From Fox to Natasha Lyonne: Three Key AI Developments in Media

0:00Gonna bet speculating here that the other studios are just gonna watch this so closely because for sure it's like canary in the coal mine thing it's like oh fox is going through with this okay let's see what happens let's see what the public output is let's see if it's actually good in this episode of denoised fox clears runway ai for use in public deliverables the actual state of ai today for the use of film and tv and natasha leone is making her directorial debut with an ai film let's get into it all right what's up addy hey man welcome back thanks good to be here let's get right into it. Yes, a lot of AI stuff happening.

0:36First up, this literally hot off the press came across my radar from newsletter friend, Jenko, who runs the low pass newsletter and headline story Fox Entertainment has approved runaway AI for use in public facing outputs. That's incredible. It's such a big green light for the AI industry as it pertains to M &E. Huge. Yeah, I mean, this has always been a sort of like back and forth questionable. do like is it commercially cleared is it right legally allowed yeah so it seems like this also might have been a thing happening for a while because it is a screenshot from uh fox is uh q a internal q a and i believe it goes back to february so this might have been okay for february it's just kind of coming yeah out now but yeah the question was uh could you confirm runway is legally cleared for use in actual deliverables and the answer is yes all clear please use it and share how you're using it because people would be huge it would be hugely helpful to justify the spend and fun to show people.

1:33Yeah, sounds like Fox is still rolling it out as a test case and nice to have feature just to see how their employees are going to use it. But the fact is, you know, it's not just about having an ethical model advertising that it's, you know, good to go commercially safe, clean, whatever label you want to put on it. It's about the actual approval from the studio to use it. Yeah, which big studio is giving a green light that it's okay to use this right now and also like that's not just necessarily fox movies this fox is fox entertainment's broadcast sports yeah there's a bunch of outputs and should also say like we don't know and there's no indication that anything has actually been used yeah in broadcast we don't we don't know yet if they have published anything or for sure and i think those things will come with time like the this is like the first of many steps towards us seeing public use of pixel generated with ai other big studios like you know disney paramount all the whole entire viacom family like are they gonna follow suit like this is this is the beginning of i think other studios just kind of opening up the gates if you will yeah and i'm wondering if it's just like if everyone's gonna try to wait for some legal clarity or legal or answer that could take years and maybe still never fully be clarified of like what is and isn't approved.

2:52So it's just sort of leaping forward and be like, okay, we're just going to go with this. I mean, there was some clarity on from the copyright office where if something is completely AI generated, then it doesn't, it can't be copyright protected, which is also there are two sides to this too, from a large studio's perspective, because there's the main one of are you allowed to use generated outputs if they're trained on copyright material? And are you liable for copyright infringement? But then the other flip side is the stuff you create can you copyright protect it because that is a huge obviously of interest for studios to make sure that their stuff that they generate is legally protectable right and it's not like a runway can kind of have ownership over it or if it's even not ownership right you know and a lot of the ai companies i mean uh i i know fox is on you know an enterprise plan or something so like the issue is like if they're entering stuff from one runway whatever plan they're on.

3:46Yeah. The mega plan. Yeah, the mega plan. They have the copyright protection to the extent of the law. But we know we have the ruling from the Copyright Office that without human input in it, which I think is still probably going to be debated of what that classifies as, it can't be copyright protected if there's no human input involved. 100%. I'm going to bet, speculating here, that the other studios are just going to watch this so closely. Oh, for sure. It's like canary in the coal mine thing. It's like, oh, Fox is going through with this. Okay, let's see what happens. Let's see what the public output is.

4:20Let's see if it's actually good. And then the other thing I'm wondering about is how is it actually deployed inside of Fox? Is it like a secure cloud portal to runways data centers? Or is it locally run inside of the Fox studio walls? Or is it just an API handshake? Like, what is it? Yeah. Like, are they still using runway servers? what is yeah i mean i'm also just curious like what are they what would the outputs be like i'm guessing it would probably start with images images or just marketing assets additional assets i wouldn't even go that far i think it would just be previous stuff concepting maybe in the development teams yeah but we know about that i mean this is saying it's a proof for it's a proof for for distribution not that they're not allowed to use it but that they're allowed to clear it for use in actual deliverables.

