• Content

  • Why don't we get into private deepfakes?

Vrsumo2017 There are only a couple of quality VR creators there, I sub to their fan-topia for pretty cheap and download the 4k+ versions of their clips.

      KingpinVR

      OK so there are a few free software involved. You will need a mid-range+ NVIDIA GPU (30 series and up I would think).

      To create clips of your VR video you want to face swap, I recommend using LosslessCut. This is extremely easy to use and very fast, as it cuts the video where you want to without re-encoding it. If you are unsure how to do things in Losslesscut, there are lots of YouTube videos explaining and it is a really user friendly program.
      https://github.com/mifi/lossless-cut

      For the face swapping software, you can use Rope, follow the python installation and guides at the link below. I would practice with the 2D 1080p 'benchmark video" to get the hang of it, and to optimize the speed of swapping for your system by increasing the number of threads. The author has a discord and made some videos showing how to use it as well.
      https://github.com/Hillobar/Rope

      Now if you want to change the audio as well, you will need to use a software called FreeVC (Voice to Voice conversion). Here, you would take the voice clip of the audio that you want to convert (that can be exported as a *.wav file from LosslessCut alongside the video) and a 6-15 second sample clip of the voice you want to convert it to. Once the voice has been converted, you can substitute the new audio *.wav file back into your video using LosslessCut again.
      https://github.com/OlaWod/FreeVC

      Now, I have to use FreeVC by means of the HuggingFace Demo or there may also be a Google Colab linked on that page, as my 8 GB VRAM 3070 does not seem to be enough for FreeVC. I think it has more to do with the software not being optimized for memory efficiency tbh.

      And that is it. It takes a bit of work to get everything installed but the workflow itself is not overly difficult. I recommend starting with a clip where the model is mostly in the center of the screen and facing forwards for best results, maybe in missionary or riding as long as she is not too high up. Once you get a feel for it, you can see where you can push the boundaries a bit. Results will vary, but they can be quite good.

        What about Deepfakes of your favorite Porn star from 1980s 90s etc and porn stars who have retired and never did VR Porn ?

        17 days later

        rlrqwbzmudgxnyltqc Sometimes I just wonder what world did I wake up into? Text to VR would be sweet combined with BYOJ as source material. Any model, any scene, any position, any rare niche now standard AI generation.

            4 days later

            I've been doing some tests in this field and it's some scary stuff 😁

            MickyCheese cool experiment, shows us it can be done. Probably won't be long before this is far more op optimized too.

            No idea who you face swapped though. Might be a better example to put the original and the processed one underneath eachother.

              12 days later
              7 days later

              justsomedude101

              New model with similar architecture as Sora is announced from Stability AI. However, it appears that these new models are also becoming "safer", so they might not be very useful for adult industry. 🙁

                  rlrqwbzmudgxnyltqc that's stable diffusion 3. Mostly images as I understand it. Hopefully the safety warning is just lipservice to keep the investors happy. We won't know before it's actually released. The model seems promising though.

                  Yeah and I agree, safety and AI is such fucking patronizing bullshit at the moment. Safety is not actual safety either, Safety = no brand damage. No sensational headlines that damage their reputation. If they where actually concerned about safety they should think about what it will means for one country or government to wield the power of agi. Or big tech having agi and not democratizing it. Not worrying if we might get a nip slip in an image or if the AI says something that isn't totally woke. The days that those ais where blatantly racist are far behind us and we are living in an era of overcorrected and overcensored AI. Can't last forever though and open source is getting more usable. Still the cutting edge like sora and gpt-4 are so far ahead of that..

                    2 months later

                    Q. Why don't we get into private deepfakes?

                    At least in the U.K. and without consent from the actor/actress being deepfaked it will now be a criminal act, even if that deepfake would never be shared. At this point I imagine that not many companies would want to touch this 'private deepfake' with a ten foot pole. That said, you could still have the options for studios to offer deepfake releases for models who could or would be willing to be body or face swapped but things could potentially get murky in the future here as well.

                    https://time.com/6967243/uk-criminalize-sexual-explicit-deepfake-images-ai/

                    I heard a story on the news that students are using deep fakes on classmates. It's lol but also its very crazy times were in 🤦‍♂️🤯

                    Vrsumo2017 surprised they don’t have any more updates.
                    it’s a shame they aren’t showing likes.