Deepfakery

Пікірлер

@a--------------- 5 күн бұрын

Definitely in my top 5 movies of all time

@stoney819 7 күн бұрын

can I re use the source for multiple destinations? or do I have to clear the workspace and re train every time

@Hoowler 9 күн бұрын

This was sublime! Great job

@Gethris 10 күн бұрын

Do i need to label forehead if i'm using f face type or over the eyebrows will do? Or its still better to label whole face?

@ASHLEENKAUR07 19 күн бұрын

Mujhe toh ek ladki hai uski deepfake nude video banani jisne meri life barbad ki school time uski video ko viral krduga internet pe public sali ko aukat dikhaduga uski😢😡

@SoldiersDoingThings 20 күн бұрын

I keep getting "This version is not compatible with your GPU please download a different version"

@fgdj2000 22 күн бұрын

So 1994 stranded in the Delta quadrant, 23 years later they arrive home, which is 2017, 10 years later, this Admiral Janeeay should be played by 2027 Kate Mulgrew, meeting a 2001 Kate Mulgrew

@SitiAminah-x4u 23 күн бұрын

can i use in ryzen 5 integrated gpu amd radeon

@cfhgudj6379 24 күн бұрын

I downloaded deepfakelab Direct 12. I unpacked everything, and now my question is, what should I run to activate deepfacelab?

@Deepfakery Ай бұрын

Download DeepFaceLab here - www.deepfakevfx.com/downloads/deepfacelab/

@EmptyPocketsXotics Ай бұрын

Repository has been removed from Github. No longer useful.

@Deepfakery Ай бұрын

The repo is down, but you can still download the software here www.deepfakevfx.com/downloads/deepfacelab/

@EmptyPocketsXotics Ай бұрын

@@Deepfakery Negative. Github and Torrent links are no good. Mega link only allows limited download unless you pay $110 or something stupid. This is basically a scam link at this point.

@jonnymacn9457 Ай бұрын

I am running with a 4080 super on the 30 series executable as thats the most modern, however, my iterations per second is only 1.46it/s when a 1080ti in the video is getting 3.71it/s , how do I increase the iterations, my GPU isnt being utilised at all, thanks

@ironmanYT-n9o Ай бұрын

I understand all the steps. I have after this a pretrained model. but how can i use this then, to apply it for a certain image e.g. my fathers picture, so that the deepfake is applied to his face at best?

@Deepfakery Ай бұрын

There are 2 ways: 1 - Extract the pics as dst, continue to normal training for a short time, then merge. 2 - Export as DFM and use DeepFaceLive. It can quickly apply the model to images.

@AGVenge Ай бұрын

Any version of dfl that works well with a new AMD gpu like xtx7900?

@Toti330 Ай бұрын

Today, the github deepface lab repository got taken down due to violations of githubs terms of service

@Deepfakery Ай бұрын

You can still download the software (which include the code) here - www.deepfakevfx.com/downloads/deepfacelab/

@Toti330 Ай бұрын

@@Deepfakery Thanks

@blackswan6386 Ай бұрын

github deleted it...sad

@fabriziohasselbach5735 Ай бұрын

I have I little Problem. When using "data_dst faceset MANUAL RE-EXTRACT DELETED ALIGNED_DEBUG", how do I mark/extract more than 1 face per Frame?

@Deepfakery Ай бұрын

Sadly you can't do that.

@SECourses 2 ай бұрын

would these pop up windows work on ubuntu linux desktop? those GUI windows?

@khanameen4692 2 ай бұрын

hey i am confused when to stop training i am currently at 80k iterations on the batch size of 14, how do i know when to stop ?

@Deepfakery Ай бұрын

Just stop and do a merge. If it looks good, good! If not, you can keep training.

@khanameen4692 Ай бұрын

@@Deepfakery can I merge in pre training?

@beniwolverine 2 ай бұрын

Nice video.Can it do multiple face swaps.

@Deepfakery Ай бұрын

To do multiple different face swaps in one video its best to make multiple projects and combine them in some editing software.

@Unreal_Burak 2 ай бұрын

which model did u use? liae? what is the resolution of this?

@Vamonos529 2 ай бұрын

Nice Tutorial. But i have sometimes frame issue. idk exactly.. guessed when i have 8000~10000 Frames, then the frames are intertwined some. then i have no option and just delete or quit that project. do you have a solution? i checked both extracted original frames name sorting and aligned faces' name sorting (file name and order was not intertwined).

@kai_harm942 2 ай бұрын

I don’t understand. The video doesn’t show where to leave the face pack with the pre trainer faces

@Deepfakery 2 ай бұрын

The pak file is just a single file archive of the faceset so it should be placed in the appropriate aligned folder.

@kai_harm942 2 ай бұрын

@@Deepfakery I got it in the end, I didn’t enable pre training

@T.JOfficialMusic 2 ай бұрын

Do you know how I can fix alien eyes (pitch black eyes and mouth)? I trained on SAEHD because Quick96 default 4 batch size is too much for my CPU. While setting the parameters, I selected "y" yes to eyes and mouth priority but I still got alien eyes and mouth after training.

