SDXL - BEST Build + Upscaler + Steps Guide

Рет қаралды 51,053

11 ай бұрын

Here is the best way to get amazing results with the SDXL 0.9 Model. How to use the Prompts for Refine, Base, and General with the new SDXL Model. What Step Ratio is best for SDXL Base and SDXL Refiner rendering. Getting the most out of your SDXL images with a 2-step upscale to 4096 with ultra high quality. A special SDXL ComfyUI Build that you can download and use right now for free!
#### Links from my Video ####
MY SDXL Comfui Build: drive.google.com/file/d/1Y5ji...
(Drag this image into your ComfyUI Canvas to load the nodes!!!)
Stable Diffusion Discord: / discord
SDXL Base Model huggingface.co/stabilityai/st...
SDXL Refinder Model huggingface.co/stabilityai/st...
1x Skin Detailer Upscaler (load pth and yaml into same folder) drive.google.com/drive/folder...
4x NMKD Upscaler huggingface.co/gemasai/4x_NMK...
4x Ultrasharp Upscaler mega.nz/folder/qZRBmaIY#nIG8K...
Upscaler Database (Check HERE if other links are dead!!!!) upscale.wiki/wiki/Model_Database
ComfyUI Download: github.com/comfyanonymous/Com...
What to watch next:
ComfyUI install guide: • ComfyUI - Node Based S...
ComfyUI Best Builds: • LATENT Tricks - Amazin...
#### Join and Support me ####
Buy me a Coffee: www.buymeacoffee.com/oliviotu...
Join my Facebook Group: / theairevolution
Joint my Discord Group: / discord

Пікірлер: 134

@OlivioSarikas 11 ай бұрын

#### Links from my Video #### MY SDXL Comfui Build: drive.google.com/file/d/1Y5jiWd3G3VNixNGPOD9QDjJ8B-FGOcuk/view?usp=sharing (Drag this image into your ComfyUI Canvas to load the nodes!!!) Stable Diffusion Discord: discord.gg/stablediffusion SDXL Base Model huggingface.co/stabilityai/stable-diffusion-xl-base-0.9 SDXL Refinder Model huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9 1x Skin Detailer Upscaler (load pth and yaml into same folder) drive.google.com/drive/folders/1VkT6tpbCPn2gKZYPtawDJGMpLg6EyRpO 4x NMKD Upscaler huggingface.co/gemasai/4x_NMKD-Siax_200k/tree/main 4x Ultrasharp Upscaler mega.nz/folder/qZRBmaIY#nIG8KyWFcGNTuMX_XNbJ_g Upscaler Database (Check HERE if other links are dead!!!!) upscale.wiki/wiki/Model_Database ComfyUI Download: github.com/comfyanonymous/ComfyUI

@HarryHeck2020 11 ай бұрын

I wonder if you could use a 1.5 model for the input and the SD_XL_refiner to refine them?

@mufiku 11 ай бұрын

So your SDxL Comfyui build is an output image of the guy in the forest? Could you help me understand how it work? P/s: just finished the video, I get it. Thanks Olivio! You're the best!

@elbistv 11 ай бұрын

You've didn't share the Comfui Build the link is providing us to an Image @Olivio Sarikas

@mufiku 11 ай бұрын

@@elbistv Drag that image to ComfyUI, it will load everything. Other upscale files and stuff, send it to "model\upscale_model" folder.

@patagonia4kvideodrone91 11 ай бұрын

greath video! Comfyui is fantastic, have a cuestion, how can add fix faces? or some extensions?

@rishdot1 11 ай бұрын

Deep fried is a specific visual style. It comes from deep fried memes where an image is shared so much on social media platforms where it gets compressed multiple times it creates a pixelated over sharpened look. Having it mentioned in the negative prompts prevents low quality renders.

@OlivioSarikas 11 ай бұрын

really? lol, that's cool. never heared of that

@baddealrage 11 ай бұрын

Wow amazing work. I was a little bit disapointed when I noticed that the same prompt from the official website returned pictures that were miles better. I can't wait to download these files and see how I can improve my images with the additonal quality prompts.

@PaulByrd1 11 ай бұрын

Amazing rundown on comfy and SDXL! Wanted to say thank you for expanding the flow of knowledge. Keep killing it🙌🏾🙌🏾🙌🏾

@OlivioSarikas 11 ай бұрын

Thank you very much :)

@pauloparanhos846 11 ай бұрын

Thank you my friend for the kindness of sharing so much knowledge, in such an easy way

@ahminlaffet3555 11 ай бұрын

Thanks, another great video. Never tried ComfyUI, really should :)

@griftgfx 11 ай бұрын

I don't mean any offense by this, but sometimes when you say "CFG scale" I hear "sea of cheese" and it makes me chuckle.

