• Content

  • Why don't we get into private deepfakes?

catflap Images generated using Unstable Diffusion are already very high quality and is improving at a rapid rate.

I wouldn’t be surprised if we’d be able to generate high quality VR videos with a few years of development.

Another big plus of this approach is it will give us unlimited models to choose from. No matter what our tastes are, we can repeatedly generate a new face that match whatever look you prefer!

    7 days later

    Now that AI can learn how people speak, and continue a conversation in someone's voice from a very small initial vocal sample, how about the ability for users to upload a sample of their voice so that the male porn star's script is spoken in the viewer's voice? VR porn is weird in that the dude never speaks, and they don't speak because it breaks immersion. At some point we should be able to have a fully vocal dude but speaking in our own voice. Use sparingly of course.

    You would have to encode the audio separately from the video, so everyone sees one VR scene but just the audio is adapted on the fly to match the user's voice.

    Might be weird, might be cool 🙂

    2 months later

    I make my own. not too complicted, just requires some patience and time. trial and error, and the right software to make it easy and maintain quality. what I use: (all software can be obtained for free but not sure if I can disclose that here) I use swapface for the deep fakes. videoprocconverter for triming and croping or resizing. also use Topaz video AI for same thing. Topaz is better for specific frame trimming and also ai upscaling. just as good with cropping. I use swith audio converter free for extracting audio to edit in audacity or RX 8 Audio Editor, and finally I use After Effects to put it all together since its more effecient to crop each eye seperate for the swapface. tho the output is extremely large when using after effects, its good to use the videoproconverter to convert to a decent size file but with that you are limited to 4k. using topaz resave original after effects output is a more efficient way to keep output size but reduce the overal file size. the most time consuming and computer resource taking woule be the exporting from after effects. if you can find a software that allows you to video edit above 4k I recommend that instead.

      4 months later

      mapratt1771 That's awesome. Do you have any fresh tutorials that go into more detail? Have you managed 8k yet? What GPU do you have and how long does it take to convert one video relative to size/length/resolution?

          a month later

          rlrqwbzmudgxnyltqc

          That's what I said to do, we can use old film pontstars faces on these hotties today and voice, if they allow their likeness to be used.

          Man! Get sum Jenna Jamison, Tera Patrick
          Hell I bet sum celebrities would join in too, Kim Kardashian, cardi b, it'll happen, but I'd want that shit in vr fuck a 2d video. Get me up close!

          Man they bout to scan their bodies too I bet. You'll have their actual full body deep faked!

              doublevr this is an amazing idea! We definitely need a deep fake feature built into the video player. Like you would have the pictures of faces you'd like to swap saved on your device and then just pick the video then hit face swap and choose the face you want to swap in. Has AI advanced enough for this to work?

                So yes we can do some of this already with existing technology. Results will vary in quality. Currently, we can change and mimic voices with models and using the transcript with appropriate inflection you can get some authentic sounding voices cloned. In terms of swapping the face, I use Rope (Github), which is a wrapper for Insightface, which uses a stable diffusion like process and you can import the video into it, it will track the face (you can have multiple faces like in LR VR, or just multiple people in general) and then you choose images of the face you want to swap. It works best to have the face with multiple angles and multiple lighting conditions if possible, I use like 15 images per video. The software then steps through each frame, identifies the face and swaps it for the desired face.

                Things that will cause problems include if her face gets occluded (like she is sucking dick) or if she is too close to the top of the camera lens or just getting too much lens distortion on the face. The software doesn't really know how to handle this. Of course, to move the technology forward, we would need a custom solution tailored for VR, either by projecting the video onto a flat rectangle before swapping the face, or training a custom model that can learn how to swap a face that is very distorted by the curvature of the lens. I have some ideas but would need time to play with this to see what works and what does not.

                Currently, there really is not a full body swap technology either, but again that can be something that can be worked on in a similar method that the face model was trained on as well. If people want to try this I recommend starting with a trimmed video where the model is mostly in the center of the screen for best results, maybe in missionary or riding as long as she is not too high up.

                In terms of how long this takes, I have an i7-10700K CPU @ 3.80GHz with a 3070 and the process tends to take about 3-4x the length of the video, but this will vary a bit depending on resolution and frame rate.

                  I mean VR deepfakes have been a thing for a very long time... Although the quality does vary, but it's definitely getting there.

                  https://mrdeepfakes.com/videos/virtual-reality

                  You can face swap a non-vr videos using deepswap.ai

                  Although the quality of the video isn't all that great given that it is simply an image that they are referencing.

                  You can try to generate your own with DeepFaceLab, it's an open sourced tool that is capable of achieving some pretty impressive results. You do need a higher end GPU to achieve decent training speeds however.

                  I think the biggest bottleneck currently to generate a quality piece of VR deepfake with a custom face as a service is computing power. It's not as simple as stick a face on a VR video, and expect it to work flawlessly. I definitely think this is achievable in the near future though, just need the technology to mature a couple of more years at the slowest.

                  On the subject of ethics, personally speaking I don't really see an issue of people creating deepfakes for private use.. I don't see that being any different than fantasizing about being with someone, which everyone has done at one point or another. I think the ethics comes in play only when the creator starts to distribute these deepfakes without consent, and that's what really should be monitored and prohibited.

                    This idea is really something id like to see and use

                    6 days later

                    muSLR damn that's bad ass, omg hopefully they gonna use the voices too!

                    Id really love hear Ariana Grande's voice, Selena gomez. 🥵🤯

                      chris5554 sorry just noticed i had recieved messages. i never get on here anyway to answer your so far questions, no i dont have a tutorial vid, dont really want to make one unless there's, idk, some incentive. I have managed to get 8k. the software I use to put it all together "after effects" idk when or how but seems to be exporting the videos now at an extremely reasonable file size. i just upgraded my pc recently (gpu and ram) and my projects seem to go quite quickly now to a couple hours for a couple min 8k deepfake. my pc specs:
                      Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz 4.00 GHz
                      64 GB DDR4
                      RTX 4080
                      any other question feels free to ask, sorry for delayed responses

                          mapratt1771 right on dude, greatly appreciate it mate! What program or software do you use to do this? I am really curious about this and want to learn how to do it myself. The VR community appreciates your help as well im sure!