Hedra looks cool. I'm going to try it out. I have your "Live Portrait" song stuck in my head now. Over and over and over. Somebody help me. AAAAAAAAAAAAH!
You at the end were reducing the retargeting eyes and mouth values, trying to lower them but you had the option to retarget both at 'off' you must turn it on. A great video and result in the end.
Hendra is clearly easier and took far less time to achieve great results. Even after tweakig the hair is still partially stuck w Live Portrait. Im sold - Hendra.
Good video, been working on a movie for a while but options for character face talk animations it was no good but now with things like hedra I can finally do dialogue conversations correctly.
So do not waste time remixing or re-generating the static image to make the model look in certain directions, etc... Hedra still considers your prompt in final video
Amazing video and tech, thank you for demonstrating how it works, there is so much stuff coming out and just imagine what it will be like in another year. Wicked.
I would say the two can not be compared to each other. I have a few hours of audio (and more being created all the time) for bio's and story telling for various guilds I am in... AI being a hobby of mine. I have an image of the story teller who tells these tales. It should be easy to just feed in the audio and the image to get a talking avatar... after all we had Crazy talk 8 back in 2019 that did just that (though recently retrying it was depressing) Sadly the ones that can do this (sadtalker? sadtalking? i forget the name, abandoned a fair few months ago. EchoMimic, new and has promise but couldnt get it set up(waiting on the comfyui nodes, which could be a while) there was another one whose name escapes me where you had to email for the models. Hydra... so low res and limited to 30 minutes, the sub prices are insane for a hobby too**edit sub prices were the Toking heads site, another Hydra one**) All the other methods, like live portrait need a video to drive them.... thats a problem in my situation, I could spend hours lipsyncing to the Scribe to make the video but that will slow the workflow down drastically and will turn my hobby into work lol. Searching for a way to do this brings up a lot of videos like yours, searching alternatives to Hydra also brings up videos like this..... its frustrating as the two softwares end results are the same but the input needed is vastly different...and I feel like I am starting to rant lol so will leave it at that.
@@DaveTheAIMad no worries. I feel ya. I face the same frustrations as I play with all of these toys. But we’re in such an early stage of this, I think we’re forgetting what a miracle all of this is, just as it is. Just a little patience and I’m sure we’ll all have the tools we want.
@BobDoyleMedia been using suno to create amusing songs for the guilds I'm in and I often wonder what what the tech will be like in 10 years time. I mean I grew up with spectrums and tape loading... now we can have a website create a song from our lyrics!
I see the headphones in your video and the green screen bleed is affecting the hair... have you noticed a difference in the quality of the eye movement if you record yourself without glasses on...?
Not sure why, but Hedra cannot be used in Illinois where I do live. There are only 2 other states that this software cannot be used. Is it that terrible to use this software when the company flagging three restricted states. I mean how bad can it be to use this software. I don't know why you never mention this in any of your videos about the check boxes. Anyway, off to look for other similar types of AI software.
Ok, here goes.. I've been a professional 3D modeler since just about the beginning - It's really a grind and always has been - I've tried all these AI tools - and as cool as they are, and as much as I wish they'd deliver pro standard results - they don't. In 3D model land, Blender, Maya, unbranded tools and others you build or import a close "replica" and then apply the "skin material" that can be manipulated to the "N'th" degree. It really doesn't take much longer than fine tuning these AI tools.. (And the work you do live on your hard-drive, no sharing - EVER. Yes the learning curve is slow - but it's getting better. It's the POST editing that fails in AI production - you cant fiddle with the end render.. I'll keep hoping for AI - but it has a long ways to go.. Thank you - for showing us all this new tech - it really does help us see how to get things done more efficiently..
@@theno.1idea938 I totally agree that we often tend to overcomplicate tasks that can already be done by other solutions in the effort of teaching AI to do it. But that’s part of the process and I do believe it will get exactly where we all want to go… Whatever the hell that is.
Hey Bob! New subscriber and loving your work. I am a poet who needs *free* software that can produce my own reading and delivery of my work in other voices - can you help please?
im late, know it, as a late advice, just make sure the head size of your avatar is the same size of your video char. once its done most of the problems will be fixed.
Bob do you think wearing eye glasses might cause problems as your source video? This issue with the hair as in, the edge around the head/hair that is not being affected, kinda leads me to believe it is just pushing pixels, which is kinda cheap-ish. You would think AI could separate the model character from the background completely and manipulate characters more freely. Is there a setting for the influence range? So you can expand the influence of movement slightly beyond the edge of characters boundary
@@axistiltproductions That particular setting I haven’t seen, which would be great. It’s early yet. Watch for a slew of phone apps with this feature…for pay. Seems to always be the way. That’s why I like looking for the open source stuff.