5:08That was the quote from the Q &A. Yeah, I think it's still a long ways out because it's one thing for Fox employees to have access to it. And given the green light, it's another thing to actually master the tool and get it to a level where the output is acceptable. Yeah, exactly. And I'm guessing like you that it would not be we're going to generate a complete shot or something and insert that in our, you know, like that they're going to generate a shot of a football player and use that in a promo video for like, you know, NFL or something like I don't think that's going to be the case. You know, I'm guessing, you know, probably just modifying assets or background plays or some element or something.

5:44There is another interesting point to and also this ties into like that it's not just for previous but for broadcast. The FAQ document did indicate that employees should tell Fox's broadcast standards and practices group if they were using any AI generated videos in any broadcast or production material. so just to tell them not necessarily that it's not prohibited it's allowed and from their original statement and that also their gen ai use guidelines require them to consult with their manager and business unit legal team prior to commercial or external external use it's like uh well well yeah but if you know fox is massive and has a bunch of different units so right yeah but no i mean i think the big thing here is like it is getting the green light for public distribution not just internal use.

6:26And interesting that they chose Runway and not somebody like Adobe or OpenAI or, you know, whoever. Why Runway? Is it because of quality or was there like a, you know, a back end deal or what have you? Yeah, I mean, I agree. I think, I mean, just from a user perspective, like Runway has generally been ahead of the curve and had the best and most realistic looking models out of anyone else. We covered the references thing. that's amazing yeah and gen 4 uh their latest model has been up there with vo2 from google like as the best outputs that i've seen our guy crystal ball was killing it so maybe maybe fox is just waiting for the audio i don't remember what the name of the speculative audio controls they're just yeah they're on board with that they're all yeah they're like well we don't want to do any work we just want to talk to the thing i mean the funny thing is this has been around for a few months.

7:20So we just know about this now. But yeah, I think it's a step forward. And one of the early to mid dominoes falling that... It's a big domino. Let's see if it's big enough to push the other dominoes. And also, this is not something that you advertise. This is not going to help Fox's publicity in any way. The only reason we know about it is it probably just got out and they wanted to get ahead of it. Yeah, it seems like just, you know, there was a screenshot or something from their FAQ that came out. Yeah, I mean, like we said, AI is stuff that everyone is using or probably using. Yeah, for sure.

7:52And no one wants to talk about it because there's just nothing but like negative backlash against it for usually not a good reason. How could you not be testing with AI if you are a studio in this climate, in this downturn with the industry the way it is, with the budget the way it is? How could you not at least have a few engineers that are just pushing this? Yeah, you got to understand it. 100%. Also, yeah. And also, so... Or you'll be left behind. Yeah. And so whether you use it or not, or whether you internally make the decision to use it, or there's a legal clarification whether you can use it.

8:25So like, when that happens, you don't want to be starting from zero. Yeah. And being like, oh, well, okay, now we're allowed to use this AI thing. Let's figure out this AI thing. Yeah. You definitely want to be at the point where it's like, well, we know how we can and the ins and outs of the AI thing. So that once we get the green light, I mean, look, I think, you know, it's not like this is magically going to disappear. there's going to be some ruling that the AI thing is, I guess, not going to work out. Sorry, everyone, let's pack it up and go home. Like, that's not going to happen. No. So, you know, I mean, maybe there are ways to train models.

8:54And we'll talk about this in the next story. But I mean, you can train models and completely clear data and stuff. So like, there are ways to work with AI and completely eliminate the debate or issue of, you know, is the AI that we're using trained on commercially clear data? Because, yeah, we know there is a way to do that. 100%. And from, like a public sphere, like stepping back as like a regular American and just looking at where AI is really coming in, coming in odd. It's our industry, M &E and automotive, like with all the autonomous vehicles. Yeah. Like you don't see fintech being impacted too much.

9:30Well, I mean, you know, Mark Andreessen just, you know, said that the one thing that AI can't replace is venture capitalists. Of course, of course. You can replace everything else but venture capitalists. Yeah, because he's a venture capitalist. It'll replace everything else that I don't do, but it can't replace me. I would say the complete opposite. I think venture capitalism is a state of decisions that could be handled much better by an emotionless, highly reasonable AGI. Analyzing a bunch of data and making a yes or no decision. And how much money. Right, and how much to invest in the risk tolerance.

