Deepmind seems to be really really competent. I don't think that $100+ billion valuation for OpenAI will last for long. At this point OpenAI has nothing that is ahead of its competition.
@@darshank8748 thanks for the opportunity to clarify. i don’t think it’s that simple. it takes a team of fantastic researchers to accomplish this feat, which deepmind does have. but… having youtube helps
It's crazy how a lot of people can't tell some of the AI videos are fake.I seen a AI video of an old asian monk, talking about spiritual stuff,and people were thanking him! Saying thanks for the inspiration.Were in trouble.
Great video Matt! Can’t wait for these video tools to become better and more accessible! Both models seem to have their strengths and weaknesses, but VEO really seems to be a step up from SORA in general!
Wow, Veo2 looks like a game-changer! The hands-on demonstration really shows how powerful and intuitive this AI video tool is. It seems like it could save so much time while still delivering high-quality content. Thanks for giving us such a detailed review, Matt! Do you think Veo2 can be used for different types of content, like educational videos or even gaming content, or is it more suited for specific niches?
@budekins542yes it still requires hard work of editing, connecting each clip together, and making consistent characters. I made a simple, 3.3 minute music video of a merman story using free, 5 sec clips, took me 7 days to finish editing.
If you consider that this is still in the early stages of development, the videos are truly impressive. Especially when you take a closer look at some details-did you notice how well the water physics are executed in the first video with the dog in the pool? That’s remarkable! Depicting water with real physical properties is probably one of the toughest challenges for VFX artists to recreate. I’m not talking about the appearance but the animation-how it interacts with objects or other states. That’s really incredible! I assume that by the middle of next year at the latest, we won’t be able to distinguish AI-generated videos from reality anymore. And then, all video platforms will likely be flooded with such content. You’ll really need to be careful about what you believe. Ideally, all such videos should come with a mandatory label (AI Generated).
Check out my merman music video, i used free 5- secs hailuo clips on those, the water looks so natural and the movements... hailuo has done that already.
I used minimax in my merman music video, look at the water movements. Minimax is far better than veo. Those are just from free 5 secs clips stitched togethr.
@kayeaivideos never heard of that but will have a closer look but to your explonation this tool seems specificly constructed towards Special Effects i guess?
@@micromedia26 Minimax isn’t specifically for special effects but has better physics, which makes it great for realistic water movements. I haven’t tried Veo, but I’ve already made good water effects with Minimax, so I think it’s better for that.
@@micromedia26 Minimax isn’t specifically focused on special effects, but I’ve found it handles realistic water physics really well. I’ve been able to create smooth, natural water movements that I think are just as good, if not better, than some newer tools like Veo. While Veo is getting a lot of attention right now, Minimax is still great for tasks like this. Just wanted to share my experience with a tool that might not be the latest but still performs really well for specific effects!
The dog surfing and bouncing around on two surfboards is GREAT! One day the random uncanny elements will be programmed out and it will not be fun anymore.
Great surprise seeing actual tests that aren't cherry-picked and really showcased the AI video agenerators success to failure ratio. Despite the video title, the contents show something pretty good. Not flipping amazing compared to the competition. I prefer reality to hype, so really liked this video.
If you watch 11:34 carefully veo actually kept the title of the DVD cover consistent through to the next shot. Zoom into the lettering and logo placement, it is the same. Veo seems like the future. I am dying to use it.
I feel like the coherency and physical understanding of these models will just steadily improve, so what I'm most anticipating is *length.* I can't wait for the day when we're not limited to 10-seconds-or-less on generations, required to string them together in hopes it keeps temporal consistency across generations. I want to be able to prompt for, say, a 4 to 5 minute clip, minimum (ideally with multiple coherent shots, maybe even multiple scenes).
Take a look at today's movies/shows. Often the scenes last far less than a minute with the camera view changing often. if the producers continue that design, then there won't be as much need for very long videos. Coherency is key in that case.
Just imagine in the future: you will have favorite movies that nobody else has ever heard of. Custom designed for your specific viewing pleasures. Man, I'm never going to leave home.
So your favorite streaming channel just cancelled your favorite show when you were really wanting to see what will happen next season. Soon you'll be able to generate the next season yourself.
