AniPortrait - AI Audio-Driven Synthesis of Portrait Animations - Local Install!

Поделиться
HTML-код
  • Опубликовано: 1 янв 2025

Комментарии • 39

  • @vi6ddarkking
    @vi6ddarkking 9 месяцев назад +18

    Ok, so hear me out.
    This with SD3 models + Tavern AI text to speech with Llama 3 or Grok derived models.
    2024 is shaping out to be a truly fun year.

    • @jackrabbit1704
      @jackrabbit1704 9 месяцев назад

      It'd likely take a nasa quantum super computer to run stable diffusion image prompts, a moderate llm, rvc/applio and then this all at the time. But yes, yes please.

    • @vi6ddarkking
      @vi6ddarkking 9 месяцев назад

      @@jackrabbit1704 Not really. Anything above a RTX 5070 should be able to handle it comfortably.
      Considering the Blackwell architecture and the improvements in AI efficiency we're seeing.

  • @kariannecrysler640
    @kariannecrysler640 9 месяцев назад +5

    Here comes Peter cottontail. Hopping down the bunny trail. Hippity hoppity nerdy’s on his way! 🐭🐇

    • @NerdyRodent
      @NerdyRodent  9 месяцев назад +1

      😀

    • @kariannecrysler640
      @kariannecrysler640 9 месяцев назад +2

      @@NerdyRodent 🤘😉💕

    • @marilynlucas5128
      @marilynlucas5128 8 месяцев назад

      @@NerdyRodent My suggestion is to try experimenting with fourier transforms to eliminate the flickering in stable diffusion videos as the frequency level. Please do you understand me?

  • @PrincessSleepyTV
    @PrincessSleepyTV 9 месяцев назад +2

    This is so cool!

    • @NerdyRodent
      @NerdyRodent  9 месяцев назад +1

      Can’t wait for a few more papers down the line! 😉

  • @5olrain
    @5olrain 9 месяцев назад +4

    I wonder if we'll ever get something like LucidSonicDreams but with SD, that would be incredible!

  • @UnchartedWorlds
    @UnchartedWorlds 9 месяцев назад +5

    Fix those eyes to look directly into the camera and this is great!

    • @leavemealoneandgoaway
      @leavemealoneandgoaway 9 месяцев назад +2

      there is software for that too

    • @marilynlucas5128
      @marilynlucas5128 8 месяцев назад

      @@leavemealoneandgoaway What is that software? descript?

    • @MrRaja
      @MrRaja 7 месяцев назад +2

      If you have Nvidia GPU you can use Nvidia Broadcast on your camera and there is a A.I. function to lock your eyes to camera. even when you are reading something on your monitor or looking down to your keyboard to type your videofeed will show you staring at the camera at all times as long as your eyes are decently visible (bang/too dark).

    • @marilynlucas5128
      @marilynlucas5128 7 месяцев назад

      @@MrRaja oh? How nice

  • @AguniAgooni
    @AguniAgooni 6 месяцев назад

    Could you tell me the inference time and you system configuration ?
    And do you know any near real time talking head models?

  • @DeconvertedMan
    @DeconvertedMan 9 месяцев назад +4

    +1 points.

  • @smtabatabaie
    @smtabatabaie 9 месяцев назад +1

    How's the inference time with audio driven mode? is it near real time?

    • @NerdyRodent
      @NerdyRodent  9 месяцев назад +2

      Not even close 😉

    • @smtabatabaie
      @smtabatabaie 9 месяцев назад

      @@NerdyRodent Thanks, Do you know any talking head with near real-time inference? Something like D-ID real-time avatars

    • @NerdyRodent
      @NerdyRodent  9 месяцев назад

      Where you can do your own custom stuff easily, locally and for free… not that I can think off 🫤

    • @AguniAgooni
      @AguniAgooni 6 месяцев назад

      @@smtabatabaie Hello, did you find any such near real time talking head models?

  • @pfbeast
    @pfbeast 9 месяцев назад

    How to use "instruct pix 2 pix" & "SDXS" in comfyui?

  • @Trungkhai-z1h
    @Trungkhai-z1h 8 месяцев назад

    now this tool can make , two hand ,mouse , Natural movements and realistic performances

  • @Trungkhai-z1h
    @Trungkhai-z1h 8 месяцев назад

    How long time we can make out put video 5 nminutes or 10 or 30 minutes if we want

    • @NerdyRodent
      @NerdyRodent  8 месяцев назад

      Each video can be as long as you have the hardware for!

  • @Trungkhai-z1h
    @Trungkhai-z1h 8 месяцев назад

    and any tool can make voice clone and train voice , thanks

    • @NerdyRodent
      @NerdyRodent  8 месяцев назад

      Do you mean like the example in this video?

  • @LouisGedo
    @LouisGedo 9 месяцев назад +1

    Hi

  • @fernandodiaz8231
    @fernandodiaz8231 8 месяцев назад

    Thank you for the information. I would like to ask if you know some Colab options or Kaggle notenook for AniPortrait

  • @jkl-x7p
    @jkl-x7p 9 месяцев назад +1

    Strabismus attack

  • @sinayagubi8805
    @sinayagubi8805 9 месяцев назад

    we want a speaking rodent in the corner of your videos. ahaha

  • @el-_-grando-_-_-scabandri
    @el-_-grando-_-_-scabandri 9 месяцев назад +1

    creepy

  • @LilShepherdBoy
    @LilShepherdBoy 9 месяцев назад +3

    Now this is actually very cool. Must be great for people that want to do VTuber content but don't want to go through the whole rigmarole of setting one up.
    -
    Jesus Christ loves you 💙
    He has a plan and a purpose for your life, plans to prosper you and not to harm you, plans to give you hope and a future.
    Jesus Christ loves you 💙

  • @RhapsHayden
    @RhapsHayden 7 месяцев назад

    Ugh I forgot to create an environment and screwed up Comfyui. Took me all day to fix it😂. I'll try it again tomorrow because I need this