Thank you for being honest about the ones that look weird. For some reason, a lot of KZitemrs are applauding these crappy looking pictures and videos.??? I like the honesty
@theAIsearch
3 ай бұрын
No problem!!
@ArturoEspinosaAldama
2 ай бұрын
If only he had been honest about how slow and/or inefficient this process is, even on a 4090. Look at the stats on his video at 30:30: almost 4 secs per iteration, and the process uses 12x40 iterations per process... that's 1920 secs or 32 minutes for a 7 sec video (sample audio 1). Imagine you want a presenter for a standard 15 minute video. It would take 68 HOURS to generate: almost 3 days. On the cloud he suggests, that's 54USD. You can see that this can mount up pretty fast, and that's without even counting if you have to re-render due to mistakes or whatever. So, this is the problem with channels that want to hype and bring enthusiasm to some technology: they are too biased. 30:30 for the part where he minimally mentions this core problem. This is NOT personal computing: it belongs to huge datacenters consuming hundreds of thousands of watts where developers can manipulate the parameters and see results in real time, the way Microsoft demoed his technology. Imagine: to make it real time, you would need the equivalent computing capacity of 275 of those RTX 4090, plus the infrastructure to keep them running. That's like 137,500 Watts per hour, or a 90 Horse Power, 1.8 cc SOHC engine running at full capacity and burning some 9 gal of gasoline per hour, just so you han have your little window with a face moving at the dance of your mouse and keyboard.
@ArturoEspinosaAldama
2 ай бұрын
@@I.Am.Nobody yeah, for sure as there is a lot of vested interest in saving costs. I personally have a friend who worked for a couple of years in optimizing AI tensors to the current nVidia architecture, using specific numeric types that could best be processed by these new units... but it IS going to take a lot of time, and we should be real about that.
@ihzakarunia2408
3 ай бұрын
Him: "This is a gpu that you and i could easily buy...." (RTX 4090) Me: .........
@NetTubeUser
3 ай бұрын
Because coders only use the latest technologies available, without any prior optimization. For example, there's an optimized version of Stable Diffusion that can use older video cards, not just the latest ones. And the result is the same as with newer video cards. Of course, it is faster with newer video cards, but the result remains the same.
@pixobit5882
3 ай бұрын
Would you rather buy a 4090 for 1.8K USD or a H100 for 28k USD?
@lukeb5584
3 ай бұрын
@@pixobit5882 Neither. My 1080 is just fine until I upgrade my PC. What an absolute waste of time. Reminds me of the initial VR hype.
@roejohntiolengco3938
2 ай бұрын
You can easily buy it if you have the money.
@bigglyguy8429
2 ай бұрын
@@pixobit5882 I bought a 3090, which has the same 24GB of VRAM and a lot cheaper
@simplereport8040
3 ай бұрын
Thanks for the nightmares on that hugginface anime one! 😂 Loved it. I’m trying it to troll my friends tonight after work.
@theAIsearch
3 ай бұрын
Have fun!
@Zuluknob
3 ай бұрын
"realistic" you haven't seen the monsters i have created
@theAIsearch
3 ай бұрын
lol is it some good nightmare fuel?
@Zuluknob
3 ай бұрын
@@theAIsearch yeh, don't add people with teeth showing
@xenn2996
3 ай бұрын
@@theAIsearch Can i install hallo with an external ssd?
@nathanielthomas7718
3 ай бұрын
Yeah… the monsters I created just turned 21 & 18 👹🧌😳
@Zuluknob
3 ай бұрын
@@nathanielthomas7718 Ahh, you downloaded pregnancy by mistake.
@ChristophBackhaus
Ай бұрын
Sounds amazing. This combined with some nice embeddings could make a great conventional bot. Over time you could generate more answers to similar questions and make the conversation sound a lot more natural. I am currently building a coding curse and having an AI Tutor to ask questions that actually looks like a human would be great.
@azhuransmx126
3 ай бұрын
Nice!! Agents will have a face generated image but this Avatar will be animated Not by simple user prompts but in Real Time with Zero Latency by an LLM behind this Avatar and those same *Mimic Outputs Signals* can be used to feed the *Inputs PWM Signals* of electric motors to animate a Fully Autonomous Robotic Physical World Version, with these Physical Avataras performing as the Puppet of these Artificial Neural Networks. That's The *Last Stage* of this tech during the *AGI Incarnation World Event* of 2028... And So The Ray Kurzweil Singularity begins.