Matt I’ve been watching your videos and really enjoy them. I think the AI tech is mind blowing. The quality of this video is scary good. As the google guy said this tech is the worst we’ll ever have. Given the short attention span people have it really concerns me the potential that is coming to fruition to be able to manipulate masses very easily. Maybe it’s always been there but this new tech is going to make it even easier. Not as pumped about the future as I was. Keep up the good work.
it's incredible where we're at!! 2025 will be a crazy year. You can kind of see how the models "imagine" when it comes to how they place the items prompted in the video.
I have been critical of Google's handling of gen AI in the past, but even I'll say they've been hitting it out of the park lately. Looking at Veo2, it completely demolishes Sora in almost every way. Sora has been a giant letdown in so many ways. Very happy to see others swoop in and spank OpenAI because it's what they deserve at this point.
I need to point out that the "Rubix Cubes" in the Veo videos are actually speed cubes (of a different brand, not Rubix). Speed cubes are deigned with a nylon core, trimmed edges, and a lubricant that allows the pieces to stretch and slide past each other EXACTLY as you see it in the videos. However, Matt is correct about the colors changing/not changing properly. If you ever watch professional speed cubists, they move so fast you can't really see the colors moving, so it would be really hard to have those in training data.
Been waiting for ever on the waitlist for V1 even!!! :( I've had image FX since the beginning! This looks amazing but I wonder what Googles resistance to allowing us to use our own image references is. I Cannot wait for this and everything AI brings to 2025!!
Can you test to see if Veo can do text / logos with video background? Sample prompt: Create a text effect for 'RIVER' in a flowing, current-like font. Inside the text, water rushes, fish swim, and rocks protrude. Occasional leaves float by. Dynamic river simulation with smooth current and water flow effects.
Telling the difference in these examples is quite easy - *good quality* real video is high fidelity, meaning lots of detail. AI video can't generate that much detail yet. AI video seems like really well upscaled 720p at best (or even less). If you watch on a small phone screen, it's much harder to notice. But watching on a bigger screen...
Is Meta winning in all domains compared to OpenAi? Bought Gemini today. An other day of testing claud-o1 pro-Gemini-co-pilot today. An other fantastic video, Matt! Sending our engineers to you platform. How are the Prompt Awards going? 🥇 🥈 🥉
Impressive. But it feels like many people forget that the most important element is missing: acting. The ability to make characters speak and express themselves believably. I wonder how far away we are from achieving that?
I was hoping it was mode advanced than SORA.. I agree it beats SORA but still Minimax is much better in animation things like Hamster, Unicorn or anything non-human.. Here we see VEO2 is just making still frames..
To generate video from image, veo 2 allow only the use of images generated by imagen3, which very constraining at least for me. I will not use it until it can generate videos from any image.
Seems like they have real trouble with multiple noteworthy things happening at once. You can have interactions in the foreground in an interesting setting, but you can't have interesting background actions, too.
I got all the others right, but I thought the rhino video was real because of the bouncing donger, I didn't think the AI would add that part. The fighter jet was only obviously AI because I understand what the instruments should look like, and it looks like I'm having a stroke trying to read any of the gauges.
Feels like we are hitting the limit of text to videos using this kind of architecture. It's getting better but mostly visually, the actual actions are messed up. They need to be able to ground them into real physics motion.
It's cool but I don't think you'll ever be able to actually upload an image and then have it animated due to everybody being so afraid of copyright. Great demo though Matt!
how about something like this: "loving squid sets standards behind universal hypersquare without apostrophe, except invasive quarterly mobster taste triumverates the holocene transistor, invasion is illiterate ominvore poliburo with a frown diamond". How would it respond to this?
Veo2 seems an entirely different beast to Sora. Vastly better with the physics from what we're seeing in these early demo's.
That’s what having access to the biggest video platform on the planet gets ya.
Deepmind seems to be really really competent. I don't think that $100+ billion valuation for OpenAI will last for long. At this point OpenAI has nothing that is ahead of its competition.
@@RyluRocky Good point
@@johnzach2057 2025 is going to be the most interesting yet for AI Video progress
@@johnzach2057l mean, openai and all the companies have something cooking that they cant release it yet because of laws or that are not ready yet
This video saved me $200 per month. Thank you!
do you even think google's would be $200? i bet you it'll be > $500
@@hqcart1 lol i'm using it free wdym? you didnt join the waitlist 3 months ago???
@@hqcart1 500$? are yall trippin?
@@OversampledSecretLab sora is 200 for a TURBO mode, Veo2 is a full model that is 5x bigger, what were you expecting, a $5 monthly sub???
