I tested Seedance 2.0. Wow.

0:00 Yeah. So, my friend Serio, one of the world's greatest AI creative minds, just took me through Seance V2 and it blew my mind. It blew my mind because the people that are going to understand how to use this model and this is the world's greatest AI creative model on the planet, they are going to be able to create AI influencers, faceless accounts, original movies, literally uh ads that convert, ads in any language on the planet. This is the creative AI model we have all been waiting for. In this episode, Serio takes you through a bunch of these use cases, show you how to do it, the prompts, the tactics, everything you need to know about Cance V2 is in this episode. And if you stick

0:46 to the end, you will be a weapon for how to use Cance V2, how to use AI video to make money, create content that gets you followers, and more. I've got one of my most creative friends on the podcast. Cereio Cerio, by the end of this episode, what are people going to learn? Ooh, a lot of things. First, why are all these image models, video models, and API providers so important to your business if you are starting uh some sort of AI app or if you're trying to solve for issues in the creative

1:31 space uh with AI tools. Um we're going to talk about all the use cases. Cance 2 is here. So we're going to try and explore all the use cases and how we can build on top of Cense to solve particular issues and then productize around those workflows. I love it. Yeah, there's tons of tutorials and videos about okay, Cance 2 is here. Look how cool this is. But this is going to be a more practical guide to actually, okay, great. How can you build a business around these models? How can you make money from these models? how can you, you know, create creative assets that are going to transform your business. So, that's my hope out of this episode and Sio, if there's anyone who can deliver on this, it's you. So excited to get into >> Thank you for having me, Greg. And I'll

2:17 I hope I can do my best here. >> All right. >> Okay. So, so Cance 2 officially launched today. Um, you can access it anywhere in all of your favorite um AI tools. And something very interesting about CDANS um is that it's probably the first AI model that allows for multi-input u uh generation. So what does that mean? We usually if you're uh never or if you've used AI tools, you know that u you can either use first or last frames and you can generate videos based on those two um uh inputs. But now with CEN 2, we're able to generate um videos with multiple inputs. For example, we can add

3:03 up to two images. We can add up to two videos. We can add an audio file. And then what CDE is going to do based on um what we are prompting and what we're trying to achieve, it's going to combine all those inputs together um and uh give us a final um video. Uh that's something very interesting here. Um because it allows us for way more control. Um and to show that I'm going to go into my demo page. Give me a second. So this is what So this is what uh it actually means right. Um in here we have a video like a green screen video to provide. So, and this is AI generated, completely

3:48 AI generated with Cense, by the way. Um, and let's suppose that I want to change I'm a production studio. I'm creating this game and and I want to put some sort of a demo on my social media or a quick video on my landing page and I want to replace these two people with um two different characters, but at the same time, I want to replace the background. Traditionally, this would take very long time, but also it would cost a lot. Uh, and what we're doing here is that we're using the multi-input feature inside CD dens. Um, and we're going to have our character one, our character two, and then we're going to have our background image. And since this is again multi-input, um, we're going to reference all these inputs in the prompt by tagging them. Um, we're

4:33 going to hit generate. And it's going to take about 60 seconds, uh, for our video to generate here. And again the purpose of multi-input as I said is to get very creative with um our editing process cense 2 it's not only a video generator it is a video editor that's how I see it. It's almost like nano banana pro whereby the use cases are unlimited. It's not it's not just producing an image an image through text in this case a video through text or a video through an image but you're combining multiple um inputs uh to produce an output that's way more complex than traditional um image to video models. You can do something very similar with Cling U 3.

5:19 Um, but the quality of Cense 2 based on my testing so far is unmatched. And um, we're going to see all the the use cases and and all um, the demo videos today. Um, and I hope that you make the decision on your own. But let's This is the video that it generated. So, this is pretty crazy. Let me try and pull up the original uh video input that uh uh the green screen here. >> This one over here is what C generates.

