Animated Portraits with HeyGen from ANY image

No video

Animated Portraits with HeyGen from ANY image

Рет қаралды 19,775

Күн бұрын

Check out HeyGen here: www.heygen.com...
TalkingPhoto Discord Bot - www.heygen.com...
ChatGPT Plugin - www.heygen.com...
FREE Prompt styles here:
/ sebs-hilis-79649068
Support me on Patreon to get access to unique perks! / sebastiankamph
Chat with me in our community discord: / discord
My Weekly AI Art Challenges • Let's AI Paint - Weekl...
My Stable diffusion workflow to Perfect Images • Revealing my Workflow ...
ControlNet tutorial and install guide • NEW ControlNet for Sta...
Famous Scenes Remade by ControlNet AI • Famous Scenes Remade b...
LIVE Pose in Stable Diffusion • LIVE Pose in Stable Di...
Control Lights in Stable Diffusion • Control Light in AI Im...
Ultimate Stable diffusion guide • Stable diffusion tutor...
Inpainting Tutorial - Stable Diffusion • Inpainting Tutorial - ...
The Rise of AI Art: A Creative Revolution • The Rise of AI Art - A...
7 Secrets to writing with ChatGPT (Don't tell your boss!) • 7 Secrets in ChatGPT (...
Ultimate Animation guide in Stable diffusion • Stable diffusion anima...
Dreambooth tutorial for Stable diffusion • Dreambooth tutorial fo...
5 tricks you're not using in Stable diffusion • Top 5 Stable diffusion...
Avoid these 7 mistakes in Stable diffusion • Don't make these 7 mis...
How to ChatGPT. ChatGPT explained in 1 minute • How to ChatGPT? Chat G...
This is Adobe Firefly. AI For Professionals • This Is Adobe Firefly....
Adobe Firefly Tutorial • Adobe Firefly Tutorial...
ChatGPT Playlist • ChatGPT

Пікірлер: 72

@jonescrusher1 Жыл бұрын

Possibly the driest delivery of a one-liner i've ever heard, great work.

@tozmark2 Жыл бұрын

Free option for Automatic1111 Sad talker extension

@ClashMafia Жыл бұрын

I can't make blink and head movements accurate

@Nutronic Жыл бұрын

Does it add a voice

@sino1449 Жыл бұрын

How to download?

@FictionFrontiers Жыл бұрын

Someone will soon make an open-source alternative!

@vannoo67 Жыл бұрын

There are already is. SadTalker can do this with a supplied image and audio. The only difference is that you would need to use a TTS to produce the audio as a separate step. I wasn't enormously impressed with HeyGen's TTS, I've heard much better.

@helix8847 Жыл бұрын

@@vannoo67 Yeah exactly. Already better out there, this is sadly one of the reasons AI content will start to get repeititve as so many are doing the same thing but different name now.

@Gh0sty.14 Жыл бұрын

@@vannoo67 What would you say is the best free TTS to use with SadTalker?

@vannoo67 Жыл бұрын

@@Gh0sty.14 Its not free, but the best one I've seen is ElevenLabs Prime Voice AI. Along with the pre-baked voices, you can train your own

@CheckTheWiki Жыл бұрын

Yeah anytime I see something exciting like this I don't bother because there will usually be a free open source version within a month that isn't restricting what I can create or selling my data. It's not worth it getting in on these things early.

@weirdscix Жыл бұрын

I think all sponsored videos should have that in the title so we can avoid them if we want to .

@nicopixus Жыл бұрын

Im waiting for a A1111 extension to do that.

@niatro Жыл бұрын

SadTalker has already a extension in A1111 my friend

@nicopixus Жыл бұрын

@@niatro thx

@minimalfun Жыл бұрын

That is pretty amazing!

@sebastiankamph Жыл бұрын

Thank you! Cheers! 😊

@ToddMikosh 11 ай бұрын

I love avatars with mustaches!

@GrocksterRox Жыл бұрын

SadTalker isn't as fluid re: video, but it's free, I bet other options will be coming out soon in the future too

@ElHongoVerde Жыл бұрын

I will be honest with you. I really laughed a lot at the jokes this time... Always great content. Thanks for the video! And I think there's only a year from now (or maybe less) to have great AI avatars or realistic animated images with only a couple of prompts or even with just a 2d image from SD.

@sebastiankamph Жыл бұрын

Haha, good to hear that! In a year, we'll be seeing some cool stuff for sure.

@blackvx Жыл бұрын

It's pretty cool, even for the jokes!😊👍 Thanks for this

@sebastiankamph Жыл бұрын

Glad you liked it! I had fun putting the intro together 😁

@popeye175 Жыл бұрын

nightmare fuel. thank you

@sebastiankamph Жыл бұрын

😂

@iXzenoS Жыл бұрын

HeyGen (and all these animated avatar apps in general) are simply WAY too expensive for such a saturated market while only being limited to a video duration of like under 5 min also isn’t really useful or practical for anybody who wants to create tutorials, reviews and any full content. They don’t even offer a lifetime deal which is a dealbreaker IMO. I’d pass until they significantly lower prices and a lifetime deal is offered at least temporarily.