10:05Seems like a prime use case for AI. I think he would know that better than anybody else. He's not stupid. Yeah, the only thing AI Baby doesn't do right now is the human interaction of knowing about the deals or whatever. But what's, you know, about the deal then? I think he's just trying to keep his employees cool and calm. So you're not going to be replaced, I promise. Which brings us to our next topic, state of AI use. Now, I wanted to talk about this because I thought we hear a lot of hype. We cover a lot of new tools. We cover, you know, like dominoes falling. What is the actual capabilities of AI today?

10:43And how are creative technologists actually using it? And I have a little bit of insight. I was just on a project where we tested with AI, didn't get the clearance to use it. But we certainly got to a point where it was like, oh, this is legit. It's going to save us a lot of time, money, and get us a better output. Can you talk about anything like what you tested in vague terms? Yeah, it was a video generation tool that was really good at the thing that we were trying to solve. We were trying to generate motion graphics. And motion graphics for a motion graphics artist is very time consuming. Of course, they'll have way better control over it, perhaps higher quality than something AI can generate.

11:25But we were literally given eight days to create 30 minutes of motion graphics, and there was two artists. Yeah. And the first thing they did was they turned to some, you know, off the shelf video generation tool, kind of like a runway or whatever. And stuff came out really good. And then they actually went into After Effects and modified the AI generated stuff and layered it with stock footage. Right. So they used the AI output as a base layer. and they got to a good place and then we brought it to the studio. Studio's like, well, don't use that tool. We kind of are talking to these guys, referring to another AI company.

12:06Why don't you try their tool? And we're like, okay, let's get on a meeting with them. Let's kind of call with them. And then that call went really well. We were just about to convert over to this tool that is quote unquote studio approved. And then the studio comes back and changes its mind. this is actually hold that thought because no ai is going to be used on this project okay even though it's going to be just for like motion graphics correct yeah yeah okay and uh we were like sorry guys you're gonna have to work your butt off so those two motion graphics artists just went at it for like the next six days or whatever okay so these ended up the solution ended up being they didn't cut anything down they just they we had to remove all the ai elements no but i mean you had to remove the ai stuff but because initially the issue was you had about 30 minutes of graphics you had to create with two animators yeah and so the solution ended up being make the animators work like non-stop yeah correct did you cut any of the graphics down or it just was like i would argue that the graphics were compromising quality because of that just to like because i had a triage yeah like just get something done just just get the minutes out yeah work but exactly okay yeah so that was my story and then uh going back to i have a really good friend who's also in the AI world and consults for a lot of studios and does AI, you know, R &D and sort of test bed situation for them.

13:27And we were like, yeah, the way, how do you use AI for the consultation work that you do? I do it this way. And I was like, this is what I have experience with. And a lot of that stuff lined up. So I want to share some of the things with you. I think the most obvious is, you know, you'll hear this from everybody ai is just a tool it's not the entire thing it's part of your arsenal and the other 90 of your arsenal is stuff you already know like nuke like maya like unreal what i've always been complaining about too is like you know ai is such a broad term and i feel like we just need better lingo a more specific lingo around because it could be so many things of like a tool you know it's something from runway type of text get a whole shot out or 11 laps of re-speecher that's also ai yeah or move ai is a right or it's like i need you know i want to go to another site and just generate a 3D object that I'm using in my Unreal Engine scene.

14:17I just need something specific to spin up. So there's so many different use cases. I feel like that's where so much nuance gets lost. Yeah, I think in this case, I'm talking specifically about generative AI. So from text to image or text to video. And what I think a lot of people are realizing is there is no way around the fact that you're going to have to custom train and fine tune foundational models to get what you want. so it doesn't matter how incredibly good you are at prompting or if you're using like a prompt engineering mechanism like you put your prompt into a prompt model and then that prompt model will generate like almost like machine talk for the video generation or i've like made a project yeah prompt pre-built so i give it like a very crappy prompt and then it rewrites it into a yeah better prompt for whatever i'm trying to do prompt structuring is is like uh is going to help but it's not going to get you what you want.

15:10Like if you are Coca-Cola and you need your cursive Coca-Cola, you know, signature logo, there's no way around it than fine tuning image generation, video generation model with a ton of the Coca-Cola logo. Right. And then attach it as a Laura. And we've covered, we've talked about Laura's before. Low rank adaptation models. It's basically a mini model that latches on to the big model. So if you think about the big model as like a giant ship, a LoRa is like the tugboat. It's a tiny little powerful thing that's like steering it. Custom train on yourself can be from 20, 50 images of something like a person, a face, an object, a product, a location.