@MrCrazyGameGuy
3 ай бұрын
I think I'll give it another 5 months, then look back at how you said "it's the most realistic" and then be like "That looked like shit" lmao
@theAIsearch
3 ай бұрын
yep, that's the world of AI
@munchaking1896
2 ай бұрын
At the begining of the video you should have said it will cost 80c/hr to use it and I would have skipped the video and saved my self 15 minutes.
@GreenHatAnimation
3 ай бұрын
Hey, I'm a new sub! Loved your last vid, watching this one now!
@theAIsearch
3 ай бұрын
Awesome! Thank you!
@TealDreamIneo-ki3kq
3 ай бұрын
Suspect: "I didn't do it." Investigator: "We have video evidence."
@MadsterV
2 ай бұрын
a full confession
@youtubesurfer134
3 ай бұрын
Man now things are really starting to pick up.
@theAIsearch
3 ай бұрын
indeed!
@Seriouslydave
2 ай бұрын
Imagine if they wereopen source and all worked together.
@numbers93
3 ай бұрын
OMG Harry Potter talking portraits here we gooooo
@theAIsearch
3 ай бұрын
😃
@hermannrudas
3 ай бұрын
All the fears you used to have, now have been redrawn !
@theAIsearch
3 ай бұрын
😃
@xenn2996
3 ай бұрын
thanks im gonna use this for my animations
@theAIsearch
3 ай бұрын
😃
@benfrank6520
3 ай бұрын
Im not really sure if i should be happy or terrified that this is closed source. Those who have full access can do insanely good deepfakes. Propaganda will reach a whole new level.
@theAIsearch
3 ай бұрын
this tech can definitely be dangerous. imagine all the forged evidence it can create
@TechnoMageCreator
3 ай бұрын
I went in this panic in February 2023. I realized the internet is on a risk to die. I archived lots of movies, documentaries, lectures, went on eBay and ordered encyclopedias for all fields, just in case. Helped me be more relaxed working with AI and accepting the journey
@randomnameeeeeee
3 ай бұрын
@@theAIsearch I think in court it will probably be not too hard to figure out if it's AI generated, by proffesionals who can examine it (but who knows, maybe people will find a way to make it hard to prove, we'll have to wait and see) But it will have huge consequenses on social media in general Most people already don't read beyond the headlines. So even if it will be debunked as AI generated, the damage will already be done So yeah. The potential of this tech is terrifying
@NoidoDev
3 ай бұрын
It's obvious: People just need to learn that they can't trust such videos.
@randomnameeeeeee
3 ай бұрын
1. The tech is in early stages and developing very quickly. Eventually it will not be obvious at all 2. Many are already fooled by obvious false social media posts.
@darkflux
3 ай бұрын
6:05 watch the old guy's beard spazz out!
@invitia901
3 ай бұрын
Still looks like the video has been dubbed, almost right, but still somewhat wrong
@ghhdgjjfjjggj
3 ай бұрын
If only we had this around during the peak of StarCraft! The custom mods we can make!!
@theAIsearch
3 ай бұрын
😃
@MarcoCholo-iz9js
3 ай бұрын
Now you're thinking
@sirdrakey
3 ай бұрын
Debates this year are going to be wild!😅
@tokugagua2008
2 ай бұрын
Great value as always
@thegoodthebadandtheugly579
3 ай бұрын
This is great for animating drawn images.. 👀
@ListenGRASSHOPPER
3 ай бұрын
Hedras emotions are synced better and lip sync is better most of the time. You're blind. Most of these examples are pretty bad on sync
@AbigailJrney-1
3 ай бұрын
Does Hallo provides it's own audio voices like Hedra, or do you have to upload all the voices yourself?
@theAIsearch
3 ай бұрын
you need to upload
@AbigailJrney-1
3 ай бұрын
@@theAIsearch I see. Ok, thanks!
