Microsoft's AI Lip Sync. MIND. BLOWN!
Vložit
- čas přidán 22. 05. 2024
- In this video, AI News for Narrative Filmmakers...
- Midjourney announces "Personalisation" and Video
- Leonardo.ai launches new Style Reference feature
- Microsoft's MINDBLOWING new AI Lip Sync tool
- LTX Studio Launches in New York
- Astonishingly beautiful work by @BinaryFrameProductions
00:00 Coming up...
00:24 Midjourney announces "Personalisation" and Video
01:50 Leonardo.ai launches new Style Reference feature
02:00 Microsoft's MINDBLOWING new AI Lip Sync tool
04:13 LTX Studio Launches in New York
05:31 Astonishingly beautiful work by Binary Frame Productions
Midjourney Personalisation - Reported in The Decoder: #midjourney #midjourneyai
the-decoder.com/midjourney-ge...
Microsoft Lip Sync White Paper: #Vasa-1
www.microsoft.com/en-us/resea...
Binary Frame Productions: @BinaryFrameProductions
• #aifilmmaking #airevol...
#haiperai #haiper - Jak na to + styl
"Don't look at the camera" toggle button. 😁
EXACTLY!!!!
They are almost there. Since I found your channel last month, it looks like you're looking for the same exact thing I am looking for, along with a lot of other story tellers. I've been keeping an eye on you becase I know once this THING we are looking for in the AI world to come together finally comes together, you'll be the one who talks about it. I just need the consistant character formula + proper lip syncing + enviroment control. I feel Eleven Labs has the voice creation down with the ability to not only create voices, but now use that voice with your own voice controlling it. Exciting times.
Absolutely! I’m right there with you!! No matter how I try though, I can’t handle the whole spectrum of voices for the characters in my movie (even with audio tools like ElevenLabs), so I’ll still need actors help for now.
@HaydnRushworth-Filmmaker I've noticed this as well. It takes a lot of effort for me to read a few lines into Eleven Labs, then have that converted as a female voice (I'm male) but have it _not_ sound like me to an extent because of my natural inflections and speech patterns.
@@PhilAndersonOutside agree entirely. We still need a female voice actor for authentic female inflections and delivery.
Great video. Thanks for the helpful info❤❤
Hey, no problem, thanks for watching :-)
I was rooting for EMO but VASA 1 just incredibly sophisticated .
*Microsoft and major AI authorities waiting for perfect digital signature system. And I think we need that.
That’s a really good point. If there’s a solid system in place for digital signatures and some kind of traceability, then it allows Microsoft (in theory) to offload liability into the creator. Job done. Hands washed (so to speak).
Love your videos so much! Can you make a tutorial video on FlexClip’s AI tools? Really looking forward to that!🥰
Thanks very much, really appreciate the support. 😁
All these lip-sync platforms give us square examples like this Microsoft one (but also the EMO platform, that was also promising a while back) god forbid that they don't give filmmakers some aspect ratio options, like 16:9. I'm wondering when we can finally get our hands on these lip-sync features.
Absolutely. I think the hopeful thing is that there seems to be a race between multiple teams to introduce lip sync products, so this is where, ultimately, a free market economy and the influence of market demand should lead to worthwhile tools.
To be really useful, considering your "beautiful girl" example, the AI should ask the user questions to narrow down what is sought.
Agree entirely. The ideal project-wide settings will be selected from drop down lists and check boxes as well as free-text descriptions. As it happens, I finally got access to the Beta version of LTX Studio and it has all of those, it’s genuinely really impressive. I’m literally editing a long, “first impressions” video about it right now.
GAAHH!!!!
I understand your frustration with img2img. I lost all my battles trying to make developers to understand that models should be trained looking in all directions, but I gave up about a year ago…..now, there are some open source AI models where you can control the gaze direction, but you’ll need a coder to create an API to use them. Annoyingly enough, the model is being used but several free and paid apps, but only to redirect the gaze to the camera. But the same model can do whatever you want with the eyes direction. Other than that, don’t waste your breath because there’s no way around in the matter…..even Sora has the same issue…..typos by iOS.
That just adds insult to injury, but it’s good to know that the ability is clearly already available. We now need enough serious filmmakers to ask for it, then one of these AI video teams will spot an opportunity to get ahead and implement it in the next version of their tool.
The future is going to be absolutely incredible. Future as in, early 2025.
Absolutely, and this is the right time to be catching the wave and developing skills so that we reach the limits of the tech sooner rather than later. Then, as new developments emerge, we’ll be better prepared to mow the most of them with a shorter learning curve and an established workflow.
@HaydnRushworth-Filmmaker I agree 100%. I think it's a mistake for someone to wait for Sora, Stability, etc. to come out with their video, or wait for anything.
The smart thing is to use what is out there now, even if you produce junk with it that you wouldn't show your best friend. This builds knowledge, it builds a foundation that you can build upon when future AI portals and apps release.
This is why I do not consider myself an AI artist, or "expert", no matter what I learn. I am a "user" or _power user._
@@PhilAndersonOutside I like that distinction, although it might interest you to know that the difference between an amateur and a professional is just a single penny. As soon as somebody pays you anything, you become, in that instant, by definition, a professional, or in other words, somebody who does something as a profession. An amateur, by contrast, does something because they love it. Literally, that's it. When you look at the background of the work amateur, it comes from French / Latin amare, or to love. It literally translates as a motivation of love, not money.
@@HaydnRushworth-Filmmaker I guess I'm. a professional then!
I often consider someone a "professional" when they are earning their primary income doing something. Then again, if someone is unemployed, and makes $.01 selling an AI creation, this technically makes them a professional I suppose!
To be honest, I love doing this too.
@@PhilAndersonOutside of course. Bear in mind that you could be earning $1million per year, but if your lifestyle is costing you $1.1million per year you'd still be in debt every year by another $100k.
AI generated content is the worst best idea.
😄 ain’t that the truth.