Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

We're still limited by the 6 second limit so it's bouncing here Soon that'll be 12 seconds though "Subject reference image" makes talking videos more real and interesting like this below Obviously still with a fakey AI voice but that'll also improve

@levelsio

959,023 subscribers

119,226 просмотров • 1 год назад •via X (Twitter)

Образование Наука и технологии Юмор

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Dave

Dave1 год назад

Can you edit multiple angles of the same subject, in the same setting together?

Фото профиля The Rundown AI

The Rundown AI2 лет назад

AI won't replace you, but a person using AI will. Join 500,000+ readers and learn how to use AI in just 5 minutes a day (for free).

Фото профиля Brian Skinner

Brian Skinner1 год назад

Look out for more UGC videos giving product reviews!

Фото профиля A Happy Penguin

A Happy Penguin1 год назад

What did you use for the lipsync?

Фото профиля @levelsio

@levelsio1 год назад

I AM ALSO AN INVESTOR

Фото профиля Zachary Allen

Zachary Allen1 год назад

What are you using for the lip retalking?

Фото профиля @levelsio

@levelsio1 год назад

I AM ALSO AN INVESTOR

Фото профиля Esteban

Esteban1 год назад

There is one more limit, the camera control. I been trying to get the camera to remain static, yet it seem impossible to get stable results.

Фото профиля @levelsio

@levelsio1 год назад

Usually you can prompt like fixed camera

Фото профиля steve ike

steve ike1 год назад

To get around the 6 second limit I’ve been considering if a “cut” to a different camera angle could be used, similar to how in movies they often cut to different cameras. ffmpeg them together and then overlay the audio to the longer clip.

Похожие видео

Yeah yeah, those AI videos of high-octane action sequences are real neato but the real test will be if anyone can create a scene with AI that's more interesting to watch than this still shot of a woman just talking to a camera in front of a concrete wall.

Yeah yeah, those AI videos of high-octane action sequences are real neato but the real test will be if anyone can create a scene with AI that's more interesting to watch than this still shot of a woman just talking to a camera in front of a concrete wall.

Dudley Newright

22,282 просмотров • 7 месяцев назад

After a few weeks of Flow Matching, I still think it's bonkers. But also so so clever. I wish more of ML was like this, instead of the typical "let's add an extra layer here and there and see what happens". Link below.

After a few weeks of Flow Matching, I still think it's bonkers. But also so so clever. I wish more of ML was like this, instead of the typical "let's add an extra layer here and there and see what happens". Link below.

Julia Turc

48,204 просмотров • 5 месяцев назад

AI Bedtimestory You can soon create personal audio/image stories like this from a single input ⚡️ It's been more than 2 years since we launched Bedtimestory. Some +100.000 hyper personal stories later, and here we are. But it's just not limited to bedtimestories... 🧵

AI Bedtimestory You can soon create personal audio/image stories like this from a single input ⚡️ It's been more than 2 years since we launched Bedtimestory. Some +100.000 hyper personal stories later, and here we are. But it's just not limited to bedtimestories... 🧵

Linus ✦ Ekenstam

14,029 просмотров • 2 лет назад

Anthropic CEO, Dario Amodei: "we might be 6-12 months away from models doing all of what software engineers do end-to-end" We're approaching a feedback loop where AI builds better AI But the loop isn't fully closed yet, chip manufacturing and training time still limit speed

Anthropic CEO, Dario Amodei: "we might be 6-12 months away from models doing all of what software engineers do end-to-end" We're approaching a feedback loop where AI builds better AI But the loop isn't fully closed yet, chip manufacturing and training time still limit speed

Haider.

744,185 просмотров • 8 месяцев назад

lando: "if the pace can be that strong on a day like today, i'm confident we can still win more races this year but we have certain areas we have to improve on.. we'll still work hard but the team deserve a good break and so do i"

lando: "if the pace can be that strong on a day like today, i'm confident we can still win more races this year but we have certain areas we have to improve on.. we'll still work hard but the team deserve a good break and so do i"

ray

15,408 просмотров • 2 месяцев назад

✨ First AI talking video made from within Photo AI with the new [ 💬 Make talking video ] interface AI photo -> AI video -> AI lipsync -> AI captions Obviously not very passable yet, BUT it's a start and with voice and lipsync models improving so fast I think it'll be passable in 3-6 months One thing is severely missing is background sounds which I didn't add here manually just to show the state of things, is there any good TTS API that DOES have bg noise? Captions are by CapCut, but it'd be nice to be able to do that in-app with Photo AI too, not sure where to start with that though Again cool thing of this vs HeyGen is it has no limits to where you wanna place yourself or your model, the source is just a prompted AI photo in Photo AI that becomes a talking video with 2 clicks

