No video :(

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

Подписаться 4,8 тыс.

Просмотров 40 тыс.

50% 1

This video explains what the HiRes Fix in the Stable Diffusion Automatic1111 Web GUI is useful for, describes how the feature works, then identifies which settings are important and what the appropriate range for these settings are to ensure you can consistently generate good images.
Overview of Hires Fix - 01:05
Methodology - 01:40
Steps and Samplers - 02:13
Denoising - 03:40
Upscaling - 04:29
Upscalers - 04:50
Recommendations - 06:40
Settings Chart - 7:10
#aiart #stablediffusion #upscaling #automatic1111
Link to Google spreadsheet with the figures shown in this video as well as some useful prompt constructors. It is read only, so make a copy for yourself if you want to use the constructors.
docs.google.co...

Опубликовано:

28 авг 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 69

@edphonez Год назад

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

@adriennef9758 5 месяцев назад

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

@frangimenez4674 Год назад

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!

@kapytanhook Год назад

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.

@SlickSonicTitan 6 месяцев назад

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.

@Nitrate1984 Год назад

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

@slashkeyAI Год назад

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 Год назад

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.

@Kryptonic83 Год назад

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 Год назад

Really well made and helpful. Thank you so much!

@siliconthaumaturgy7593 Год назад

Thanks! I'm glad you enjoyed

@achiche1337 Год назад

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

@BoldMold Год назад

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.

@diamondthree 5 месяцев назад

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

@LordkaBerlin Год назад

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

@ArtificialBeauties Год назад

all your videos are amazing !!

@daffertube Год назад

Thank you

@vr180asmr 11 месяцев назад

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

@mistermcluvin2425 Год назад

Thank you for this video, very good information!

@NanamiKairyu Год назад

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

@GG-ii1uc Год назад

Great info, thank you very much. Subbed :)

@Tresdin.7 8 месяцев назад

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

@TahuRock Год назад

Very helpful video, thanks!!

@rgb1996 Год назад

Thank you very much, really helpful.

@menamariano 11 месяцев назад

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

@andresklagges460 Год назад

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!

@FilthxSpewer 6 месяцев назад

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

@xitdedragon Год назад

Really useful info!

@timovaringjarson Год назад

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

@LennyDadu Год назад

can use a different prompt for the Hires. fix ?

@LennyDadu Год назад

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

@juliana.2120 11 месяцев назад

dang thats good to know!

@dmitrymyshkov811 8 месяцев назад

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.

@autumndev Год назад

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

@bentontramell 3 дня назад

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

@Feelix420 Год назад

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.

@twilightfilms9436 6 месяцев назад

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?

@camilo3626 Год назад

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

@ihavetubes Год назад

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.

@achiche1337 Год назад

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

@KirigayaKazuto. Год назад

...

@LilCurlyBlonde Год назад

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 Год назад

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 Год назад

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

@Feelix420 Год назад

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

@SmartKeyboard2011 Год назад

why when I set Denoising below 0.75, everything get blur

@siliconthaumaturgy7593 Год назад

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

@cosciblog Год назад

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 Год назад

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

@cosciblog Год назад

@@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 Год назад

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

@krolon9786 Год назад

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

@Axodus Год назад

Yes, those are the non-latent ones.

@mattmunroe4928 Год назад

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.

@hplovecraftmacncheese Год назад

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

@siliconthaumaturgy7593 Год назад

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 Год назад

@@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 Год назад

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

@siliconthaumaturgy7593 Год назад

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 Год назад

@@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.

@thanhlam5126 Год назад

7:16

@itycagameplays 5 месяцев назад

Your sound is too low.

@mightymouse5930 7 месяцев назад

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.

@doyen86 Год назад

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 Год назад

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 Год назад

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 Год назад

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.