@djr3386
3 ай бұрын
Thanks for the sharing the video. Is there an app or AI plugin to correct weird AI generated faces?
@theAIsearch
3 ай бұрын
you could try using stable diffusion img2img & inpaint to fix weird parts. are you familiar with how to use stable diffusion?
@djr3386
3 ай бұрын
@@theAIsearch Sorry no. There should be an AI app made specifically for correcting faces and fingers. AI can make other things.
@user-mo6dt9lw7g
2 ай бұрын
We have gone across the uncanny valley
@paulfrancis8836
2 ай бұрын
You've driven me nuts !
@VoltaSlime
Ай бұрын
Mix this with Udio AND BOOM! MAGICO!
@theAIsearch
Ай бұрын
😃
@researchgrouponhealthylivi108
3 ай бұрын
Excellent review and content !
@theAIsearch
3 ай бұрын
Thanks!
@VintageForYou
2 ай бұрын
Is there a script available to set everything up in Windows for Deepfake.🤔
@MaxSMoke777
3 ай бұрын
Nobody's cooked up a little web interface for this? Having to do it all through the command prompt is very basic.
@NeilRoy
3 ай бұрын
This is both amazing, and worrying, as I wonder how this could be abused, especially in politics.
@theAIsearch
3 ай бұрын
I'm sure this will be heavily abused in politics
@williamobrien2382
2 ай бұрын
Am I taking crazy pills or what this thing ran for like two and a half hours and then bottomed out and said it wants to restart now if I just paid for 2 hours of servers?
@Capy_random
3 ай бұрын
Absolutely crazy and beautiful. Imagine a utopia where there are no degenerates hungry for power or malicious intentions. Humanity, being kind, would achieve greatness in such a short time.
@Derpyzilla894
3 ай бұрын
I am confused how this achives that future.... I just want ai gene editing and then boom utopia.... hopefully.
@theAIsearch
3 ай бұрын
@Derpyzilla894 hope we figure out a way to live forever before i die!
@Capy_random
3 ай бұрын
@@Derpyzilla894 It's not about 'image' generation, you need to see further. There are many powerful models out there, probably some really close to AGI, maybe from Anthropic or OpenAI or some national research private labs. The point is, if we were in a utopia, those models would already be out there. But you can't let an AGI roam free with so many mentally unstable people, asking how to create explosives, making deepfakes of people in NSFW contexts; the list goes on. That's why many AIs are so restricted.
@Capy_random
3 ай бұрын
@@theAIsearch soulkiller from cyberpunk 2077? hahaha
@Capy_random
3 ай бұрын
@@Derpyzilla894 It's not about 'image' generation. There are many powerful models out there, probably some really close to AGI, maybe from Anthropic or OpenAI or some national research private labs. The point is, if we were in a utopia, those models would already be out there. But you can't let an AGI roam free with so many mentally unstable people, asking how to create explosives, making deepfakes of people in NSFW contexts; the list goes on. That's why many AIs are so restricted.
@eSKAone-
3 ай бұрын
Dude with high movement and high expression it looks way more convincing
@theAIsearch
3 ай бұрын
agreed. tweaking the settings can make it very natural
@KryzysX
3 ай бұрын
11:27 that's really the most believable
@montereycalifornia
3 ай бұрын
Thank you for the info:)
@theAIsearch
3 ай бұрын
no problem
@Avalon19511
3 ай бұрын
Well I tried this with an actual gradio interface that someone was kind enough to send me the link and for right now it's just too slow and when I say slow I mean really slow, for a 2 minute video it was going on 5 hours when I finally shut it down. I hope at some point they optimize it because it looks interesting
@h3video1ravenshadow
2 ай бұрын
when installing install ps1 I get errors it seems like things arent installing right but it says its done at the bottom in pwrshell and there is no torch even when using venv
@h3video1ravenshadow
2 ай бұрын
no module named torch
@Avalon19511
2 ай бұрын
Can't get it to work in comfy either, not sure why all the nodes are in green but when I generate it just flashes to the end and does nothing?
@BeardofBeesPool
3 ай бұрын
reface had something similar to hello a couple years ago. I think they removed it.
