Frame-by-Frame Controllable Image-to-Video Workflow by PIA and AnimateDiff: Make Any Image Blink!

Поделиться
HTML-код
  • Опубликовано: 25 ноя 2024

Комментарии • 11

  • @aivrar
    @aivrar 3 месяца назад

    Thank you tons, this is the only comfy PIA tut I can find on YT.

    • @SweetValberry
      @SweetValberry  3 месяца назад +1

      Glad to hear it was helpful!😄

  • @MilesBellas
    @MilesBellas 3 месяца назад

    Great video!
    Thanks! 😊

  • @thibaudherbert3144
    @thibaudherbert3144 3 месяца назад

    is this the best way to create videos ? I don't know there are so many models like animatedif, animate anyone, mimic motion, liveportrait....

    • @SweetValberry
      @SweetValberry  3 месяца назад +2

      I've basically used most of them, and I've even made video tutorials for many of them. In my opinion, to create different types of videos based on different inputs, we need to choose different solutions. If we want to strictly control the evolution of the video, AnimateDiff is currently indispensable. When AnimateDiff is combined with the PIA model, it can greatly improve the stability between different frames and produce higher quality videos.

    • @thibaudherbert3144
      @thibaudherbert3144 2 месяца назад

      @@SweetValberry thanks for your reply

  • @flyingstapler1241
    @flyingstapler1241 3 месяца назад

    How does Cogvideo differ from PIA?

    • @aivrar
      @aivrar 3 месяца назад

      CogVideo uses 30+gb vram to use.