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

[@Nitrate1984]

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

[@kapytanhook]

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.

[@adriennef9758]

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

[@SlickSonicTitan]

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.

[@frangimenez4674]

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!

[@edphonez]

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

[@Kryptonic83]

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.

[@TheBoomurdead023]

Really well made and helpful. Thank you so much!

[@siliconthaumaturgy7593]

Thanks! I'm glad you enjoyed

[@ArtificialBeauties]

all your videos are amazing !!

[@achiche1337]

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

[@slashkeystudio]

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]

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.

[@LordkaBerlin]

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

[@BoldMold]

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.

[@GG-ii1uc]

Great info, thank you very much. Subbed :)

[@mistermcluvin2425]

Thank you for this video, very good information!

[@TahuRock]

Very helpful video, thanks!!

[@daffertube]

Thank you

[@camilo3626]

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

[@xitdedragon]

Really useful info!

[@andresklagges460]

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!

[@diamondthree]

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

[@NanamiKairyu]

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

[@rgb1996]

Thank you very much, really helpful.

[@FilthxSpewer]

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

[@autumndev]

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

[@Tresdin.7]

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

[@timovaringjarson]

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

[@LennyDadu]

can use a different prompt for the Hires. fix ?

[@LennyDadu]

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

[@juliana.2120]

dang thats good to know!

[@pxrposewithnopurpose5801]

what do you think about the restart ?

[@dmitrymyshkov811]

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.

[@twilightfilms9436]

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]

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

[@KirigayaKazuto.]

...

[@Joniyah444]

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

[@Feelix420]

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

[@vr180asmr]

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

[@Feelix420]

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.

[@menamariano]

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

[@LilCurlyBlonde]

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]

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]

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

[@cosciblog]

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]

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

[@cosciblog]

@@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]

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

[@ihavetubes]

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.

[@SmartKeyboard2011]

why when I set Denoising below 0.75, everything get blur

[@siliconthaumaturgy7593]

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

[@krolon9786]

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

[@Axodus]

Yes, those are the non-latent ones.

[@StygianStyle]

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

[@siliconthaumaturgy7593]

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]

​@@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)

[@airport_motels]

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

[@siliconthaumaturgy7593]

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]

@@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.

[@bentontramell]

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

[@mattmunroe4928]

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]

7:16

[@itycagameplays]

Your sound is too low.

[@mightymouse5930]

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]

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

[@doyen86]

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]

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]

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]

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.

[@vulubalulubalulu]

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.