StableDiffusion Deep Dive - HiRes Fix - How to avoid twinning and losing composition

Поділитися
Вставка
  • Опубліковано 23 гру 2024

КОМЕНТАРІ • 71

  • @Nitrate1984
    @Nitrate1984 Рік тому +2

    Thanks for the quick and clean information, this video every second counts.

  • @kapytanhook
    @kapytanhook Рік тому +1

    I was looking for this guide for so long. forgot it was a video and not an article so google searches got me stuck. This is the best deep dive around.

  • @frangimenez4674
    @frangimenez4674 Рік тому +6

    Thank you so much! This solves a lot of questions I had, mainly "what upscaler should I use and when?". This has also let me understand a bit more of how the whole upscaling process works. Great video!

  • @adriennef9758
    @adriennef9758 9 місяців тому +1

    Very clear, thank you very much. I just stepped up my SDXL game.

  • @SlickSonicTitan
    @SlickSonicTitan 10 місяців тому +1

    I came to similar conclusions with my own tips research and noob testing, as i have a 2070s im not going to make a big xyz grid so this video is good to see it all laid out. Wish i saw this earlier, would have saved me loads of time, but hey the experimenting was good for learning a1111, id still say im a noob though.

  • @edphonez
    @edphonez Рік тому +11

    This tool really is a puzzle to use. It's time consuming but in a good way.

  • @Kryptonic83
    @Kryptonic83 Рік тому

    great info, love your charts and summaries of recommendations. Really enjoyed your upscaling video a month ago so now going back through most of your videos, good stuff.

  • @camilo3626
    @camilo3626 Рік тому

    2:43 you would recommend keeping hires steps "glow at 30"?

  • @TheBoomurdead023
    @TheBoomurdead023 Рік тому +2

    Really well made and helpful. Thank you so much!

  • @slashkeystudio
    @slashkeystudio Рік тому +1

    A follow-up on your hands testing might be worthwhile to see impact that hi-res fix can have on improving hands and faces.

  • @dzordzkeko2608
    @dzordzkeko2608 Рік тому +2

    Tried it out and it works, but when I go below 0.5 denoising it starts to look bad many details are lost. I tested 0.5-0.66 and results are decent, on 0.70+ it starts to generate weird horror stuff. Good tip thanks.

  • @NanamiKairyu
    @NanamiKairyu Рік тому +1

    When i only apply hi rez fix its emmidiately changes original picture to something elce even with 0 denoizing.

  • @ArtificialBeauties
    @ArtificialBeauties Рік тому

    all your videos are amazing !!

  • @autumndev
    @autumndev Рік тому

    I don't have the highres fix checkbox? Has this been removed in newer versions?

  • @FilthxSpewer
    @FilthxSpewer 9 місяців тому

    Any insight or help with images made in defourm? Colors are never consistent as more images are made. I have color coherence set to LAB. I don’t know what to do. Cfg 7

  • @achiche1337
    @achiche1337 Рік тому +3

    From my experience the latent upscalers are better in adding more details in the initial phase of image generation

  • @dmitrymyshkov811
    @dmitrymyshkov811 Рік тому

    How do you manage to generate one face, and not two, or three in one?
    There are so many tutorials and theories, but I just don’t understand this point.

  • @daffertube
    @daffertube Рік тому

    Thank you

  • @Tresdin.7
    @Tresdin.7 Рік тому

    Did u manually generate the images in the spreadsheet or is there an extention to selec all samples?

  • @BoldMold
    @BoldMold Рік тому +1

    Thanks A LOT for the video!
    I was really curious about that subject and my graphics card is way too weak for me to make a complete analysis like that myself.

  • @Joniyah444
    @Joniyah444 Місяць тому

    i decreased denoising all the way to 0 and it looks awful and grainy.. what went wrong? ugh

  • @twilightfilms9436
    @twilightfilms9436 10 місяців тому

    I know this video is 1 year old, but I wonder of through a similar technique can you achieve similar results as Korea or Magnific. Have you tried something like that?

  • @achiche1337
    @achiche1337 Рік тому +1

    Can someone tell me why I would use Hires fix instead of upscaling in the "Extras" menu?

  • @LordkaBerlin
    @LordkaBerlin Рік тому

    thank you very much for the great explanation, it helped me a lot!