15:51Yeah. So that LoRa model, you still have to build on your own. Right. And the way you could build it is you could build it on the cloud. You could build it in comfy UI or there's other ways to build it. I was like more and more tools to have been adding features of, they don't even call it LoRa, but it basically is like. It's fine tuning. Right. build your own custom object or something. And it's like, give us 20 photos of your thing. And then it trains a model. It's basically doing this in a very easy to use fashion. Absolutely. And now that you're getting into essentially building your own model, you have the same problems that these big guys do, which is like, how do you create a data set correctly?

16:25How do you condition that data set, prep the data set? And then how many times is that data set going to run through this model, which is called an epoch? How many epochs are you're going to have to get this to be right. And then there's a problem of overfitting and underfitting. Overfitting is when you've trained it so hard that it's just rigid and all it can output is that Coke logo, right? Like, you know, you can ask for a car and it'll just output the Coke logo. It's overdone. It's like a steak that's too well cooked. But you, you know, the other end is if it's medium rare, it's not giving you the Coke logo, right?

16:58You haven't trained it enough. Yeah. So you want to just, you know, medium, just in the middle. So, yeah, I've had this issue trying to do like some early Laura's on like myself. Yeah. And, you know, a lot of the photos were maybe from an angle or like smiling. So then all the outputs. Yeah. Even if I'm trying to get a different expression for myself, it's always sort of like a weird, like a smiling kind of thing because that was all the photos I gave it up. Yeah. And on the specific topic of face, one of the videos that I saw that solves that is take your photos that you gave to the Laura and remove the background.

17:31like keep it on a white background red or green or blue background and that'll actually train the loras way better just having a clean background yeah exactly just no additional noise to yeah that's interesting yeah so there are all these tricks that people are finding out yeah the other thing that is used a lot for controlling the generation is structuring structuring is just a fancy way of saying that you're giving it lines and edges for the generation to stick to so it's almost like you know you give the ai a skeleton and then it's filling in the muscles and the fat and the skin okay yeah but that skeleton you have a high level of control over and generally that how that's done is through actually 3d so let's say you know in the case of like uh like paul trillo making that cuckoo video how they generated that la street was they built that la street i think in blender with all the little shops and then the background was just like 2D mats of city and skyscraper.

18:31And they had a camera through that 3D environment, which was the correct perspective, correct number of buildings. And then what the AI model did was just neural render over that. So like kind of like a video to video, essentially. And that's the other thing I want to talk about. I think a lot of the work for professional use is not images. It's not images at all. It's not even image to video. Yeah, there is a big sort of focus on image as the reference guide, not prompts, not anything else. But end of the day, it's about taking some kind of input video, making some kind of output video. Yeah, we're talking about that.

19:09I think that is probably going to be the way things, whether that is near term, the next like year to two years, that's how we get the job done. And then who knows where the AI capabilities are after that. Right. But yeah, some type of in painting in a video. So like that could be shooting with a real actor, on a green screen or some sort of just roughly keyed background like with light craft or something and keeping the actor in the performance but changing the background yeah yeah something like in that realm but working with video as the source because yeah the image to video and despite all of these other tools adding you know pre-built camera movements and motions and stuff it's like this like no one here in the industry wants to operate a camera with like a preset it's like that it's not operating a camera that's not controlling the movement that's never worked even animators you know working on like animated films or you know between programming the camera with keyframes or using an actual like camera tracker right it's a different feels a different experience i mean even in the animation world like you would think there is a walk cycle i mean every character walks right so like wouldn't an animator just start with like a walk cycle and then modify that walk cycle like why animate every single bone in a walk cycle well it turns out if you want to have full creative control and create a very unique sort of gate and walk to that, you have to start from scratch.

20:29And that's the same approach to cinematography. Like you don't want this weird punch in that is preset and pre-programmed. No, I want to build my own and put my own fingerprint on that. Right. I mean, even for regular films, it's like, yeah, these are cinematographers, DPs, they know cameras, they know lenses, they know films or digital, they will still do extensive camera testing with every lens and the camera. And if they're shooting film, the different film stocks and different skin tones and different clothing to test it all out for the look for that film. Yeah. And creatives a lot of times don't do this for obvious reasons.