@@BobDoyleMedia Hey Bob...hru. I’m producing a Vacation Bible School series for 6 - 13 yoa... And Udio does not follow directions as well as wanted... Very challenging to pull up, for example, Children’s Gospel Choir... etc
@@BobDoyleMedia Hey Bob...hru. I’m producing a Vacation Bible School series for 6 - 13 yoa... And Udio does not follow directions as well as wanted... Very challenging to pull up, for example, Children’s Gospel Choir... etc sooooo. ... essentially, I’ve been able to produce each one of my intended tracks... with adult vocals
Hey tech bro's! Give us this functionality for SINGLE IMAGE as "drivers". It would revolutionize the way we tweak around with expressions and emotions on our image gens. Simply find an image (not a video) of an expression and let that tweak your target face.
![[DOKKAN BATTLE] Worldwide Campaign Announcement Video Part 2!](http://i.ytimg.com/vi/JpT5Voak6WA/mqdefault.jpg)
Hedra looks cool. I'm going to try it out. I have your "Live Portrait" song stuck in my head now. Over and over and over. Somebody help me. AAAAAAAAAAAAH!
You at the end were reducing the retargeting eyes and mouth values, trying to lower them but you had the option to retarget both at 'off' you must turn it on. A great video and result in the end.
Hendra is clearly easier and took far less time to achieve great results. Even after tweakig the hair is still partially stuck w Live Portrait. Im sold - Hendra.
It tears too much, Hedra far outclasses this
Good video, been working on a movie for a while but options for character face talk animations it was no good but now with things like hedra I can finally do dialogue conversations correctly.
So do not waste time remixing or re-generating the static image to make the model look in certain directions, etc... Hedra still considers your prompt in final video
Live Portrait is above my pay grade!
*Fantastic* comparison video. Thank you! 💫
Amazing video and tech, thank you for demonstrating how it works, there is so much stuff coming out and just imagine what it will be like in another year. Wicked.
Been using video leap since 2013, love the cap cut too
Those are also my go-to video apps!
You’re incorrect about live portrait, not doing live animation from a WebCam, it most certainly can but you have to run it through comfyui.
@@evolutionsfake It will do it in real time? If so, that’s great! I’d love to get that workflow and feature it here!
Has anyone figured out a way to improve the quality on Hedra? I have tried numerous upscalers.
Increase the scale of the cropper for live portrait. you can capture full hair, hats, animal ears... etc.
@@aivideos322 excellent! Thanks!
Hedra is Awesome!
Awesome compare vid brah
@@thewebstylist Thank you so much!
I would say the two can not be compared to each other.
I have a few hours of audio (and more being created all the time) for bio's and story telling for various guilds I am in... AI being a hobby of mine. I have an image of the story teller who tells these tales.
It should be easy to just feed in the audio and the image to get a talking avatar... after all we had Crazy talk 8 back in 2019 that did just that (though recently retrying it was depressing)
Sadly the ones that can do this (sadtalker? sadtalking? i forget the name, abandoned a fair few months ago. EchoMimic, new and has promise but couldnt get it set up(waiting on the comfyui nodes, which could be a while) there was another one whose name escapes me where you had to email for the models. Hydra... so low res and limited to 30 minutes, the sub prices are insane for a hobby too**edit sub prices were the Toking heads site, another Hydra one**)
All the other methods, like live portrait need a video to drive them.... thats a problem in my situation, I could spend hours lipsyncing to the Scribe to make the video but that will slow the workflow down drastically and will turn my hobby into work lol.
Searching for a way to do this brings up a lot of videos like yours, searching alternatives to Hydra also brings up videos like this..... its frustrating as the two softwares end results are the same but the input needed is vastly different...and I feel like I am starting to rant lol so will leave it at that.
@@DaveTheAIMad no worries. I feel ya. I face the same frustrations as I play with all of these toys. But we’re in such an early stage of this, I think we’re forgetting what a miracle all of this is, just as it is. Just a little patience and I’m sure we’ll all have the tools we want.
@BobDoyleMedia been using suno to create amusing songs for the guilds I'm in and I often wonder what what the tech will be like in 10 years time.
I mean I grew up with spectrums and tape loading... now we can have a website create a song from our lyrics!
I see the headphones in your video and the green screen bleed is affecting the hair... have you noticed a difference in the quality of the eye movement if you record yourself without glasses on...?
I think you would make a very good Max Headroom.😉
Not sure why, but Hedra cannot be used in Illinois where I do live. There are only 2 other states that this software cannot be used.
Is it that terrible to use this software when the company flagging three restricted states. I mean how bad can it be to use this software.