@h3video1ravenshadow
12 күн бұрын
how to get this to work locally with GUI on windows for long clips of audio if you can figure it out please provide a full walkthrough step by step I have the hello and hello 2 portable but cant get them working and hugging face doesn't work or doesn't support long audio perhaps ran locally but in a browser or in a portable app what I have I haven't been able to figure out but seems to be for using it locally with gui
@h3video1ravenshadow
12 күн бұрын
have hallo*
@Darknight_84930
3 ай бұрын
Hm..... More and more I look at these new models I feel like someone is definitely gonna slap a model into bot and let em learn continuous and wallah we made the first ever humanoid.
@skullwund8676
3 ай бұрын
i don't understand why this exist and what is the porpouse of this
@FriscoFatseas
3 ай бұрын
good coverage appreciate it
@theAIsearch
3 ай бұрын
No problem 👍
@xrayban2
3 ай бұрын
Maybe AI will take care of the Earth after wiping us from it ...
@theAIsearch
3 ай бұрын
It'll do a much better job than us
@MuradBeybalaev
3 ай бұрын
That doesn't look good for anime. Everyone knows animes speak in low framerate.
@wangte27
3 ай бұрын
Thanks. Is there an equivalent that's available for Android phone
@theAIsearch
3 ай бұрын
unfortunately you need a gpu. or you could run it on hugging face on your phone
@budekins542
3 ай бұрын
Thanks
@theAIsearch
3 ай бұрын
my pleasure!
@PavelReyes
3 ай бұрын
After all that, and I still get ModuleNotFoundError: No module named 'torch'
@musicbro8225
3 ай бұрын
lol, this is literally putting words into other peoples mouths! The legitimate uses for this are virtually zero. All it proves to me is developers of AI have lost the plot, if they ever 'had' the plot in the first place...
@TOILETPOOL
3 ай бұрын
What if there wearing a mask?
@hbasm3271
3 ай бұрын
I have CUDA version 6 with 512mb ram. Can it work on CPU only
@MrJohnnyseven
3 ай бұрын
Probably yes....I have an AI video face changer...on GPU it takes maybe an hour, but on CPU at least 5+ hours so yes it probably will but expect a long wait.
@9A4GEMilan
3 ай бұрын
Does not work: ModuleNotFoundError: No module named 'triton'
@budekins542
3 ай бұрын
Can someone please explain something in plain English. .if I increase the RAM of my computer with an external hard drive will I be able to install HALLO?!
@theAIsearch
3 ай бұрын
no, you need VRAM which is your GPU's memory. increasing just RAM won't work
@rayb3000
2 ай бұрын
so much blinking and the lips are out of sync with the words
@Entity303GB
3 ай бұрын
finallyy
@theAIsearch
3 ай бұрын
😃
@Entity303GB
3 ай бұрын
@@theAIsearch I love your Videos about new AI tools 🫶🏻
@gingerversestudios
3 ай бұрын
gooona try it hope it works
@derbybOyzZ
3 ай бұрын
Taking 10 mins for a 10 second generation is too long. If people want to have chatbots with an image of their face it needs to not be video and instead something else.
@atozgametesting8595
3 ай бұрын
Can I use it on phone?
@theAIsearch
3 ай бұрын
maybe if you use huggingface. you'll need to pay for compute tho
@ArcanePath360
3 ай бұрын
"A GPU which you or I could easily buy" ... if you don't care about eating and heating for the rest of the year and want to dip into your mortgage.
@theAIsearch
3 ай бұрын
lol just gotta live in your parents basement, sell your car, eat costco free samples every day, and save up for a few months
@LydianMelody
3 ай бұрын
Might wanna cut out the racial slur from the movie clip or whatever it is at 5:35 …
@theAIsearch
3 ай бұрын
Thanks! I'm not sure what he's saying but I'll trim it out just in case
@LydianMelody
3 ай бұрын
@@theAIsearch I figured it was something like that, no worries. Keep up the great work
@SS801.
