ComfyUI Tutorial: Save the Strawberry People! Optimizing AI Image Generation with TensorRT Nodes

Поділитися
Вставка
  • Опубліковано 8 січ 2025

КОМЕНТАРІ • 13

  • @salmonskinlover2365
    @salmonskinlover2365 Місяць тому

    15:57 okay you're the real deal if you can fine tune like that on the fly from pure experience lol, that's awesome

  • @trisvin7068
    @trisvin7068 5 місяців тому

    Salut comment a tu fait pour SD3 je ne trouve pas le .json pour build la version static?

  • @galnart5246
    @galnart5246 4 місяці тому

    Where is the model after you've built it?

    • @EdwinBraun
      @EdwinBraun 4 місяці тому

      It saves it to the same folder.

  • @nkofr
    @nkofr 5 місяців тому

    nice! is it compatible with LoRas, controlnets, etc.?

    • @EdwinBraun
      @EdwinBraun 5 місяців тому +1

      It should as it just replaces the checkpoint, so everything after should work just fine.,

  • @trisvin7068
    @trisvin7068 5 місяців тому

    How to make .engine sd3 ? Pls

    • @EdwinBraun
      @EdwinBraun 5 місяців тому

      What you mean? I show the process so far it is all the options you have.

    • @trisvin7068
      @trisvin7068 5 місяців тому

      @@EdwinBraun i dont have the Tensor rt SD3 , i m build sdxl turbo good , but i dont build thé et sd3

    • @trisvin7068
      @trisvin7068 5 місяців тому

      How did you build sd3 tensor rt static? I can't figure it out, did you use the trt engine sdxl base build or did you find a build trt sd3 workflows? help me I beg lol​@@EdwinBraun

  • @openroomxyz
    @openroomxyz 5 місяців тому

    This is all nice
    but it just add complexity which is not
    optimimal nvidia could host all models for all their GPUs in optimal format

    • @cebasVT
      @cebasVT  5 місяців тому

      Yes that would be nice. However it seems the amount of drivers,hardware and CUDA models is way too complex. It is pure chaos out there right now. Just look at PyTorch and CUDA versions and how this sometimes just does not work. Maybe AI can save us :)

    • @trisvin7068
      @trisvin7068 5 місяців тому

      ​@@cebasVTHow did you build sd3 tensor rt static? I can't figure it out, did you use the trt engine sdxl base build or did you find a build trt sd3 workflows? help me I beg lol