6:05 >> The motion control is crazy here. >> Yeah. >> Um and it's simply from a a prompt. You're literally telling it to control the motion, to keep the motion of the original video exactly the same. This is all natural language. >> First of all, this just like exceeded my expectations. Um, I think this is beautiful. Two questions for you. One is from a prompt perspective, did you just manually create that prompt or is that something that you used an LLM to optimize? >> You you can definitely use an LM to optimize. I think that Claude does a phenomenal job. Um, and it's the best by far, especially the 4.6 version. Um, Opus 4 4.6. I've used GPT before. Um, but I do think that Claude does

6:52 understand um, prompt engineering for uh, vision models a bit better, at least in my experience, and I could be biased. Um but this is uh the the more something with Cens is that the more detail you give it, the better it does differently from other models um where you can be simple and to the point. For example, Clink 3, if you're simple, straightforward, you're not using a lot of tokens or words in your prompt, um then it might do a better job. What I'm uh what I'm figuring out with C dance is that you have to be highly specific if you want to get very high quality output, especially if you're doing

7:38 something with uh that that relates to preserving character identity, that relates to preserving particular motions in the video or particular or particular um um transitions uh uh throughout. So I think that both work. I like to start my prom myself and then uh most of the time I will optimize it with claude um uh 4.6. >> Cool. And before we go into the next use case, I think I mean you're you're a stylish guy, you know, and uh I think one of the reasons why >> Yeah, you you are, you know, you're wearing your hat says Los Angeles, you know, upside down. I feel like you always got good style. Every time I see you got good style. A part of why this video crushed it was yeah C dance 2.0

8:27 did a good job but also your reference images are really on point. How how were you able to find those reference images and videos and any tips for people? Everything starts with a very good idea a very good source reference source image. What is your vision? you can describe your vision, but the second that the these LLMs or these these models see a source reference, they're able to understand your taste and they're able to mimic uh um that that reference image into something more concrete and more tangible for you. So, always focus on having a great source image, source reference that matches your idea. It's like in any traditional art, uh um I'm I'm also a painter. I

9:12 draw, I sculpt. Um, and for me, in order to visualize my idea, I have to have something in front of me that I can see and I can be, hey, I'm inspired. I want to create something similar to this. Um, and it's the same thing with LLM. Like, think of them as as as humans. If they were to be like your your your assistants or like your your friends, that's how they understand inputs. So give it a very good source u reference of whatever you're trying to to to achieve and then follow it with a very specific prompt. >> All right. Should we should we keep going? >> Yes. Okay. I'm going to showcase a video that I did myself. This is u a virtual try on video. Uh I recorded myself out there in Canada in Montreal.

10:00 It was like -30°. I was wearing shorts and I was like, "Oh, I wonder whether AI can put me into this outfit." So now I want AI to replace me to actually put me put on uh this outfit and have a bear walk by. >> And this would be, you know, helpful if maybe you're doing like what, like an ad. Maybe. >> Yes. If you want to replace, let's say that you have an actor and you're you did an ecom shoot and um you want to have the exact same motion of the model and you just want to replace the clothes, the clothes that they're wearing because you're creating this very cool transition or just because you want a very clean uh style throughout um your your um e-commerce assets. So, let's see what he came up with.

10:46 >> It is minus 30 and I'm wondering whether AI can help me put on this outfit. Okay. How about have a bear walk by? >> Look at look at the details. Like look at like how when the bear walks by and then you have all the um footprint. >> Can you stop it for a sec? >> Yeah. I >> I cannot tell that your outfit is AI. Like honestly, >> not not only that, but what I'm very impressed with is that my face is the same. If I saw this video myself, like I know how to how to >> I'm very familiar with all the AI models, open source, closed source, everything. >> Um, and I can tell you which video is what. I can tell you if it's generated with clink, if it's generated if I can tell you if it's generated with cling,

11:32 if it's generated with uh cense 1.5 uh with WAN. Um, but when I saw this video myself, I'm like, it looks like me. There's no distortion in the face, which is crazy. Um, and yes, the outfit too, like it was able to match the exact look at the boots like look look at the pattern of the u um of the pants over here. So if you go into our source reference. So if you go into our source reference over here. >> Yep. >> You see how it has like all these um like this specific pattern, this cut that's like dark. >> Yep. If we go into our video, it's here. >> Yep. >> Just crazy.