✨ First AI talking video made from within Photo AI with the new [ 💬 Make talking video ] interface AI photo -> AI video -> AI lipsync -> AI captions Obviously not very passable yet, BUT it's a start and with voice and lipsync models improving so fast I think it'll be passable in 3-6 months One thing is severely missing is background sounds which I didn't add here manually just to show the state of things, is there any good TTS API that DOES have bg noise? Captions are by CapCut, but it'd be nice to be able to do that in-app with Photo AI too, not sure where to start with that though Again cool thing of this vs HeyGen is it has no limits to where you wanna place yourself or your model, the source is just a prompted AI photo in Photo AI that becomes a talking video with 2 clicks

@levelsio

200,632 просмотров • 1 год назад

Two years have passed,but I still rewatch TBF Ss1 over and over again. Just like this scene, Tuesday July 23, 2024 was the day I held my breath and cheered them on with all my heart❤️ As the host said "It's a kissing scene that'll go down in human history"💋👬 #Dai_Shun #DaiShun

Two years have passed,but I still rewatch TBF Ss1 over and over again. Just like this scene, Tuesday July 23, 2024 was the day I held my breath and cheered them on with all my heart❤️ As the host said "It's a kissing scene that'll go down in human history"💋👬 #Dai_Shun #DaiShun

LiveHappyLife

336,414 просмотров • 2 месяцев назад

👑 KING RASKO GREY was probably over the top by Punchestown but still pulled out enough to back up his Cheltenham Festival success. 👍 He's a real interesting one - already a 6-yo and looks like a chaser but might be stuck a little bit trip-wise.

👑 KING RASKO GREY was probably over the top by Punchestown but still pulled out enough to back up his Cheltenham Festival success. 👍 He's a real interesting one - already a 6-yo and looks like a chaser but might be stuck a little bit trip-wise.

Road To Cheltenham

43,195 просмотров • 1 месяц назад

Software may be starting to show early signs of life but I still think the “hard” side of AI has the cleaner lane for 2026 and probably most of 2027. We're nowhere close to done with the physical AI buildout since compute demand is still ahead of supply, power is becoming the bottleneck and every layer of AI infrastructure still needs more capacity. I own some software names but I still see this as more of an oversold bounce than a true leadership rotation away from the companies building the AI infrastructure layer. Software probably becomes a cleaner leadership group once inference costs fall, enterprise AI budgets expand and AI features start flowing through margins but that still feels more like a 2027 story to me.

Software may be starting to show early signs of life but I still think the “hard” side of AI has the cleaner lane for 2026 and probably most of 2027. We're nowhere close to done with the physical AI buildout since compute demand is still ahead of supply, power is becoming the bottleneck and every layer of AI infrastructure still needs more capacity. I own some software names but I still see this as more of an oversold bounce than a true leadership rotation away from the companies building the AI infrastructure layer. Software probably becomes a cleaner leadership group once inference costs fall, enterprise AI budgets expand and AI features start flowing through margins but that still feels more like a 2027 story to me.

Shay Boloor

122,716 просмотров • 4 месяцев назад

Just saw this, it's pretty crazy to see what people do with AI these days 😯 I'm sure this'll improve a lot in the upcoming years, but even with Seedance 2.0 you can clearly see the Mortal Kombat in here... 😂🤣 All of this is still nothing to what we produce internally though 👍

Just saw this, it's pretty crazy to see what people do with AI these days 😯 I'm sure this'll improve a lot in the upcoming years, but even with Seedance 2.0 you can clearly see the Mortal Kombat in here... 😂🤣 All of this is still nothing to what we produce internally though 👍

thomasmahler

33,754 просмотров • 6 месяцев назад

‼️⚡️TRUMP: We'll give them the right to make Patriots. We'll show 'em how to do it. It's very complex, actually. Most, most countries couldn't do that. But this is a very ingenious group. This way you can't complain that we're not giving 'em enough. We said, "Make 'em yourself." We haven't informed the company of that yet, but that'll work out all right. “I think we're gonna be talking about today. I just… a little birdie told me this about the fact that we'll give them the right to make Patriots. We'll show 'em how to do it. It's very complex, actually. But it's, you'll figure out the complexity quickly. And we're talking about that, and we'll, the company that makes them, which is building now 4 plants, you know, all of our companies will be able to do this in two to three months. If you order a Patriot now, you have to wait a long time for 'em. Same thing with Tomahawks. We have a lot of certain equipment, but with the, they call it the elite equipment, and you don't need elite equipment necessarily for a war. But, so one of the things we're gonna be talking about is you'll, we're gonna give a license to you to make Patriots. That's pretty cool, right? This way you can't complain that we're not giving 'em enough. We said, "Make 'em yourself." We haven't informed the company of that yet, but that'll, that'll work out all right. You know, they, I'm sure they'll be thrilled, but you know, they'll be able to do it. You'll be able to figure that out. Most, most countries couldn't do that. No. If I said that to most countries, they wouldn't know what I'm talking about. But this is a very ingenious group. And what I like about that, it's a defensive, it's a defensive situation as opposed to an offensive. But I think one of the things you might want to be talking about is that. That's what I heard. Little birdie told me that” - American President on Wednesday, July 8, 2026, in Ankara, Turkey, during the NATO summit.