  • @vr180asmr
    @vr180asmr Рік тому +1

    Good video but the sound volume is very low for me.

  • @pxrposewithnopurpose5801
    @pxrposewithnopurpose5801 3 місяці тому

    what do you think about the restart ?

  • @GG-ii1uc
    @GG-ii1uc Рік тому +1

    Great info, thank you very much. Subbed :)

  • @diamondthree
    @diamondthree 9 місяців тому

    a year later and i still have that little upscale vs denoising chart as a jpg on my desktop for quick review

  • @mistermcluvin2425
    @mistermcluvin2425 Рік тому

    Thank you for this video, very good information!

  • @Feelix420
    @Feelix420 Рік тому

    hi, how many hires steps do i need to use to upscale by 2x? i keep getting errors

  • @ihavetubes
    @ihavetubes Рік тому

    mine creates a double image, meaning it creates in original than at 50% it breaks off and creates another image, sometimes with two people and never looking as good as the original, the second image gets the upscale and not the first.

  • @Feelix420
    @Feelix420 Рік тому

    i keep getting this when trying to do hires steps: RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 128 but got size 64 for tensor number 1 in the list.

  • @SmartKeyboard2011
    @SmartKeyboard2011 Рік тому

    why when I set Denoising below 0.75, everything get blur

    • @siliconthaumaturgy7593
      @siliconthaumaturgy7593  Рік тому +1

      I assume you are using a Latent upscaler (any upscaler with Latent in the name). I would use a non-Latent upscaler to see if that improves things

  • @TahuRock
    @TahuRock Рік тому

    Very helpful video, thanks!!

  • @LilCurlyBlonde
    @LilCurlyBlonde Рік тому +2

    Hello, perhaps you can help me, English is not my first language and although I understand most of it, concepts like "converging" & "fractualization" are hard for me to understand. What exactly do you mean, in laymens therms when you say that some of the samplers are converging ? I think I understand the fractualization part, it's just making some weird repeating patterns , right ?

    • @nio804
      @nio804 Рік тому +4

      Convergence means that the image approaches a "final form" that won't change with more steps, so high step counts just waste time.
      The non-converging samplers add randomness into their input, so the image keeps changing forever.

    • @siliconthaumaturgy7593
      @siliconthaumaturgy7593  Рік тому +4

      A fractal is a geometric pattern that continues as you zoom in/out on the object. For a famous example, see the Mandelbrot set.
      Here, it basically just means that a single subject starts getting split into multiple smaller subjects

  • @timovaringjarson
    @timovaringjarson Рік тому +1

    Hires fix can also have a different Sampler, different pos./neg. prompt so much left unsaid. : )

    • @LennyDadu
      @LennyDadu Рік тому +1

      can use a different prompt for the Hires. fix ?

    • @LennyDadu
      @LennyDadu Рік тому

      I found the option in settings/User interface : Hires fix: show hires prompt and negative prompt (requires restart)

    • @juliana.2120
      @juliana.2120 Рік тому +1

      dang thats good to know!

  • @cosciblog
    @cosciblog Рік тому

    Hi, do you know how i can upscale above x2? Everytime i try to create some images and want them to upscale to more than x1.9 times the resolution, i get out of vram errors.
    Base resolution 768x768px, Euler a, 30 Steps, Hires Steps 10 on RTX 3090

    • @Flashdog97
      @Flashdog97 Рік тому

      i upscale 1280x720 to 2560x1440 with hi-res-fix and I only have a 3060ti 8GB lol

    • @cosciblog
      @cosciblog Рік тому

      @@Flashdog97 i think i found the problem, didn't set --no-half-vae in webui-user.bat after that i get an output for 95% of my images, before that, around 40% where just black (testet with RTX 2060s, 3070 Mobile and 3090)

    • @Flashdog97
      @Flashdog97 Рік тому

      @@cosciblog also add --xformers to the bat. sped up my game by 3-times

  • @xitdedragon
    @xitdedragon Рік тому

    Really useful info!

  • @andresklagges460
    @andresklagges460 Рік тому

    Great video! It took me 1 hour to process this 8 minutes video. Weed doesn't help, but man that was a lot of amazing information. Thanks!

  • @menamariano
    @menamariano Рік тому +1

    The audio level is too low ! Its very hard to listen this on a cellphone. Thanks any way, nice video.