12:17 >> Okay. How about have a bear walk by? >> Look at like the footprints. It's like looking at the bear. It's tracking the bear with with with uh with the eyes and the head. Like, so it understands the input very well. Um, and mind you, the input here was very simple. Like I didn't go into any details. I could have been way more specific. I could have actually described my outfit so that the outfit could have been um more accurate. Um so it's phenomenal and again it doesn't take more than 60 seconds. >> And this tool that we're in enhancer you're the founder of this right? >> Yes sir. I am the founder of this. >> So this you can use enhancer not just with cense 2.0 right you can use other

13:03 models. You can use it with with u Yeah, you can use it with any model. Another cool use case is translating for everyone that wants to build a translation app. >> Mhm. >> Um that's going to take 30 seconds to translate or not only that but also replacing the character in the frame. Take a look at this one. So we have this original video in Chinese. >> She's showcasing the glasses. But now your company operates in the United States and you want to showcase the same classes. You want to have the same asset. You want to have her move exactly the same because you're AB testing the ads and you want everything to look exactly the same, but you want the language to be different and also the model to be different because you're

13:49 targeting different demographics. So here's our a reference model. This is a model uh that we generated previously. And now we want this model to replace the woman, >> but also we want her to speak in English. And this is the prompt that we're using. You can stop and screenshot this. Um, go and use these assets. We're inside video editor. We're going to hit generate. Again, you can take your time to read the prompt. And what it's going to do um is that it will replace the woman in the first video with our source image and it's going to translate everything she's saying in Chinese from Chinese to English um in a matter of seconds. So let's see how it does. >> Yeah, this is really interesting also just like creating ads and just creating

14:37 content spec in in like a hundred languages right? >> Yeah, it's AB testing at its finest. Yeah. And getting higher conversion rates, just getting cheaper ads because of >> optimizing. Optimizing. Optimizing. >> Yeah. All right. >> There it is. So, what do you think she said? >> She said, "I love you, Serio. My new glasses." >> I don't Let's see. Let's So, we we translated the original video um from from uh Chinese Mandarin. This one's amazing. It's flattering and versatile. Mustave. >> So, you see the wink?

15:23 Let me go back into into the the reference video. >> It feels like she's selling the glasses that I'm wearing back to me. And I want It's so good. She's doing such a good job selling it. I want another pair. That's how good of a job this is doing. >> Look at the wink. Look at the way that she puts her her her hand on her glasses. It's the exact same motion. >> This one's amazing. >> Look at Look at the blur in the camera. Like the the focus. The mo the the the motion. The focus. >> This one's amazing. It's flattering and versatile. Must have. >> Right. Nailed it. >> This one is very interesting. Look at this video. What we're going to do here

16:08 this video, this is an ad. Now, we have a package, right? And this is like traditional just like 3D render. There's no branding in the package. This is meant for like evergreen. Okay. Like a template. You can buy these templates. What if we actually replace that package with this image? So, what are we doing right now? Again, here's a prompt. You can screenshot this. >> We're replacing only the package and keeping everything the same. >> Generate um and you can find any 3D asset out there. You can start um applying texture to all these 3D assets by combining the source reference with

16:55 image references and just literally telling it to hey make sure that you put the the texture from image number one into the 3D render video in image number uh in video uh number two. We could do this with nano banana in images >> and now we're doing this with Cense 2 in videos which is quite insane. So that template was that a was that found on some like a stock video website >> that was entirely generated but you can go into freepic for example I think that they have a bunch of templates like that not quite sure if it's a video template that they have but you can take an image that is an an image template you can turn it into a video and then you can put everything together and then you can create this templated video and then you

17:41 can replace the templates um with your source um references. Let's take a look at this. It didn't do any changes. There you go. >> The logo is completely consistent in and understood like the background that it had to be yellow. Um kept everything the same. >> Is is Cance 2 the best video model to ever exist >> for now? Yes. Yeah. Like >> waiting for Google 4. No, V. Yeah, it's V4. >> Um, but by far, >> uh, it is the best out there in terms of realism, in terms of motion, in terms of quality. Um, they it's only up to 720p

18:30 for now. >> Um, and when they release their 1080p version, um, it's going to be a gamecher for anyone that's creating digital assets. >> Cool. Do Do we have time for a couple more? >> Yeah, we do. So, I want to show you two other use cases that are very interesting that everyone would love. The first one is extending videos. You have a 3-se secondond video, you have a 10-second video, and you want to extend it to 15 more seconds while keeping everything the same. We could not do this before. Um, now Google V3.1 kind of tried, but look at this. We have our

19:18 3 second video here and we don't know what's happening next. We can recreate this entire scene. Here is the prompt. You can screenshot it. You can take a look at it. And then again, we're using our video extender feature. Hit generate. And what it's going to do is that it's going to continue the the actual story line based on what we said in the prompt while keeping everything consistent. This is use case number one of video extension. And there's a different use case for a video extension that would actually fill in the middle of the video. This is extending the last bit of the video. And there's a use case that I'm going to show show you in after we uh explore this one where it's gonna fill in the gap. So, we have two videos and it's