@louisswift3437 11 ай бұрын

you're right

@keisaboru1155 11 ай бұрын

Zat's cherman accent for ya 😂 (German)

@subduction3876 11 ай бұрын

Brilliant! This is what I’m calling it from now on

@jzilla1234 5 ай бұрын

A Sensible chuckle, i hope

@-invisio 11 ай бұрын

Very good video,.... and thank you for your "easy english" vocabulary -> Although your explanations are very precise, they remain totally comprehensible for those with a very average level of English.

@avazgaziz 11 ай бұрын

thanx for such good teaching!

@NATO_B_XATY Ай бұрын

Thank U for this video 🙏

@dcpuzzles2990 11 ай бұрын

Always enjoy your videos and learn a lot of useful info. I saw in this video that you were putting the 4x upscaler into the comfyUI folder structure - I wondered whether you were aware of the extra_model_paths.yaml file in the root of the ComfyUI folder structure. This allows you to use your existing models from an A1111 install within ComfyUI by just putting the path to your A1111 installation into this yaml file - then ComfyUI adds the paths to its local paths when ComfyUI loads. This means you can keep putting all of your various models into a single folder structure but use them from both A1111 and ComfyUI. Forgive me if you have already included this in one of your videos, but if not, it is a handy thing to know and you could pass it on in an upcoming video.

@winstonwoof732 11 ай бұрын

Appreciate the shoutout but even better was seeing my image of an eye as the thumbnail :)

@juridjatsenko2013 8 ай бұрын

looking great! How do you add Loras to this workflow?

@dannyvanlaarhoven 11 ай бұрын

Awesome again

@funnerisaword 11 ай бұрын

Hi Olivio! Awesome tutorial thank you so much for holding my hand through the whole process. Your tutorials are always clear and thorough! ❤ I watched your Lora training video but my dataset is too large for my my hardware to train within a reasonable timeframe. Can you please, please, please make a tutorial for training LoRA’s using a cloud gpu like colab, preferably focusing on training a concept with thousands of training images. Thanks again friend!🎉

@chadcrypto2675 11 ай бұрын

Thanks, this is awesome.

@Zer0Wulf1337 Ай бұрын

You explained that really well 👍🏼 sub’d

@swannschilling474 11 ай бұрын

Thanks a lot, might try to set it up...the nodes seem to be a bit hard to use, but its probably just a matter of spending some time to try how it works! 😊

@thecorgisbobandgeorge 11 ай бұрын

Thank you so much! ComfyUI is amazing. It is soooo much faster than Automatic1111 and Vlad! Anything over 768x768 on either of those gives me an out of memory error. ComfyUI has never given me one! This thing is amazing.

@funnerisaword 11 ай бұрын

Hi! How much vram do you have? Do you think I can run this in my 6gb rtx 2060?

@hecophoto 11 ай бұрын

@@funnerisawordYes you can, I've been trying on 1050 TI 4gb vram

@launcelotgobbot7354 11 ай бұрын

Put in webui-user.bat, at set COMMANDLINE_ARGS, - - medvram. (Automatic1111)

@funnerisaword 11 ай бұрын

THANK YOU!!! 🫡

@VivinPaliath 11 ай бұрын

This is great! Thank you for this. I found it very easy to follow your instructions and to set up the workflow is ComfyUI; and this is my first time using ComfyUI! I ran into an interesting issue though. I notice that if I do 60 steps overall, with the refiner starting at 32 steps, it works. But if I up the refiner step to start at step 40, for example, all I get is a black image from the output of the refiner. Any idea what could be causing that to happen?

@mynameizj1 11 ай бұрын

This is great 👍 would be nice to see how it makes a "rug made of souls" 😂 Sorry had to do this as I kept seeing this request by chat and had no idea what it meant 😅

@ahlokecafe_articulate 11 ай бұрын

Hi Olivio. Recently automatic 1111 updated the way the training models works and I was following your tutorial but lost my steps as it was totally revamp on how it looks now

@AAbasel 11 ай бұрын

thank you @OlivioSarikas, do you have any idea how to use the SDXL Styles?

@nic-ori 11 ай бұрын

Thanks.

@testales 11 ай бұрын

Can you do the upscaling also in latent space? In A1111 I'm bascially only using this method as it upscales the image where it's created and that results always in a better quality than any upscaler working in pixel space.

