Видео

As far as being able to detect the face? No. Only thing you can do is try the different detector models or just use "many". If you're asking about how to deal with things covering the face when the face IS detectable, then just make sure to use occlusion masking.

@@shadyendeavor i see, thx a lot for the videos.

@@NinjaKittyBonks thanks! Yeah, came together last minute as I didn't even have the swaps done until a bit before the show. Then still had to do all of the editing, music creation and thumbnail. I didn't even really watch it until after it was uploaded.

@@AbhijeetMaurya-g1l colab is not supported by FaceFusion currently, and hasn't been for a while. If you want to use it for free, you'll need to install it locally on your computer.

1. Yes, I did state towards the beginning that this is only currently in the NEXT developer version and will be available to everyone when 3.0 is released. 2. Anybody can test out the NEXT version with the understanding that it is a developer release and that things constantly change and can break and you are using it to test and report any bugs you come across. If you are interested in trying it out, check out the FaceFusion Discord and ask in the "early-adopters" channel. 3. Nope, not possible. Thanks for watching!

@@shadyendeavor thank you so much! Appreciate your time and effort. 👍

Very cool! I'll check those out a bit later when I can turn up the speakers. ;) Also, without having heard them, I love that all 3 (based on their names and prompts) are completely different styles/types of music. I honestly can't say I've noticed a drop in quality, but to be fair, I also don't use Udio nearly as much as I did while it was free. Kind of ironic that now as I'm paying for it, I use it less. But what I have created since, I've still been very happy with.

it happens when trying to paste the last command after installation.

It sounds like you're having a directory permissions issue. I'm assuming you're doing this all in the correct directory. To verify permissions type the following: ls -ld $(pwd) The rest of the information I'm about to post is directly from chatgpt, so I'll let you decipher it for yourself. I'm not exactly tech support for Homebrew. ;) "This command will show you the permissions of the current directory. The permissions string should look something like drwxr-xr-x at the beginning. If the directory isn’t readable, you can modify the permissions using: chmod +r . ---make sure to get the space and perio at theend of that command Hopefully you have the correct permissions setup now. Try installing Homebrew again. If this doesn't work. I'm not sure how to help. Good luck!

Thank you! I'm glad it made sense. It always makes sense in my own head, but I never know how people are going to react to it from their perspective.

Oh, believe me, I would love this. Getting barely 200 subs in a month when 30,000+ are using this software is definitely frustrating. Oh well, hopefully that will change soon. Especially with the video I have been working on for some time now. But I can't release it yet. Blame Henry :P I assume by your graphics, that you mean the interface changes that you created for FF, I would love to, but I, myself, even use a very different looking interface most of the time, but I try to use the default so that viewers aren't confused by any changes and can easily relate what's in the video to their own. As always, thanks for the support!

@@shadyendeavor I meant just that, you could show users com and install mods. (e.g. my graphics mods) or the various other interesting mods found on the discord channel.

Yes and no. I've had times where I've had an image or two that didn't really make the swap look like the person, so I added another 1 or 2 and then it looked much better. I played with those a bit and yeah, some single images just aren't as good at portraying the subject. So, as I do this so much, I just got into the habit of having multiple images for ever subject I use. At least if it's not someone new that I want to try really quickly. I'm sure a lot of the time, it's not making much of (or any) difference), but I don't think it hurts in anyway. So why not? ;)

Yes, definitely works with images. I just never show images in my videos as, well, first of all, it's never as exciting to see the output and I very rarely have a use for single image outputs.

Yep, Gradio is not a great UI. And it's definitely on the Roadmap to be replaced, but it's a huge venture to switch over. But yes, could definitely be better.

Now I can't get Sinatra music out of my head for some reason... Yeah, I'm pretty excited about the new feature and this is just a small part of what I used for the video of what I told you I'd been working on for quite some time. I guess I need to go watch Army of Darkness now. It's been quite a while.

Hahaha, to be honest, I agree with that sentiment. I'd been super busy working on a video that I can't mention yet, but I can't release it yet as it's to coincide with the release of something else and that's been pushed back quite a bit. However, I do have a new video that should be coming out on Thursday. And in English!

What? You mean you don't think I understand Italian and the other languages fluently? Either way, computer browser version of YT has translation built in, so I don't have to go anywhere for it. ;) Yeah, the speed up and slow down, there really isn't anything I can do about that other than reroll the entire thing in ElevenLabs and hope for a better version. Sometimes, if its just one small part that is obvious, I can speed it up or slow it down in Davinci when I'm editing it, but tbh, these are also supposed to be low effort videos for me. They don't get much in the way of views and putting in more effort into them than I already do isn't really worth the time. I'd love for them all to be perfect, but well, too bad! :P

Not something I've run into. Did you get a dialog with that request? If not, does it work anyway? If it's not working, you're going to have to ask for help on the Pinokio Discord. Link in the description.