20:04 going to figure out what goes in the middle. Um, which is insane to me. >> Yeah. I mean, if this could do this, this is this is big because this is this has been a pain point for me personally with playing some with some of these models >> like ads. Yeah. >> Yeah. Exactly. With ads. Literally ads >> or just traditional film making doesn't have to be ads. Like there's something that you just you want to have at least three more seconds of that video. Cannot do that. >> Let's take a look at this. So it extended the video from the point where we where the video cut, right? You have a complete you have a different scene and it's the exact same last frame. Um, this is use case number one

20:53 of of uh extending your videos. There's a bunch of others, but there's one last thing I want to show. uh which is AI influencers in lip syncing. This is the best model for you to generate AI influencers and they can do anything you want them to do. Again, as I said, you can screenshot this prompt over here. The prompt is highly specific. This is the source image generated with Nano Banana Pro. um you're going to go and use the asset and the way that um the influencers or avatars lip sync um is simply you prompted to say particular

21:39 things in the prompt you go and say hey she is saying and then um you go and go and say give me a second or she's saying this is what I mean in um what do I call these >> quotation >> in quotation yeah in quotation marks so everything inside quotation marks marks um is what the model or the the the the avatar uh will say. Um very simple natural language. You just tell it what you want it to do and it's going to understand exactly. Um now of course there's ways to prompt things so they look and feel more realistic, especially emotions. Um how to control emotions, how to prompt emotions. You do not prompt emotions by saying, "Hey, the character is sad or the character is happy." You have to describe the muscle

22:26 movements, right? Because just saying character is sad, okay, there's not a lot of control. Like sad, how there's thousands of ways for someone to be sad. Um, but by describing the the the muscle movements, by describing the transition in emotion, transition in tone, um, in in body language, um, it's able to to achieve more, um, realistic results. So, this is what we're going to see here. That's why this is a very long prompt because I'm being very specific with what they are saying because we the aim for this video is so it doesn't look AI. >> Okay. Yeah. >> Give me a second. >> This is what I mean. The way I breathe, the way I talk right after moving, it's all generated inside

23:14 enhancer. >> It's crazy. There's Let me show you. >> I know. I have goosebumps on that one. like that that looked real. >> No, let let me show you another one right here. Um, so this is our source of reference. Let's say that we want to generate ads, right? And we have our product and our product has some sort of text. And again, one of the main flows for other video generators is that the text was usually wrapping or was changing as the video was generating, right? Um, then we have our prompt over here. Again, we're very specific with our prompt, with what they're saying, how they're saying it, how we're structuring the prompt. We're going to hit generate, and then we're going to have her talk about this product that she never tried. Uh because this AI model does not have thoughts or does not

24:00 have taste. She doesn't exist and the product was never sent to her. So that's the beauty of of AI models because you can create a version of yourself if you want or you can create a completely different IP and the brand does not have to send you the actual clothes that would cost them a few bucks to to actually uh send like ship them to you and now multiply that by like thousands of of AI influencers. Um it becomes like very costly. Now the brand can just be like hey can you just place this inside your image with Nano Banana Pro? It's going to keep it very consistent. Can you just generate it with Cense Stew? Or maybe we can do it for you if you want. Um, and there you go. Like unlimited content, very cheap. There it goes. >> Okay. Quick taste test.

24:50 Huh. Wait, that's actually nice. It's not super sweet. It's really clean. I wasn't expecting that. Yeah, I'd drink this. >> Look at Look at the text. Like the text is quite on like spot on. It's not changing. Insane. All right, Serio, this C dance V2, this feels like the best creative model to ever exist. With it being so good, just walk us through quickly how to think about like think, you know, why would we use any other model? Are there any benefits using any other model or as of recording this, should we just make this the default? I think that at some point uh what will happen is the same thing that it did with Nano Banana where it become became the best AI editing image editing model.