@@hqcart1 Good news: there are more than two AI video platforms to choose from. Anyway, how much do you wanna bet?
google owns youtube. i imagined their video models would outclass the competition
💯
It’s not that simple.
@@darshank8748 thanks for the opportunity to clarify. i don’t think it’s that simple. it takes a team of fantastic researchers to accomplish this feat, which deepmind does have. but… having youtube helps
In few years everything about film production will change forever
You mean like one year lol
@@TheoBrownMusic7 could be, every time we think its gonna be this long, they bring things earlier than that. AI progress is accelerated accelerated
There will be riots and protests also
It Is here already.
@@gRosh08 at this point its nowhere near actual film production lvl.
It's crazy how a lot of people can't tell some of the AI videos are fake.I seen a AI video of an old asian monk, talking about spiritual stuff,and people were thanking him! Saying thanks for the inspiration.Were in trouble.
yo .... if this is the new journalism, Matt gets a 5 stars. No cap
I've been using sora. Absolutely insane
Great video Matt! Can’t wait for these video tools to become better and more accessible! Both models seem to have their strengths and weaknesses, but VEO really seems to be a step up from SORA in general!
Love your crowd sourced demo approach Matt!
Very amazing. Sora lost but is still the OG in the business. Cant imagine what we are able to do in 20 years
20 years? at the rate thing are advancing, we would probably have full-length movie generators in two years.
Wow, Veo2 looks like a game-changer! The hands-on demonstration really shows how powerful and intuitive this AI video tool is. It seems like it could save so much time while still delivering high-quality content. Thanks for giving us such a detailed review, Matt! Do you think Veo2 can be used for different types of content, like educational videos or even gaming content, or is it more suited for specific niches?
So long Hollywood. Hello Indy movies.
Wont always be like that
@budekins542almost every film is shot in a series of many different camera shots that last a few seconds
@budekins542yes it still requires hard work of editing, connecting each clip together, and making consistent characters. I made a simple, 3.3 minute music video of a merman story using free, 5 sec clips, took me 7 days to finish editing.
Guys. A couple of seconds is a scene. Many scenes are a movie
Yep!
If you consider that this is still in the early stages of development, the videos are truly impressive. Especially when you take a closer look at some details-did you notice how well the water physics are executed in the first video with the dog in the pool? That’s remarkable! Depicting water with real physical properties is probably one of the toughest challenges for VFX artists to recreate. I’m not talking about the appearance but the animation-how it interacts with objects or other states. That’s really incredible!
I assume that by the middle of next year at the latest, we won’t be able to distinguish AI-generated videos from reality anymore. And then, all video platforms will likely be flooded with such content. You’ll really need to be careful about what you believe. Ideally, all such videos should come with a mandatory label (AI Generated).
Check out my merman music video, i used free 5- secs hailuo clips on those, the water looks so natural and the movements... hailuo has done that already.
I used minimax in my merman music video, look at the water movements. Minimax is far better than veo. Those are just from free 5 secs clips stitched togethr.
@kayeaivideos never heard of that but will have a closer look but to your explonation this tool seems specificly constructed towards Special Effects i guess?
@@micromedia26 Minimax isn’t specifically for special effects but has better physics, which makes it great for realistic water movements. I haven’t tried Veo, but I’ve already made good water effects with Minimax, so I think it’s better for that.
@@micromedia26 Minimax isn’t specifically focused on special effects, but I’ve found it handles realistic water physics really well. I’ve been able to create smooth, natural water movements that I think are just as good, if not better, than some newer tools like Veo. While Veo is getting a lot of attention right now, Minimax is still great for tasks like this. Just wanted to share my experience with a tool that might not be the latest but still performs really well for specific effects!
WOW...great Info Matt...jealous LOL...been waiting for access to this on Google for a while... Hardly wait.!!! Cheers and great report!!!
i love how you push technology and apps - pls keep it up - VEO definitely currently kills it
The dog surfing and bouncing around on two surfboards is GREAT! One day the random uncanny elements will be programmed out and it will not be fun anymore.
Having TH-cam videos to train it with worked!!
This was really interesting and a fun format, thanks!
Great surprise seeing actual tests that aren't cherry-picked and really showcased the AI video agenerators success to failure ratio. Despite the video title, the contents show something pretty good. Not flipping amazing compared to the competition. I prefer reality to hype, so really liked this video.
Thank you for not click-baiting something that actually stunned the industry
I dream of creating series like The Sopranos or Breaking Bad... all with AI... or making my own documentaries. It's just so incredible.