3 ай бұрын
Ty 👍
@theAIsearch
3 ай бұрын
no problem
@Lorentz_Factor
3 ай бұрын
How is sad talker doing these days ? Here's the thing that was out a year and a half ago
@DaaHela
3 ай бұрын
Microsoft one is the best tbh
@potts995
3 ай бұрын
I feel like companies could provide a layer of security by making users generate profile-style images only, kinda like how thispersondoesnotexist does, for example. I could also see a lot of potential if we were easily allowed to save and reuse those same faces via face swapping, rather than having to rely on a new image with a new face each time.
@philjohnson725
Ай бұрын
Since you don't account for possible problems, thank you. I'm stuck and done. Don't know what to do further. Guess this is not for me then. Cheers.
@TheMCDStudio
3 ай бұрын
There is a ComfyUI node for this.
@theAIsearch
3 ай бұрын
Thanks for sharing!
@Avalon19511
3 ай бұрын
I keep getting a import error for Hallo, any thoughts?
@Avalon19511
3 ай бұрын
Something is odd, finally got the node to appear all nodes are in the green, but when I hit Que the Hallo node flashes, then the preview node but nothing happens, is your install working?
@theAIsearch
3 ай бұрын
@@Avalon19511 i haven't tried the comfyui fork. hopefully someone else can help you out here
@thesystemera
3 ай бұрын
Can it run real-time?
@theAIsearch
3 ай бұрын
nope
@thesystemera
3 ай бұрын
@@theAIsearch that’s a shame.
@thesystemera
3 ай бұрын
@@theAIsearch check out my next to zero latency Amanda. Wanted to give her a face.
If this tech was more matured, cheating could be possible in the presidential debate 2024
@KingZero69
3 ай бұрын
bro YAPPING too much… turned a 8 minute video in 33 minutes … 😂
@matthew.m.stevick
3 ай бұрын
Be nicer
@KingZero69
3 ай бұрын
@@matthew.m.stevick ur mom 🤡
@matthew.m.stevick
3 ай бұрын
@@KingZero69😣
@coreC..
3 ай бұрын
Very cool. But fyi: i do not want to upload Elon Musk. I want to move him, to /dev/null
@winargilang3243
2 ай бұрын
.\venv\Scripts\activate
@Roxana_Official
3 ай бұрын
not good enough to use
@TPCDAZ
3 ай бұрын
It's as good as what you feed it. You put in crap you'll get crap out. GET BETTER
@ArturoEspinosaAldama
3 ай бұрын
I have followed the instructions and started a test, but had to interrupt. The time this takes to produce video is so much, even on top-end hardware, that it is not practical for production. This should be mentioned on the video. Also, renting a computer on the cloud, even at 8 cents per hour or whatever would amount to quite a sum for even a modest production, and would take too long. This is just not practical, except for producing a video for the views and getting revenue from the ads. Will not suscribe. I have done some calculations to show how slow and/or inefficient this process is, even on a 4090. Look at the stats on his video at 30:30: almost 4 secs per iteration, and the process uses 12x40 iterations per process... that's 1920 secs or 32 minutes for a 7 sec video (sample audio 1). Imagine you want a presenter for a standard 15 minute video. It would take 68 HOURS to generate: almost 3 days. On the cloud he suggests, that's 54USD. You can see that this can mount up pretty fast, and that's without even counting if you have to re-render due to mistakes or whatever. So, this is the problem with channels that want to hype and bring enthusiasm to some technology: they are too biased. 30:30 for the part where he minimally mentions this core problem. This is NOT personal computing: it belongs to huge datacenters consuming hundreds of thousands of watts where developers can manipulate the parameters and see results in real time, the way Microsoft demoed his technology. Imagine: to make it real time, you would need the equivalent computing capacity of 275 of those RTX 4090, plus the infrastructure to keep them running. That's like 137,500 Watts per hour, or a 90 Horse Power, 1.8 cc SOHC engine running at full capacity and burning some 9 gal of gasoline per hour, just so you han have your little window with a face moving at the dance of your mouse and keyboard.
@DaaSaa-lt3is
19 күн бұрын
😅
@user-fo9ce3hr5h
4 күн бұрын
is there any model for comfy ui or another software that atlease sync lips and a little face or eyes with faster time? i am searching for a model i give an image + audio file and it give me 1 video. local pc.
@gynowhere
3 ай бұрын
In a sequence that feel natural: VASA>EMO>Hallo>Hedra
@BestieKing
3 ай бұрын
AI's growing really fast!