‼️⚡️TRUMP: We'll give them the right to make Patriots. We'll show 'em how to do it. It's very complex, actually. Most, most countries couldn't do that. But this is a very ingenious group. This way you can't complain that we're not giving 'em enough. We said, "Make 'em yourself." We haven't informed the company of that yet, but that'll work out all right. “I think we're gonna be talking about today. I just… a little birdie told me this about the fact that we'll give them the right to make Patriots. We'll show 'em how to do it. It's very complex, actually. But it's, you'll figure out the complexity quickly. And we're talking about that, and we'll, the company that makes them, which is building now 4 plants, you know, all of our companies will be able to do this in two to three months. If you order a Patriot now, you have to wait a long time for 'em. Same thing with Tomahawks. We have a lot of certain equipment, but with the, they call it the elite equipment, and you don't need elite equipment necessarily for a war. But, so one of the things we're gonna be talking about is you'll, we're gonna give a license to you to make Patriots. That's pretty cool, right? This way you can't complain that we're not giving 'em enough. We said, "Make 'em yourself." We haven't informed the company of that yet, but that'll, that'll work out all right. You know, they, I'm sure they'll be thrilled, but you know, they'll be able to do it. You'll be able to figure that out. Most, most countries couldn't do that. No. If I said that to most countries, they wouldn't know what I'm talking about. But this is a very ingenious group. And what I like about that, it's a defensive, it's a defensive situation as opposed to an offensive. But I think one of the things you might want to be talking about is that. That's what I heard. Little birdie told me that” - American President on Wednesday, July 8, 2026, in Ankara, Turkey, during the NATO summit.

Kateryna Lisunova

59,296 просмотров • 2 месяцев назад

Kling's new video model came out today I think we can finally say AI video is "good enough" for basic purposes like YouTube videos etc It's hard to notice it's AI for most people Which means the next frontier isn't quality but it's cost because it's still too expensive to generate AI videos now, like $0.50-$2.50 for 5 seconds Once we'll see cost dropping to $0.05 per second and then everyone will be using this to make YouTube videos etc Especially good already for documentary-style YouTubers who need lots of B-rolls

Kling's new video model came out today I think we can finally say AI video is "good enough" for basic purposes like YouTube videos etc It's hard to notice it's AI for most people Which means the next frontier isn't quality but it's cost because it's still too expensive to generate AI videos now, like $0.50-$2.50 for 5 seconds Once we'll see cost dropping to $0.05 per second and then everyone will be using this to make YouTube videos etc Especially good already for documentary-style YouTubers who need lots of B-rolls

@levelsio

238,745 просмотров • 1 год назад

Full clip here! It's a day late and most of this talk is no longer relevant due to the Sharks getting their butts kicked (after I said it would be a good game lol). And talk is also super Sharks-centric. But might still be interesting for some to watch!

Full clip here! It's a day late and most of this talk is no longer relevant due to the Sharks getting their butts kicked (after I said it would be a good game lol). And talk is also super Sharks-centric. But might still be interesting for some to watch!

Patrick Bacon

44,407 просмотров • 5 месяцев назад

🐹: “It's been 10 years since I last had a dream. I tried to stay grounded in reality, and be kind to those who are kind to me. I've lived by these beliefs, and I still stay true to them. Though it'd be nice to accomplish more goals, if I remain faithful to the present, I believe that'll naturally lead to greater things in the future. I want to be grateful for what I have now, and enjoy the present moment, while still making efforts to move forward.”

🐹: “It's been 10 years since I last had a dream. I tried to stay grounded in reality, and be kind to those who are kind to me. I've lived by these beliefs, and I still stay true to them. Though it'd be nice to accomplish more goals, if I remain faithful to the present, I believe that'll naturally lead to greater things in the future. I want to be grateful for what I have now, and enjoy the present moment, while still making efforts to move forward.”

jin files

92,324 просмотров • 1 год назад