The Ultimate ControlNet Tutorial: Understanding UNet, Exploring Pro Max, & Kolor's New Model

แชร์
ฝัง
  • เผยแพร่เมื่อ 15 ม.ค. 2025

ความคิดเห็น • 22

  • @bgtubber
    @bgtubber 4 หลายเดือนก่อน +1

    Excellent lecture! More of these, please! It's always fascinating to learn how things actually work under the hood with examples. You're approach is great. You don't just tell people "do this and that and you're done". You actually explain things like a good teacher. You and Matteo (Latent Vision) are my favorite Stable Diffusion/ComfyUI youtubers. I never miss a video from you, guys. 👍

    • @ArchAi3D
      @ArchAi3D  4 หลายเดือนก่อน

      Thank you

  • @dominichawgood4976
    @dominichawgood4976 5 หลายเดือนก่อน +1

    A very clear explanation and some useful tips that other people tend to miss out. Thanks!

  • @WD_MyImage
    @WD_MyImage หลายเดือนก่อน

    Great! Thanks for providing such clear details!

  • @nenu_Ne_Neurons
    @nenu_Ne_Neurons 5 หลายเดือนก่อน +1

    Kudos to your patience ❤❤

    • @ArchAi3D
      @ArchAi3D  5 หลายเดือนก่อน

      Thank you! 😊

  • @АлексейЮжаков-л8ш
    @АлексейЮжаков-л8ш 3 หลายเดือนก่อน

    Thank you for the lessons, you give a deeper understanding of working with neural networks and help solve applied problems

  • @___x__x_r___xa__x_____f______
    @___x__x_r___xa__x_____f______ 5 หลายเดือนก่อน +2

    thanks for this excellent tutorial ❤

    • @ArchAi3D
      @ArchAi3D  5 หลายเดือนก่อน

      You're welcome 😊

  • @TUSHARGOPALKA-nj7jx
    @TUSHARGOPALKA-nj7jx 3 หลายเดือนก่อน

    Such an amazing video

  • @inspiredbylife1774
    @inspiredbylife1774 3 หลายเดือนก่อน

    Thank you for this video!!! Very useful

  • @mrasa2704
    @mrasa2704 5 หลายเดือนก่อน

    Wow! Comprehensive, very useful, interesting and visual!
    What software did you use to present Unet in 3d ?
    Also, it would be interesting to know if the same t2i adapters differ in any significant way from standard controlnet.
    Plus there is also the coadapter (also for 1.5 models) I think they were trained a bit differently, but there are usable models. For example there is colors, it is much better at rendering colors compared to tile and inpaint models

  • @bgtubber
    @bgtubber 4 หลายเดือนก่อน +1

    Not sure about the other controlnets, but from my experience, the SD 1.5 tile controlnet is still unbeatable to this day. I've tested pretty much all tile controlnets, including 2-3 tile controlnets for SDXL and the latest one for Flux. SD 1.5 still seems to produce the best creative image with the richest detail. If anyone cares to explain why, I'd be interested to hear. I would expect the Flux or SDXL tile controlnets to be the best, but that's not really the case in my experience.

    • @ArchAi3D
      @ArchAi3D  4 หลายเดือนก่อน +1

      Please test ttplanetsdxlcontrolnettilerealisticV2 with advance Controlnet extension and soft weight node+ Perturbed-Attention Guidance
      The result will be amazing 🤩
      civitai.com/models/330313/ttplanetsdxlcontrolnettilerealistic

    • @bgtubber
      @bgtubber 4 หลายเดือนก่อน

      ​@@ArchAi3D I've tried the TTplanet tile controlnet V2 before, but maybe my settings were not correct, because I was not getting good results when doing img2img creative upscale of 3D renderings. I will need to try again the way you explained. Thank you!

  • @nkofr
    @nkofr 5 หลายเดือนก่อน +1

    nice, very interesting! I'm trying to understand why we would keep usind SD1.5 controlnets vs SDXL?
    also, isn't the "soft weights" for 'my prompt is more important' the same thing as lowering the strength of the controlnet? what's the difference?
    Cheers!

    • @ArchAi3D
      @ArchAi3D  5 หลายเดือนก่อน

      some SD1.5 ControlNet trained with higher step so they can work better, soft weights change the ControlNet strength inside the Unet layer and then it can make same affect as: my prompt is more important

    • @nkofr
      @nkofr 5 หลายเดือนก่อน +1

      ​@@ArchAi3D thank you, I didn't know this feature "my prompt is more important", and I still don't grasp exactly how it differs from modifying the strength of controlnet. Thanks

  • @TUSHARGOPALKA-nj7jx
    @TUSHARGOPALKA-nj7jx 3 หลายเดือนก่อน

    Is there a difference is speed if multi controlnet node for multi controlent in your workflow compared to using single controlnet and combining them one by them. Doesn't that increase the dimensions of the vector in latent space?

  • @TUSHARGOPALKA-nj7jx
    @TUSHARGOPALKA-nj7jx 3 หลายเดือนก่อน

    How can we combine controlnet with inpaint - since that usually becomes too constrained and the somehow the model is unable to follow the prompt better

  • @WhatsThisStickyStuff
    @WhatsThisStickyStuff 5 หลายเดือนก่อน

    Are the kolors controlnets better than using the xinsir controlnet with the adapter for kolors?

    • @ArchAi3D
      @ArchAi3D  5 หลายเดือนก่อน

      Yes I think it’s better, I will test and share the results