@theAIsearch
3 ай бұрын
😃
@NetTubeUser
3 ай бұрын
Yes, but the rending is still pretty robotic and emotionless.
@kippwieland6464
3 ай бұрын
Like a malignant tumor.
@TrueHelpTV
2 ай бұрын
delete this =D
@rainbowgaming8441
2 ай бұрын
its not there maybe in another 80 years lol it cant do hands and feet
@MaverickM1
3 ай бұрын
Looks very unnatural tbh, I am wondering why people hyping this ai shit all the time
@sherpya
3 ай бұрын
it says English only but you played a demo clip with Italian audio
@theAIsearch
3 ай бұрын
good point. it'll work if the language consists of mostly english syllables
@the_one_and_carpool
Сағат бұрын
this isnt deep faking its it only does minimum. deepfakes are full body deepfacelab is the best choice
@Yogsoggeth
3 ай бұрын
I've been using Vidnoz to do deep fakes of streamers and send the video to them in discord. Never fails to get a laugh! You can make them say what ever you want? Ever wanted to be a VIP or a mod in chat? Now you can make a fake video of the streamer promoting you! KEKW
@danielornstein300
3 ай бұрын
finaly i can imagine my father and sister as if they were alive again 😭😭
@theAIsearch
3 ай бұрын
Interesting use case 🥲
@Agret
2 ай бұрын
If you have voice recordings of them you can use other ai tool to generate clips of them talking to use with their photos
@danielornstein300
2 ай бұрын
@@Agret im glad i haved them saved long voice note i kept when he at hospital .i cant believe it worth more than i know
@thetailgunner777
2 ай бұрын
wait until we get the deep fake mother in laws
@RefRed_King
2 ай бұрын
@@danielornstein300 dam thats deep maybe in the future you can replace a robot with your dad
@JoeyBlogs007
3 ай бұрын
Extremely disturbing. Organised crime field day.
@user-fo9ce3hr5h
4 күн бұрын
amazing, how we can make the time less with set low setting? is there any way? my gpu is 4070 super 12gb, it took 10-15 min.
@Scorpiove
3 ай бұрын
Hallo can be installed easily with pinokio
@bigdaddy5303
3 ай бұрын
Ug 10 mins with a 4090. Here i was hoping for real timr
@TheMCDStudio
3 ай бұрын
Pinokio has a one click script install for this.
@theAIsearch
3 ай бұрын
Thanks for sharing!
@holdthetruthhostage
3 ай бұрын
The problem with Hedra minute limit face morphs
@witness1013
3 ай бұрын
Lol - it looks like garbage. The Bob Marley and Morgan Freeman one is complete trash. I love how excited people get for digital fidgets - even if they suck they promote them like some amazing advancement - instead of the 3rd rate tool w/ absolutely zero use case - it is.
@ig33ku
Ай бұрын
Since AMD can now use Cuda wouldn't AMD cards be able to be used?
@BlackPlasmaUGC
3 ай бұрын
1001 like lol
@theAIsearch
3 ай бұрын
😃
@studiosoho
3 ай бұрын
Did you know that TikTok already had this "effect" before all this AI hype, right?
@johnny5805
21 күн бұрын
Too much faff required for too little usefulness.
@rgarlinyc
3 ай бұрын
As for"laughing and coughing" @21:05 -->. they did say to use "Only English", so we shouldn't be surprised that it failed here.
@Zenless260
3 ай бұрын
lol not downloable, and censored, dying as soon as a real open source releases. thats probably in one week lmao.
@OfficialInformationMedia
3 ай бұрын
this release is going to force the others to make it free. with tech is who gets their version out first. especially if its free.
@marcoantonionunezcosinga7828
3 ай бұрын
Thanks for the video, it seems that the program needs to improve the times
@brunolopes7311
2 ай бұрын
the ones who doenst know this technology will be fooled no many times..
@MujaidinilTalebbanoNapoletano
2 ай бұрын
not work... torch is not present for me... can you help please?
@theAIsearch
2 ай бұрын
hmm it should install torch when you run install.ps1. maybe try running that again
Пікірлер: 296