21:05A lot of times it's like a self-fulfillment thing. Like they just want to do this thing because they feel so strongly about it and it satisfies a creative urge for them. It makes no sense. but it's kind of like the the ron howard motel sequence in the studio i got you on that one for those of you uh who don't know what i'm talking about addy has just discovered the studio now he's catching up and when you watch i didn't want to bring up the ai episode that just aired and also because it did just air so i don't want to spoil it if people haven't watched it yet but next week we'll talk about the ai episode because i know you will have caught up and that'll give enough people enough time if they haven't watched it yet to watch the latest episode.

21:42We got to throw up some clips of the episode when we do that. Yeah. Okay. What are some of like in the practical sense of like actually using AI and using it as a tools? What are some of the things you've been seeing? Yeah. One of the tools that I think is slept on is Invoke AI. I just discovered. Yeah. I had not heard of it either. So yeah. Tell me what, how you stumbled on this and what has been standing out to you from with Invoke. Yeah, so using something like Runway, you know, it is a fairly easy to use web UI. You know, you upload some references, you can prompt a crap out of it. And there's even a few presets to, like Runway now has, I think, the punch in the face preset.

22:27No, that's Pika. Okay. Pika's the one with like presets galore. Yeah. So like cake, the cake face or the squishy face. Exactly. That's all Pika. I saw somebody make a beautiful montage of like a bunch of politicians getting punched in the face. I was like, this is what it was really built for. Like UGC that could get a lot of clicks. The meme factory. The meme factory. But in the real world, in our professional world, that stuff really doesn't have any high ROI. The way Invoke does it is it brings it into a very familiar ecosystem of tools and workflows we're familiar with. So most of us in the industry know Nuke.

23:05we know Houdini and also DaVinci Fusion and those three tools are all node based. Resolve as well. So creating a node based tree that is easier than Comfy UI is one of the things that Invoke does. The other thing Invoke does really well is when you generate an image you can do in painting in layers. You can mask the portions of the image in layers and each layer ends up being highly modifiable on its own very similar to photoshop or after effects or any of the layer-based systems it seems so obvious but i still haven't seen something that elegantly built and i was really impressed i think that invoke uh ceo if i can remember his name kent kiersey he goes through a youtube video where he actually uses his own application to just like modify something yeah the youtube panel has a bunch of tutorials he runs a bunch of tutorials on his youtube panel using invoke yeah and it's like he gets it because like one of the examples was him taking a a very generic ai generated image of a guy uh like a model fashion model with a leather jacket and then there was a lot of skin on his chest and his face and it just looked like a plastic doll right and one of the common issues with ai yeah and that that goes into the ai slop category right And so he gets it.

24:27He's like, look, this is obviously not going to work. How do we bring skin detail and then just correct that skin? And then he'll go through layer by layer, adding like pores and fine details to the skin, taking off some of the specular highlights and all this stuff that a professional artist would do. So I think it's a really neat thing to see when people from our industry who actually do the work that we do use AI to generate the thing that is actually of caliber. Yeah. Yeah. And any other control standout? I mean, I know one of their big things with checking out their website was data and IP, both ownership and input, kind of a big focus on using neural models or using LoRa or using models that are trained on already commercially clear data.

25:09I think a lot of AI companies are big on security now more than ever before. I'm not a big internet security expert, but I keep hearing SOC2, SOC2 a lot, SOC-2. It's like a security standard. so these guys are shock to compliant as i'm sure you know obviously something like aws would be as well yeah and that's like a sort of security standard but i think that's like the standard that you have to meet to work with a lot of enterprise companies yeah that's like i think the bare minimum and then there's standards built on top of all of that yeah but like to be in the conversation to be a right viable tool for these companies you have to like yeah you can't just have like three servers in your garage connected to the internet like that's not safe you know so So there is a big cost associated with security compliant, right?

25:56And these guys have gone through those steps. Yeah. Do you see anything with the outputs or anything that it does differently, either with color space or just what it's able to generate? Yeah. So I think one of the things that even on the Bebel conversation, right? Yeah. So yeah, I bring that up. The NAB interview we did with Bebel, which we've covered them in the previous years, but super cool tool where you could upload your video and then relight your video. Right. And they built a web platform. You upload your video to their web platform, do your edits, and then they can give you the video.

26:27Either they'll give you, I believe, like an H.264 video, which is not the most usable for professional work, or I believe an image sequence. Which is a little bit more usable. A little bit more usable. Yeah. But yeah, there were some comments on that video pointing out that for professional workflows, VFX workflows, it needs to work with EXR files and also be in ASUS color space, EXR. And that a lot of the issues with AI is that the AI is trained on sRGB images. So can you break that down of like the issue of like the training of the color space and the color space that like professional VFX pipelines need?