25:36 Cense to me seems like it's the best by far. Mhm. >> However, >> and and the reason why it's the best by far is because you can practically you can animate UX UI, you can animate like logos, uh you can place logos within a video, you can do so many things that other models are not capable of and you can generate like very good lip syncing. Um now, of course, some others are very good at other things. Maybe emotion control. Clang 3 does a very good job at that. And there's other models who are fine-tuned so that the images look way more um low fidelity like more more realistic or it doesn't look like they have like the cinematic feel. Cling 3 has a cinematic feel. You

26:23 know you when you when you look at the video you know that it's very good at producing cinematic videos. I'll show you an example of another video model that we fine-tuned inside Enhancer. It's called Enhancer V4. And what this model does uh again it's does it's not the highest fidelity like video model. Um it does not produce like this crazy transitions. It just might not keep the character extremely consistent. It might not have multi-input references but it produces >> Hi guys this is crazy like I am not even real and this is version >> probably cannot do the same thing because it has different type of um color schemes that that it produces kind of different depth u different ways that it treats the background different ways that it treats the subjects and this is

27:08 a different video model that is fine-tuned particularly for this exact use case >> for best talking head video generator >> so I would not say that CEN 2 will replace everything that's out there. Um because it really depends on what you're trying to achieve with the model and and how you are using the model. But I think it's going to be for now the default model to generate and edit videos, especially editing videos. Maybe not video generator, but it's phenomenal and will be the the state-of-the-art video editor out there for any use case really. >> What's the best video generator? >> Well, I mean, for now, seems to be

27:55 Cense, >> right? Exactly. >> Seems to be Cense, but uh >> it sounds like what you're saying is like the daily driver is going to be Cance generation and editing. However, there are some use cases that certain models have a different look, visual look, like you were saying, enhancer v V4 where it's like, >> yeah, you know, I I if I'm trying to go for that look, I might >> just do, you know, use that for like a specific use case. >> And also, it depends on what the again what the user is used to. there's things that the the user really likes um or the creative in this in this case really likes a particular model and they just want to stick with it because it's good enough for what they're doing and >> maybe it's cheap, >> right? Maybe it's faster. Maybe they're

28:42 just producing lowfidelity video for for social media and they don't want to spend like $3 on a 5-second video like Google V3. Um or at least V back back in the days when it was about a three video per uh what is it? Five or eight second clip. Um, >> and again, you people that are using generative tools are not using them just for fun. They are normally using them or monetizing through them. Like they either have some sort of a business, maybe they're a service provider, maybe they're creative um um or maybe they're building their their own app. It's not that they're coming to these platforms and spending all the money without making something back. So of course price matters and depending on the the use case u then

29:28 some models become uh uh more relevant than others. >> Last question before we head out. Uh Adobe is $106 billion company. Not asking for financial advice but what do you think happens to Adobe? I mean they were the leaders in the in the creative suite, right? They they were the they were the go-to for everything for for 20 years more. um you know is is Adobe what happens to Adobe over the next 5 years be your best guess? Uh probably Adobe might require these AI generative tools. Um I think would be a smart move if they do. Uh all enhancer competitors not going to mention them. U maybe they requiring acquire enhancer. I don't

30:13 know. Um but I believe I still believe that Adobe is relevant especially for creative professionals who want way more control who actually want to edit or cut that frame. um who actually want to produce like high fidelity videos that are 8K and and who who again um are more to them than simply a creative director that's just starting out with AI tools. Um I think that every time I produce something with AI, I still have to edit it. It will not produce the perfect output for me. like there there's still there's still like is it is this the post-p production phase that that happens and I believe it

31:01 will always exist and it will there is always going to be a need for this like there's a need for for um digital photography right I believe that in the future most photography is going to be prompted unless there's an event um and there's also a need for polaroids and there's also a need for for for film photography um because those things are are way more technical and while uh I think that AI or technology advances still creatives need to have full control of their outputs and I think that Adobe what they do best is >> Yeah. I mean basically what you're saying is like Adobe is like the place for creative professionals. >> Yeah. and these tools BO3 C dense 2

31:49 things like you know these these models >> they're just the first step right there's it's simply the first step um and there's I believe that there's always going to be a need for like um there's always going to be a need for post editing and Adobe is the app where you do the post- editing it's it's not the the the app where you initially create We create videos every single day with our phones and then we go to Adobe. So we could generate videos every single days with our laptops and phones and then we go to Adobe. Um even even though Adobe now is trying to be the place where you create and also edit and also post-produce >> which is a smart move. Uh however would

32:34 be ideal if for me if they focus on things that actual proc creatives really need and want which is not necessarily generate the content in Adobe but is how to use Adobe tools to have an agent agentic um like feature where it just edits for you like focus more on the post producing than the actual production. >> Totally makes sense to me. Syria, thank you so much for coming on the show. I'm going to include links where you can follow uh CRIO on on social, links to enhancer, and dude, thank you so much for showing us all these different use cases. This was really cool. >> Thank you, Greg. I appreciate it. I appreciate you.