I don't know why you never mention this in any of your videos about the check boxes.
Anyway, off to look for other similar types of AI software.
The only problem is if I need something besides 512 x 512… I work in anamorphic aspect ratios
Ok, here goes.. I've been a professional 3D modeler since just about the beginning - It's really a grind and always has been - I've tried all these AI tools - and as cool as they are, and as much as I wish they'd deliver pro standard results - they don't. In 3D model land, Blender, Maya, unbranded tools and others you build or import a close "replica" and then apply the "skin material" that can be manipulated to the "N'th" degree. It really doesn't take much longer than fine tuning these AI tools.. (And the work you do live on your hard-drive, no sharing - EVER. Yes the learning curve is slow - but it's getting better. It's the POST editing that fails in AI production - you cant fiddle with the end render.. I'll keep hoping for AI - but it has a long ways to go.. Thank you - for showing us all this new tech - it really does help us see how to get things done more efficiently..
@@theno.1idea938 I totally agree that we often tend to overcomplicate tasks that can already be done by other solutions in the effort of teaching AI to do it. But that’s part of the process and I do believe it will get exactly where we all want to go… Whatever the hell that is.
Hey Bob! New subscriber and loving your work. I am a poet who needs *free* software that can produce my own reading and delivery of my work in other voices - can you help please?
Live portrait is on Pinokio. That's how I installed it.
The lip sync on this video seems off (audio ahead of video) so I thought you generated the talking head, too 😀
Hi, thanks for video. Which of them give higher resolution?
@@Sean43322 LivePortrait for now.
@@BobDoyleMedia Thanks
Cool video.
Do you have the comfyUI workflow somewhere?
im late, know it, as a late advice, just make sure the head size of your avatar is the same size of your video char.
once its done most of the problems will be fixed.
Yep, that was the lesson I learned making this. I've had amazing results since then!
I wish hedra team allows 3-4 min video generation (paid option is also ok to me)
@@thebrownboy1453 They will.
Yes, I have to edit together 50 Hedra clips for a full production. Yikes! I also use 11Labs voices for the characters.
Bob do you think wearing eye glasses might cause problems as your source video?
This issue with the hair as in, the edge around the head/hair that is not being affected, kinda leads me to believe it is just pushing pixels, which is kinda cheap-ish. You would think AI could separate the model character from the background completely and manipulate characters more freely. Is there a setting for the influence range? So you can expand the influence of movement slightly beyond the edge of characters boundary
@@axistiltproductions That particular setting I haven’t seen, which would be great. It’s early yet. Watch for a slew of phone apps with this feature…for pay. Seems to always be the way.
That’s why I like looking for the open source stuff.
Glasses could definitely make a difference, but mostly when you're too close to the camera...it distorts the already existing distortion even more.
Yo Mr. Bob !
Do you have a feature on audio production w/ children library?
@@MochaMediaStoryteller can you clarify more what you’re looking for?
@@BobDoyleMedia Hey Bob...hru. I’m producing a Vacation Bible School series for 6 - 13 yoa... And Udio does not follow directions as well as wanted... Very challenging to pull up, for example, Children’s Gospel Choir... etc
@@BobDoyleMedia sooooo. ... essentially, I’ve been able to produce each one of my intended tracks... with adult vocals
@@BobDoyleMedia ?
@@BobDoyleMedia Hey Bob...hru. I’m producing a Vacation Bible School series for 6 - 13 yoa... And Udio does not follow directions as well as wanted... Very challenging to pull up, for example, Children’s Gospel Choir... etc
sooooo. ... essentially, I’ve been able to produce each one of my intended tracks... with adult vocals
Hey tech bro's!
Give us this functionality for SINGLE IMAGE as "drivers".
It would revolutionize the way we tweak around with expressions and emotions on our image gens. Simply find an image (not a video) of an expression and let that tweak your target face.
Salute, I appreciate the videos. What is the audio clip upload time limit per clip for Live Portrait and Hedra? Peace
30 seconds on free. 1-4 minutes on the paid plans.
So which is better?
Anyone else have a jittery or shaky video output?
hello mate! :D
thts stpd why only comfyui plzx plz we want it use separately or use it inside A1111 ???
Hair always look weird with these programs… Almost there!
🎵🎹🎶 💃 OpenAI My Sugar Papi by PEACHY da WHUUPi on RUclips NOW.
Hey competition coming guys ! Using Hedra for close ups
🎵🎹🎶 💃 OpenAI My Sugar Papi by PEACHY da WHUUPi on RUclips NOW.
Hey competition coming guys ! Used HEDRA IMMEDIATDLY,
you are out of sync