  • @airport_motels
    @airport_motels Рік тому

    how do you get a batch with labels like that sampler/steps, sampler/noise etc

    • @siliconthaumaturgy7593
      @siliconthaumaturgy7593  Рік тому +3

      There is a drop down near the bottom of the image generation called scripts. Select "X/Y" plot from the dropdown. My video on Prompt S/R kind of covers it (since Prompt S/R is used within in the X/Y plot)

    • @krzysztofczarnecki8238
      @krzysztofczarnecki8238 Рік тому

      @@siliconthaumaturgy7593 And there is a green book button on the right of the values box that lets you add all the existing, non-numerical values such as the sampler names, so you don't have to type them yourself, and you can delete the ones you don't want to.

  • @krolon9786
    @krolon9786 Рік тому

    and what about hires fixes like ESRGAN? are those the non-latent ones?

    • @Axodus
      @Axodus Рік тому

      Yes, those are the non-latent ones.

  • @rgb1996
    @rgb1996 Рік тому

    Thank you very much, really helpful.

  • @StygianStyle
    @StygianStyle Рік тому

    Does this allow you to generate at higher res than normal? my 6GB vram only allows up to 768 x 768.

    • @siliconthaumaturgy7593
      @siliconthaumaturgy7593  Рік тому

      I'm not sure whether hires fix reduces the amount of RAM needed for larger images, but I would guess it doesn't.
      The SD upscaler script in img2img might help since it breaks down larger images into tiles, but I haven't verified that either.

    • @oMEGa7420
      @oMEGa7420 Рік тому +1

      ​@@siliconthaumaturgy7593 i tested it (3 times already) on my 3050ti laptop gpu with 4gb vram and my resolution was 552x504 (sampler: dpm++ SDE Karras | Steps: 150) and upscaled it by 2 (R-ESRGAN 4x+ Anime6B | highres steps: 30 | denoise 0.33) and it worked just fine .. not sure if thats important, but it said smth about "Tile x/9" in my console. Also: i start automatic1111 with "--medvram" and "--xformers" (not sure about xformers, might delete it again, but medvram will stay :D)

  • @bentontramell
    @bentontramell 4 місяці тому

    I think LORAs can hasten image degradation the second time through and lead to crispiness.

  • @mattmunroe4928
    @mattmunroe4928 Рік тому

    Cloning happens on almost all my upscales. That is an image of a man AND a woman, or a character and a croud in the background. In these cases almost all my upscales make all the faces the same.

  • @thanhlam5126
    @thanhlam5126 Рік тому

    7:16

  • @itycagameplays
    @itycagameplays 9 місяців тому

    Your sound is too low.

  • @mightymouse5930
    @mightymouse5930 11 місяців тому

    Could you please turn the volume down more, that way I can officially blow my ears out on the next video instead of just going def.... thanks...
    Learn to encode audio.

  • @yazumato
    @yazumato Рік тому

    i came here to watch acutaly someone press the button and say what it does, instead i saw alot of pictures, dissapointed

  • @vulubalulubalulu
    @vulubalulubalulu Рік тому

    you video is too long man. You need to divide it into two parts. in a minute here i what matters: 1. 2 . 3.. then you can go into depth of each part.

  • @doyen86
    @doyen86 Рік тому +5

    Hi, you're doing a good service here. I don't mean to be rude but might I suggest maybe dialing back some of the technical stuff. I think you would get a lot more viewership if you just kept it really simple with examples of your experiments and a simple synopsis of recommended settings and reasons for those settings. Not trying to be a jerk just giving some unsolicited practical advice. The name of the channel is a bit complex as well, don't know if u plan on doing mostly AI content but it's hard to remember and hard to search. Again no disrespect just some things to consider. Thank you for this information.

    • @audiogus2651
      @audiogus2651 Рік тому +11

      I say keep it techie and people just need to catch up to you, siliconthingamajiggy. There is no 'one set of params fits all'.

    • @siliconthaumaturgy7593
      @siliconthaumaturgy7593  Рік тому +5

      I do understand that a lot of people just want the final settings instead of the technical details, so I have a comment in the video description of where to go if you just want to see that. For this one, it starts around 7 minutes.

    • @hobologna
      @hobologna Рік тому +22

      I disagree. In the age of AI when everyone is slamming faceless accounts with the same redundant content everyone is pulling from chatbots, I'm glad he's pumping out technical content with actual value.