@musicandhappinessbyjo795 11 ай бұрын

Hope to know more about how to add Lora's and many other thing such as control net into Comfy UI. I do know that you already have a tutorial describing each but haven't seen a build(for SD 1.5 models) which almost works like Auto1111

@SeanRynearson 11 ай бұрын

Is there a node I can connect to the subject prompt so that I can put a list of prompts in?

@yakuza25rus 11 ай бұрын

Is it possible to add roop in this setup for changing faces after generation?

@EuphoricDreamSequence 11 ай бұрын

Hi I have 2 questions: 1- My Comfy UI doesnt have some of these boxes... I installed it yesterday 2- Where do I download the refiner and upscalers from?

@RamonGuthrie 11 ай бұрын

Just looking at all those nodes makes me think of Houdini and Nuke and my head just wants to explode 🤯💢

@chadcrypto2675 11 ай бұрын

It's noodle time!

@jpgamestudio 11 ай бұрын

Hello brother, what is the function of the "clip space "on the menu on the right?

@thatwittyname2578 11 ай бұрын

after refiner stage, encode image back to SD 1.5, run through your favorite 1.5 model again with a lora like more detail, low denoise .2 works well, then run through your upscalers.

@forgottenwisdoms 11 ай бұрын

do you have a workflow I could see?

@thatwittyname2578 11 ай бұрын

@@forgottenwisdoms its just rerouting the finished SDXL back through a normal 1.5 gen process

@alborzdesign 11 ай бұрын

fantastic video as always. Thank you! A couple of questions about comfUI does is support controlnet? how bout inpaint/outpaint? is it possible to only re-run the process of specific parts? for example, if I generate an image with the base and refiner, and want to test 10 different upscalers. can I only re-run the upscaler and not generate a new image from scratch?

@ebrahimchalhoub9313 11 ай бұрын

Yes

@alborzdesign 11 ай бұрын

@@ebrahimchalhoub9313 Thank you. I'm going to switch from A1111 to ComfUI since it looks a lot more flexible. Have you found any limitations that force you back to A1111 yet? any workflows that you think are not properly supported yet?

@funnerisaword 11 ай бұрын

⁠@@alborzdesignI would like to know this as well. Comfy UI just seems like the most economic choice. I have many extensions in automatic that I use daily, (adetailer, multi controlnet, latent couple, composable lora, inpaint anything). If I can use these in comfy then there is no reason for me to return to automatic1111

@ebrahimchalhoub9313 11 ай бұрын

As far as i know, no. Comfyui can be an upgrade to a1111 you can have much finer control over what you do and can go very crazy with stuff . It is almost like programming SD but in a visual way.

@user-bn8dj3vt7f 10 ай бұрын

I downloaded a checkpoint model for SDXL and I can see that it's in the checkpoint, but when I go to select it to use it, it doesn't select it. All SDXL related checkpoints have the same problem. I see it, but I can't select it, so I can't use the SDXL checkpoint. How do I fix it? It's the same on both my laptop and my PC at home. Thanks.

@nickolaygr3371 11 ай бұрын

how to set up upscaler size like 2x? or 1.5? not 4x

@StargateMax 7 ай бұрын

How can I get the "SDXL Refinder Model" then? I see lots of "downloads" there, but no download link or button exists anywhere...

9 ай бұрын

I there a way to only upscale 2 times with this json?

@thatboyp444 11 ай бұрын

hi! what kind of GPU do you have?

@UrfanFahada 11 ай бұрын

let me know if you know plugins to make cable from curve to perpendicular? thank you :D

@Paulo-ut1li 11 ай бұрын

Is there a Comfui SDXL Colab Notebook?

@EH21UTB 11 ай бұрын

Can you tell me what the ascore in the clip condition nodes does and why did you set different values for Pos and Neg? I like to take the output from SDXL, upscale and then resample using a SD1.5 model with low noise settings - and I'm using one of the iterative WAS nodes for this. That way I can also use the loras etc that are already available. So it's kind of like img2img starting with SDXL and finishing with SD1.5. I tested about 20 upscaler models and also liked the 1xSkinLite, but several other models are nice too. As you note each one alters the images - so you can just use the 1xskin and then bicubic or lanzos upscale after before resampling for possible better results. There's no real all-in-one upscaler model though.

@MrCorpsy6 11 ай бұрын

After some hours of testing, this node does absolutely nothing. It's not in the official workflow, by the way. The other similar node made for the base model has some importance though. I've found that a width and a height of 1024 is better than 4096, but a target_height and target_width of 4096 seem better than 1024.

@timfarnham 13 күн бұрын

The image in the link (MY SDXL Comfui Build:) is a man's face. I can't seem to find the workflow to drag in. Help please :)

@michaelbayes802 11 ай бұрын

Hi olivio, I tried loading the flow into my comfyui but it did not recognize the two steps "CLIPTextEncodeSDXL" and "CLIPTextEncodeSDXLRefiner" any tips how to get these node types?