@EarthKoed Жыл бұрын

No big saas company is going to offer a LTD unless they're new. HeyGen is the cheapest platform compared to its competitors.

@siddharthmishra8283 Жыл бұрын

Big fan of your style and patience , please make a dedicated video on DRAGGAN installation on windows . Only you can explain it in the best possible way ! 🎉 cheers to your hard work

@ObscurelyTitled 11 ай бұрын

need to figure out what tools to use offline???????????????????

@purposefully.verbose Жыл бұрын

so, and forgive me if i'm overstepping, isn't this just SADtalker (as seen on nerdy rodent) with a web UI?

@lambgoat2421 Жыл бұрын

Yes but now you can pay for it!

@RuneW0lf Жыл бұрын

Cheers for the video Seb, Seems to be a snazzy web frontend for facetalker and some pre-generated TTS! (loved the video quality though, getting MUCH better)

@Gerard_V 11 ай бұрын

Cool!

@sebastiankamph 11 ай бұрын

I got you my friend

@mrschneebly85 Жыл бұрын

Does it work with animals like cats??

@kinkyqt Жыл бұрын

The puns master 😭

@Adem.940 Жыл бұрын

I choose openpose_full at controlnet but model section is empty, there is nothing to choose.

@sebastiankamph Жыл бұрын

You need to download the models, see install video for ControlNet.

@Adem.940 Жыл бұрын

@@sebastiankamph thanks, I did that after commenting, downloaded all models, all good now 👍

@nic-ori Жыл бұрын

Thanks.

@MeinDeutschkurs Жыл бұрын

That‘s promising. I hate to record my stuff in person. As soon I‘m able to include my own voice (in German), I‘m in.

@coloryvr Жыл бұрын

Amazing!

@srikantdhondi Жыл бұрын

are there any open sources available to make it the same?

@TPCDAZ Жыл бұрын

Good service but the price is OBSCENE. How can they charge more than midjourney, more than D-ID and more than ChatGPT.

@KDawg5000 Жыл бұрын

Cool stuff. It would be interesting to create an avatar with a recording of a CG character talking instead of live video of yourself.

@Warzak77 Жыл бұрын

this is D-ID that got renamed

@MauiMauricio83 Жыл бұрын

Ok, this has got to be your best cold open yet. Now I want to punch someone.

@sebastiankamph Жыл бұрын

😂😂 Miss ya buddy!

@MauiMauricio83 Жыл бұрын

@@sebastiankamph miss you too bud! I'll be back soon, once the move stops kicking my ass.

@rockapedra1130 11 ай бұрын

Haha ... Dad jokes are great

@TheSmilingLord Жыл бұрын

Can we use voice files with this or is it text input only?

@TheBagOfHolding Жыл бұрын

Never have stable diffusion analyze the pictures for prompts with the person watching. The computer thinks real people are all ugly.

@ysy69 Жыл бұрын

I really like D-ID since you can upload the voice file created over at 11 labs

@JustLocos Жыл бұрын

You can also do that with HeyGen

@ysy69 Жыл бұрын

@@JustLocos is that so? Alright, I’ll give it a try

@TheBagOfHolding Жыл бұрын

Why even mention stable diffusion? I was hoping it was using that not a website.

@marwentrabelsi2983 Жыл бұрын

btw this is not 100% AI

@martinstolz5971 Жыл бұрын

you are using definatly not enough breath to say words - they barely come out of your mouth. I would love if you could imagine a bunch of people are standing infront of you - and you would speak louder instead of letting the words just fall out of your mouth. But your content ist great - thank you for that.

@gdegde4406 Жыл бұрын

So... Stable Diffusion has nothing to do with any of this? You just chose to generate the source image with it, but you could use a real photo, a still from a movie or whatever.

@sebastiankamph Жыл бұрын

I could have chosen any image, yes. I wanted to provide some added value to users by showing them my photorealistic portrait styles, which I personally believe gives very realistic results compared to "hyperrealistic" prompts and images.

@marwentrabelsi2983 Жыл бұрын

and extremly expensive software for average result, somtimes below avrg

@strid3r574 Жыл бұрын

1st

@sebastiankamph Жыл бұрын

🥇

@CProton69 Жыл бұрын

Shifts???? lol What

@ulamss5 Жыл бұрын

Tl;dw: this is an ad. 1. Generate portrait in SD. That's literally it. 2. Pay someone to run their proprietary model on their servers to animate. Not cool.

@RuneW0lf Жыл бұрын

Its what he literally says at the start of the video! its the videos sponsor and he gave a full disclosure.

@thomassynths Жыл бұрын

This video would have come off much better if he simply removed "Stable Diffusion" from the video title and just grabed some random images without mention of SD to animate with the online service.