@MWcrazyhorse 3 ай бұрын

Somehow for me it is only applying about a third of the masks in the merger. Tried everything. edit, train, apply, remove, redo. It only applies about a third of the src masks to the destination video frames.

@sarimutgaming 3 ай бұрын

Can i request for DMF file dasha taran?

@Deepfakery 3 ай бұрын

Try Discord, some ppl there will take requests

@sarimutgaming 3 ай бұрын

Where can i get link discord bro

@squeeps78 3 ай бұрын

Thanks. Do I need to train the model before or after I do custom masks? It keeps showing my pretrained model as the option for custom mask training.

@Deepfakery 3 ай бұрын

You need to train the XSeg mask, then apply it to the faceset, then train the model.

@bit_mma 4 ай бұрын

Hello what if I only want to sync my AI generated audio with just one video of a celebrity, how do I train the model for that

@Deepfakery 3 ай бұрын

You can use Wav2Lip, but it's not very accurate. Better than nothing I guess....

@imeverywhereandnowhere56 4 ай бұрын

I'm looking for a program that could this this for live streaming not with pre-rendered video. I also need it to change my voice. Does anyone know of such a program?

@Deepfakery 3 ай бұрын

DeepFaceLive will render in real time but you need a pre-trained model exported as a DFM. www.deepfakevfx.com/downloads/deepfacelive/

@AnNguyen-pd2xi 4 ай бұрын

Hello, I have a problem at the final step. When the merging reaches 100%, the process does not finish no matter how long I wait. It stops right there, and all I can do is close the window. When I open the 8) file, it also does not run. Can you help me solve this problem? Thank you very much.

@Deepfakery 3 ай бұрын

Yes it will stop at 100%, just close the window. I'm not sure about your problem with "8) merge to ..." but make sure you have the original video file in place as it is needed for the final step.

@rollie2001 4 ай бұрын

Makes her look mirror universe evil lol

@พริกหยวกออกกําลังกาย 4 ай бұрын

How do I deal with videos that have facial distractions, such as eating, eating ice cream, wearing glasses, or using hands around the face?

@Deepfakery 3 ай бұрын

XSeg

@unknownexposer8399 4 ай бұрын

Does SAEHD make the process way faster and accurate?

@Deepfakery 3 ай бұрын

Its "slower" than Quick96, but much higher quality and accuracy. Pre-training speeds up the process by creating a sort of base generic model instead of starting from scratch.

@newday8545 4 ай бұрын

Holy shit lmao. Im surprised this video doesn't have comments. Biden in an alternate universe haha

@newday8545 4 ай бұрын

I can see a bit of Clint Eastwood in there lmao.

@Cradge666 4 ай бұрын

In the final chapter, "applying the xseg mask," you say to draw new masks and retrain. It's necessary for me to do this in the project that I began, because even after 85000 iterations some of the masks were very wonky, but do I need to delete the old masks first? Or can I reshape the old mask? I'm hoping you may be able to explain that part a little more. Thank you

@balachandhar-js7pc 5 ай бұрын

Can anyone create me a perfect own deepfake model. I need different models every week. I can pay for that.

@its.ronnie.97 5 ай бұрын

Hello sir. I want to create ai influencer of ny own face and create videos... I can pay you the your charges can you please create deepfakes for me?

@skintgirafde320 5 ай бұрын

His monkey speech will never not be funny!

@jdbau2075 5 ай бұрын

This might be the best I've seen. Amazing work.

@주왕-y3u 6 ай бұрын

It's awkward even if it's over a million times There's a lot of video quality that's blurry, but if it's longer than Do I have to do more videos? It stopped at 0.1730 Someone told me to go from 0.02 to 0.08, is that right?

@kiperenok 6 ай бұрын

Trump's face would suit him better!

@aebonne 6 ай бұрын

i'm stuck at 100% merging.. can I close the window or do I need to see the "done. press any key to continue" on the merging part?

@sammysammy238 6 ай бұрын

can you use can image as data_src and implement it in the destination video?

@Zaungast-of7wy 6 ай бұрын

First of all thank you for that extremely useful tutorial. I have one question left, if I collected all my faces in my src folder and apply all my masks in "head" Typ for my first project and after that I star a second project with where I need forehead masks. Is it possible to save my head src masks so if I need them in other projects I can use them later? I all projects the same src pictures are used, only other mask types. Thank you for your time!

@troxity5589 6 ай бұрын

idk

@Deepfakery 3 ай бұрын

You can save all of the files that have masks labeled using 5.XSeg) data_dst mask - fetch.bat and 5.XSeg) data_src mask - fetch.bat. You can also save the trained XSeg model and use it to reapply later.

@deeber35 7 ай бұрын

If I have a frame where the face is at a weird ngle, do I delete in Aligned Results, will I still get to manully extract it? Not sure what deleting a frame means for masking in that frame.

@nzpham3389 7 ай бұрын

Thank you so much for your explanations

@blynkpham4369 7 ай бұрын

thanks, your video is so good, I subscribed and liked.

@thiemkom5911 7 ай бұрын

Nidia mx 940 setup verison?

@shatteredimage7826 7 ай бұрын

I have windows 11 and an Nvidia rtx 4080. Am I still able to use deepfake

Ең жақсы KZbin

Пікірлер