? Yeah the faces are bad: have you seen how much the state of the art has improved over only two years? For how much longer do you think those faces are going to keep looking bad? Two major versions? One? Not even one?

When it comes to graphics AI, don't look at right now, look at the trajectory. Is this something final, or is this just the minimal viable release that's going to be the starting point for (radical) improvement?

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#26

Post by softfalcon »

tikkun wrote: post #24
achow wrote: post #21

Earlier quoted context omitted.

Not a VFX artist, but know lot of amateur weekend movie makers, also in the circle where 'concept videos' gets made for some or other tech proposals. This could be a disruptor for above two scenarios.

> also in the circle where 'concept videos' gets made for some or other tech proposals. What do you mean by this?

It’s common to put together a pilot or proof of concept trailer with some cheap CGI shots to show to possible investors or production studios.

Think of it like an elevator pitch for a film project. It’s one way to get your show or movie green lit.

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#27

Post by plastic3169 »

Love seeing this area being developed. I think this is even too ambitious. If you would focus on professional VFX artists and follow their day to day workflows it’s quite evident that there is lot of room to improve just in the basic tools.

So far my feeling with deep learning tools is that they are too heavy handed to be usable. I’d just need small helper tools that I could integrate to existing software. No need to try to do everything for me. Just make the existing stuff ”smarter”.

Keyer that actually recognizes actor from green screen. Color corrector that gives default settings that match two elements together. Painter that fills area based on the surroundings etc. All this but so that I can take the input and continue from there.

Or maybe I am seeing first time a car and keep hoping it would be a faster horse.

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#28

Post by appstorelottery »

anotheryou wrote: post #17
eps wrote: post #15

Earlier quoted context omitted.

At 00:37 robot's hand is way thinner than the original actor's, but the missing parts of the background are perfectly reconstituted. I realize that Photoshop could do this few years ago, but here it looks a bit too flawless.

why is it "too flawless" if photoshop can do it for years :) ? You can see flaws if you look at the head around 1:56 to 1:58

If you look closely at the "Clean Plate" demo right at the end, there is a shimmering where the character was removed. This isn't a criticism of the product, because I certainly can't do better myself - and they might be pushing the realms of what is possible right now... so kudos, it's amazing stuff. But it's not perfect, and perhaps it just has to be "good enough" for the target market (which based on previous comments is not big VFX houses with the resources to create their own internal tools).

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#29

Post by nier »

achievingApathy wrote: post #7

When you get Spielberg to be on your board of directors, it really seems like it is legit.

You’re right but then again they seem to be far away from that situation as all they have is an advisory board.

How they present themselves and what they have at this point seems exaggerated to me and makes me cautious.

This is not how startups and solutions look that turn into success stories in the future. It just doesn’t feel right.

Re: Wonder Studio: this AI-powered tool might be a preview of the future of VFX

#30

Post by bbor »

plastic3169 wrote: post #27

Love seeing this area being developed. I think this is even too ambitious. If you would focus on professional VFX artists and follow their day to day workflows it’s quite evident that there is lot of room to improve just in the basic tools. So far my feeling with deep learning tools is that they are too heavy handed to be usable. I’d just need small helper tools that I could integrate to existing software. No need to…

Very well worded and helped me clarify my thinking on these models - thanks! Definitely agree, tho I don’t have experience in this particular domain. “Replace humans entirely” seems like a foolish goal for professional art; not only would audiences have an aversion, but LLMs by definition aren’t deterministic/symbolic so you’re going to end up fixing small details anyway.
Post reply on HN