If you watch 11:34 carefully veo actually kept the title of the DVD cover consistent through to the next shot. Zoom into the lettering and logo placement, it is the same. Veo seems like the future. I am dying to use it.
Thanks a lot - love your channel
Thank you for the link. I've loved their ImageFX
I feel like the coherency and physical understanding of these models will just steadily improve, so what I'm most anticipating is *length.* I can't wait for the day when we're not limited to 10-seconds-or-less on generations, required to string them together in hopes it keeps temporal consistency across generations. I want to be able to prompt for, say, a 4 to 5 minute clip, minimum (ideally with multiple coherent shots, maybe even multiple scenes).
Take a look at today's movies/shows. Often the scenes last far less than a minute with the camera view changing often. if the producers continue that design, then there won't be as much need for very long videos. Coherency is key in that case.
I joined Google's Video FX waiting list a year ago and then Veo 1 and now Veo 2 and have never received anything.
Just imagine in the future: you will have favorite movies that nobody else has ever heard of.
Custom designed for your specific viewing pleasures.
Man, I'm never going to leave home.
wait until VR is so real you'll design your own complete worlds to explore...or 1 billion others too.
So your favorite streaming channel just cancelled your favorite show when you were really wanting to see what will happen next season. Soon you'll be able to generate the next season yourself.
Do you see the downside of that way of thinking?
@@jeffkingston67 Oh yeah, it will probably be the end of humanity as we know it.
Buuuut...
@@adamruuth5562 Haha fair enough!
Matt I’ve been watching your videos and really enjoy them. I think the AI tech is mind blowing. The quality of this video is scary good. As the google guy said this tech is the worst we’ll ever have. Given the short attention span people have it really concerns me the potential that is coming to fruition to be able to manipulate masses very easily. Maybe it’s always been there but this new tech is going to make it even easier. Not as pumped about the future as I was. Keep up the good work.
It is exactly the same like with LLMs - closer to the training data (more generic stuff you are asking for), the better results, and vice versa.
it's incredible where we're at!! 2025 will be a crazy year. You can kind of see how the models "imagine" when it comes to how they place the items prompted in the video.
I have been critical of Google's handling of gen AI in the past, but even I'll say they've been hitting it out of the park lately. Looking at Veo2, it completely demolishes Sora in almost every way. Sora has been a giant letdown in so many ways. Very happy to see others swoop in and spank OpenAI because it's what they deserve at this point.
We waited soo long for SORA and Google Veo2 has killed it!
You should try the same prompts with Kling 1.6 It's much better than 1.5 and 1.0 it consistently follows my prompts and understands anatomy better.
Woah, just what a year 2024 has been
For sure syria is free too
I need to point out that the "Rubix Cubes" in the Veo videos are actually speed cubes (of a different brand, not Rubix). Speed cubes are deigned with a nylon core, trimmed edges, and a lubricant that allows the pieces to stretch and slide past each other EXACTLY as you see it in the videos. However, Matt is correct about the colors changing/not changing properly. If you ever watch professional speed cubists, they move so fast you can't really see the colors moving, so it would be really hard to have those in training data.
Nice!
Cool!
I didn't guess them all correctly.
Maybe it was because i viewed in Mobile, but guessing wrong, means they are doing well.
Been waiting for ever on the waitlist for V1 even!!! :( I've had image FX since the beginning! This looks amazing but I wonder what Googles resistance to allowing us to use our own image references is.
I Cannot wait for this and everything AI brings to 2025!!
The ability to make easy revisions to this at minimal credit cost is going to be the bane of this entire process.
Can you test to see if Veo can do text / logos with video background?
Sample prompt:
Create a text effect for 'RIVER' in a flowing, current-like font. Inside the text, water rushes, fish swim, and rocks protrude. Occasional leaves float by. Dynamic river simulation with smooth current and water flow effects.
Showrunner would be great using Veo 2.
Meanwhile, Midjourney is trying to get hands right!
Thanks as always, Matt. 💯
This is groundbreaking❤
Regular video has not gotten to real yet, but this AI model is getting closer to the HDi Video we have now. Still cool.
I like the tech for fixing and helping editors and film makers… not just generating the ENTIRE thing.
We need open source videos generation (or maybe Chinese) that doesnt have so many limits. But wow these are amazing.
The new patron of the arts is your own creativity.