Decirme que tienes errores no me dice nada. Tendrás que ir al Discord de FaceFusion y pedir ayuda allí. Asegúrate de publicar una captura de pantalla del error que recibes cuando pidas ayuda. Enlace en la descripción.

Lo siento, no. Tengo videos que ya explican cómo hacer la instalación. Incluyendo cómo hacerlo instalando primero Pinokio para que sea más fácil.

I love this! This is so cool to hear (read). Yeah, the remixing of audio is huge and I've been able to do some amazing things with it myself. I used it to make the music for a trailer that I'm working on that's coming out soon. You might say that it's 90% AI, but it's still you. You're still creating the lyrics, you're still putting together your ideas in the way you want to. It's a tool that's helping you create what you've wanted to hear.

@@shadyendeavor I appreciate you man I will be looking out for your trailer

Currently, it is only available in the NEXT (developer version) of the application. You are welcome to try that out, but I'd recommend asking in the "early-adopter" channel on the FaceFusion discord (linked in the description below). As there are a lot of other features added to try out too. Otherwise, it will be freely available as soon as version 3.0 is released.

Всегда приятно слышать. Спасибо!

git pull python install.py for updating to whatever the newest version is. Just make sure you're in the correct directory and conda environment. Default settings are the best, well, default settings, but every video/image is different and may require minor or major adjustments.

same issue. did u find how to solve it?

Yes, I was skeptical of it myself. ;) I just knew that I wanted to make something that completely showed the entire workflow of an entire song and I think I got it to that point. Yes, there were definitely quite a few things that I missed. But this was very early on and Udio was still in beta, so I, along with everyone was still learning at the time. Definitely some good tips and if and when I create another video on Udio (especially with 1.5 available now), I'll probably add most of these along with quite a few other things I've learned since. And yes, the inpainting would have been nice...had it been available to me when I made the video. I think it was released a day or 2 before I released this video and I wasn't going to go back and "fix" it when I hadn't even paid for Udio yet. Anyway, thanks for the comments and suggestions. Like I said, I'll definitely look at them and work on them with the next video.

@@CharlesLouisRosario it definitely works on Sonoma. Not sure what problem you're running into, but it definitely works.

/usr/local/Cellar/python@3.12/3.12.4/Frameworks/Python.framework/Versions/3.12/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/(hide)/install.py': [Errno 2] No such file or directory

@@victoria.bela78 I could be wrong, but I know sometimes I get this issue and you literally just need to close your terminal and then just come back in and do the install. Just make sure you CD again and start your conda environment again too. Then try the python install.py If that doesn't work, you're going to need to ask for help on the Discord channel. The link is in the description.

@@shadyendeavor thank you so much it works ! but now I have an other error 😅 I put it here juste in case you can again save me : ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. gradio 3.50.2 requires numpy~=1.0, but you have numpy 2.0.1 which is incompatible. 🙏

@@victoria.bela78 it should be fine. Does the install not continue after that and say that it successfully installed a different version of numpy? If so, you are ready to run facefusion. If not, back to Discord option.

@@shadyendeavor It works for the photos but not videos .. thanks again

that's beyond my expertise, sorry. Please check out the FaceFusion discord. They will surely be able to help you there. The link is in the description.

you're going to need to ask for help on the FaceFusion Discord. The link is in the description.

which part is loading infinitely? the source? the target? the preview?

@@Dover78 I'm not the one that Matt shows on their show. I've been doing it just as long, but Matt won't show any of mine. And you can see that I put quite a bit more work into mine. Especially if you look at the Top Gun Maverick, Silence of the Lambs, and Red Dawn ones.

@@shadyendeavor The ones you showed do look better than what ends up on the show. I was just surprised to find another Beauty and the Beta fan in the wild. The movie review AI swaps are what got me into messing with FaceFusion. Thanks for the tutorials by the way. I'm a complete tech retard and your videos have been really helpful.

but you listened to mine if you watched the whole video 😉

You are weird😄

@@simakautas I take that as a compliment!

I’m very proud of you

Yep, definitely. Although very true on the personal lyrics, I've also been having fun with instrumental only projects lately.

at first I was surprised you saw this video, but then I realized I forgot to unclick the checkbox that distributes the video to all subscribers. Oh well.

@@shadyendeavor ... I just now realized, I never went back to check if my test comment remained. Seems it did, but now that comment makes as much sense to everyone else, as that Shady AI character's language when I watched I watched it. Amazing how it replicates your voice, but then applies an entirely different language... crazy.

@@NinjaKittyBonksyep, I've actually put a lot of these videos out in multiple languages now, but I usually don't post them to the subscribers. They're meant more for people specifically looking for help in a specific language.

@@shadyendeavor ... Do you have a foreign language playlist or some way to advertising to alternate language users or what?

@@NinjaKittyBonks yep, each language has its own playlist. It should show at the end of each of the videos. But I have Spanish, Italian, German, Russian, and Chinese...so far.