27:04Yeah, I think if you go from like a consumer role, that's, you know, iPhone mobile based running H.264 or JPEGs, you're in a very like, technically speaking, you're in like a very low bar of quality that you can achieve. when you go to a professional VFX workflow, it's like what the technology today can do, as good as it gets. And so that means OpenEXR, ASUS, ColorSpace, perhaps Rec.2020, exploiting the camera's sensor abilities to the max with the most dynamic range, using a lot of raw inputs. OpenEXR is a file format for images that I think, I don't know of anything that can hold a higher quality image than that.

27:50So it's obviously much higher quality than the JPEG, much more than a PNG or a Targa. Like it's like the top of the hill. And the reason for that is I think they internally use something like 16-bit encoding, decoding, something like 100 megabits per frame. Like it's insane how heavy OpenEXR is. So when you have an OpenEXR sequence as a video, it could be easily in the hundreds of gigabytes if not a terabyte there is no compromises like it is doing some kind of loss less compression but it's as good as it gets the reason you need that is because vfx is often done at a pixel level right you're painting stuff out at a pixel level and so if you don't have the resolution you're gonna just paint a big blotch of stuff or you're going to just render something that just doesn't fit in a line, then things are going to swim by the time you composite a bunch of those together.

28:50On top of that, you need an alpha channel to control transparency, which obviously EXR supports. Most things don't. There's so many requirements for professional VFX workflows as far as file formats and fidelity goes. And I think it's just, yeah, somebody just coming to Bebel saying, yeah, this is great, but hold your horses when you say this is vfx ready actually this is what we need for it to be vfx ready srgb is a color space that is synonymous with like photoshop uh it's similar in color gamut size to like a rec 709 which is you know 30 40 years ago yeah eight bit right like 256 steps uh very small in terms of how saturated the red green blues can get right now we're in uh asus color space uh close to rec 2020 20, which is more synonymous with like HDR 10 bit.

29:41And then we're going to probably move past that color gamut into a 12 bit world very soon. You know, like the last two decades of our lives, we saw the transition from standard def to high definition, which is also a transition from 8 bit to 10 bit, which is also a transition from standard dynamic range to high dynamic range. and then the next 10 to 20 years we're going to see a similar jump we're going to go to 12 bit higher dynamic range 8k would be the standard resolution and then you know file formats will have to adjust to this new quality bar but vfx is already there right right so in the working space i mean obviously that's to get it to the good spot and then output it and the the lower i mean i think you know this more better than i do it's like you want to create your frames in the highest possible quality so then all you're doing is down sampling to all the different formats yeah but in the vfx world you need the highest highest possible sample also you gotta remember like color you're seeing the stuff in a movie theater screen and the dailies and things like i don't know 30 40 feet wide like you're gonna notice every single thing right and especially as either projection or if more movie theater switch to like onyx led displays uh slash apple vision pro or uh just other beyond high definition but yeah high quality headsets yeah another thing where like the detail will start showing yeah especially if you use film because film still has to be scanned and brought into a vfx pipeline and the vfx added and then printed back on film like there's still a process so like now you're talking even higher resolution than 8k you're talking like 16k per frame something insane something like center is on those imax 70 millimeter prints now even if people was like okay yeah sure we'll have exr export support you're still only as good as your weakest link so all the training data is still uh srgb yeah like you could definitely like throw jpeg quality image into an exr wrapper right but you're not you're not improving anything benefits of anything so i mean is that going to be an issue later on where it's like everything's going to have to be retrained on higher data or is there something that like it could be leaned on with ai sort of like there's ai upresing is there like an ai i don't think uh improving the color space upresing will get you so far so like the reason open exr's are used a lot in something like nuke is because it holds hdr's really well hdr is when and i'm not talking about like 10-bit you know hdr on our tv i'm talking about merging different stops of images or video together to create a dynamic range that goes far beyond the camera's capabilities so like a typical camera will do like 17 stops or whatever right so you go from the lowest t-stop to the highest and then what if you do three or four ranges of that through different uh portions of the light now you put the dynamic range at like 25 26 stops and to hold that level of dynamic range you need a lot more bits and now you need 16 bits.