Telling the difference in these examples is quite easy - *good quality* real video is high fidelity, meaning lots of detail. AI video can't generate that much detail yet. AI video seems like really well upscaled 720p at best (or even less). If you watch on a small phone screen, it's much harder to notice. But watching on a bigger screen...
crazy, i signed up and in waiting list. I dont know what im doing but hell yeah
"Dog jumping from water like a dolphin" would have been cool.
Hi Matt, I applied a few days ago, how do I know if I have access ? Did they email you ?
I'm just crossing my fingers and hoping that it'll be reasonably priced.
How about adding the URL you are referring to to the video description??
Is Meta winning in all domains compared to OpenAi? Bought Gemini today. An other day of testing claud-o1 pro-Gemini-co-pilot today. An other fantastic video, Matt! Sending our engineers to you platform. How are the Prompt Awards going? 🥇 🥈 🥉
Corpo wars are bloody EPIC!
Crazy , this is So good
can we use Google Image FX images that we generate for commercial purposes?
Veo 2 seems to be video generation's DALL-E 2 moment. The next couple of years are gonna be wild.
Impressive. But it feels like many people forget that the most important element is missing: acting. The ability to make characters speak and express themselves believably. I wonder how far away we are from achieving that?
Krea AI is still the King when it comes to the Most Valuable System to Rent to use
Not available in France yet 😔
I was hoping it was mode advanced than SORA.. I agree it beats SORA but still Minimax is much better in animation things like Hamster, Unicorn or anything non-human.. Here we see VEO2 is just making still frames..
To generate video from image, veo 2 allow only the use of images generated by imagen3, which very constraining at least for me. I will not use it until it can generate videos from any image.
Our AI doesn’t just solve problems; it creates opportunities 💫
Seems like they have real trouble with multiple noteworthy things happening at once. You can have interactions in the foreground in an interesting setting, but you can't have interesting background actions, too.
Can I use VPN because it is not available in my country
Thank you 🙏🏽
Matt:join the waitlist, Me: Waitlist? Oh, wait I live in Germany it's not available here 🙄
I got all the others right, but I thought the rhino video was real because of the bouncing donger, I didn't think the AI would add that part. The fighter jet was only obviously AI because I understand what the instruments should look like, and it looks like I'm having a stroke trying to read any of the gauges.
Feels like we are hitting the limit of text to videos using this kind of architecture. It's getting better but mostly visually, the actual actions are messed up. They need to be able to ground them into real physics motion.
Good morning
Cant wait and at least we know its gonna be a "Sora Killer"
Veo and imageFX solved most of the hand/fingers issue
Nice video
Can it generate videos of UFOs over New Jersey?
What do you think of the latest imagen text to image generator?
Also keep in mind this is V2 and the Sora we have access to is V1 with V2 on the way... Hard to compare the two
matt flexing his new google buddies
Insaneeee
NICE!
Wait.... I couldn't tell on two of those 4 ai vids
It's cool but I don't think you'll ever be able to actually upload an image and then have it animated due to everybody being so afraid of copyright. Great demo though Matt!
Chinese will not care
One day im absolutely blown away at the progress ai has made and then the next Im let down
how about something like this:
"loving squid sets standards behind universal hypersquare without apostrophe, except invasive quarterly mobster taste triumverates the holocene transistor, invasion is illiterate ominvore poliburo with a frown diamond".
How would it respond to this?
Veo might be the future, but will it take jobs from creatives? Or will it open new doors?
Pretty sure the bollywood prompt was meant to have the bears doing the bollywood dance
I have a question. Do you know of an AI video generator with very limited guardrails capable of generating videos of celebrities?
thank u for pronouncing Veo correctly, veo = "I see " in spanish.
I'm not signing up , they never follow through. Can't wait until it's TRULY AVAILABLE
looking at the progress it will be in next 5 years we will have a proper finale for GOT
image-fx as well
Not in UK :(
@budekins542 yes but there is no UK on the list :(
Sora is so sad 😂
It’s unfair comparison. 1-prompt structure is different for VEO and SORA. 2- SORA rendering at 480p uses a smaller model.
Please create yoga videos which other video generators struggle so much to create.
Minimax Hailuo is just as good and already available
Upload them in a Google Drive and make it available for everyone
Still a very long way to go but the progress is impressive.
Odd and very wierd prompts are most difficult to any AI becouse lack of reference material.
you need to use separators..
with out them , ai is one thought.