@OlivioSarikas 11 ай бұрын

you probably need to update your comfyui. i think using the update.py in the update folder should do the trick

@utuk3333 11 ай бұрын

The first image is generating, but after that I get an error that says "with safe_open(filename, framework="pt", device=device) as f: safetensors_rust.SafetensorError: Error while deserializing header: InvalidHeaderDeserialization." Anybody know what that means? Never mind - figured it out. One of my upscale models was corrupted.

@Aaabii 11 ай бұрын

Thank you very much for the video . But i must say that ( even though some comments says that your workflow is suboptimal) the json file you gave us produce the same of even better results from this one . This has only has an advantage of an upscaler . Can you add the upscaler part to it please ? Having 3 inputs is really weird ...

@OlivioSarikas 11 ай бұрын

you can simply copy my upscaler nodes from one to the other. Just open up comfyui in two different tabs and load the different builds and then select the nodes and copy them over

@pointandshootvideo 11 ай бұрын

What a PITA. The pain of early adoption. I think I'll wait for this to be less 'complicated.' But thanks for this video!

@Aerogelatina 9 ай бұрын

I never managed to drag and drop, it doesn't work for some reason and I can't find a solution anywhere. Does anyone have any idea?

@mrparadox6878 11 ай бұрын

Hi olivio,I did everything you've told,but I get just weird shapes

@RamonGuthrie 11 ай бұрын

Hey does anyone know how to update xformers in ComfyUI?

@AwesomeDailyVlog 11 ай бұрын

Hmm i still using Leonardo.. 😢😢

@tildebyte 11 ай бұрын

@olivio kudos on promoting Comfy; it's definitely the power-user's tool :)

@Tussorte_Dhaffer 11 ай бұрын

What is the minimum requirement to run this locally ?

@Silver_Nomad 11 ай бұрын

So... I'm curious now, how A1111 is going to completely rework it's UI for double model layout...?

@dragonmares59110 11 ай бұрын

By updating and breaking itself for days/weeks like usual. This is why a lot of people are not bothering updating it anymore.

@HolidayAtHome 11 ай бұрын

Tried out the updated node setup.... but your old "wrong" setup gives me more te results I want. It may not be the intentional way to use it, but it's far more successful to generate the targeted result, at least for me at the moment =)

@OlivioSarikas 11 ай бұрын

it's ok to use the other setup. whatever get's you the results you want is the right way for you

@HolidayAtHome 11 ай бұрын

@@OlivioSarikas I'm kind of glad that auto1111 is so slow with the implementiation. Otherwise I would have never tried ComfiUI and its posiibilities to use the same model in different ways. I'm feeling kinda like Bob Ross, using a spattle instead of a pencil to make my paintings =D

@Sebastian78120 11 ай бұрын

So SDXL is a better version of automatic1111 for better images ? I don't understand what is it X)

@dcpuzzles2990 11 ай бұрын

SDXL is the latest update of the Stable Diffusion model itself that actually creates images from text. The expectation is that the images generated by SDXL will improve upon those that are currently produced by Stable Diffusion 1 and 2. Automatic1111 is a web app that allows you to easily use the Stable Diffusion models and gives you the controls you need to make the settings that determine how the model works - A1111 doesn't generate the images, the Stable Diffusion model that you select in A1111 does that. Unfortunately, SDXL works differently from the previous Stable Diffusion models, in that SDXL generates an initial result in the Base model and then passes this to a second model called the Refiner, which adds more details to the image created by the Base. As this 2 part generation is different from the previous versions, A1111 is not currently set up to handle this process and so we are having to use other methods to use SDXL - such as ComfyUI - this is because you are able to manufacture a method within ComfyUI that can handle the 2 step process, as shown by Olivio in this video. I am sure that A1111 will be updated at some point to handle SDXL, but for now we have to use the alternatives. Hope this makes sense and answers your question.

@Sebastian78120 11 ай бұрын

@@dcpuzzles2990 Yes, thank you ! I hope SDXL will be available to automatic1111 one day :3

@PaceTheAce 8 ай бұрын

@@dcpuzzles2990 There are actually some SDXL Models that doesn't need a refiner. Like for example ProtoVision I think

@saltygamer8435 11 ай бұрын

what happened to automatic 1111??????? Catching up on AI art generations 2 months later, feel like a lot has changed quickly. Can you please make an update video Oilivio

@CitizUnReal 11 ай бұрын

a1111 is still very much present. with oobabooga_a1111 now even in the llm department also. it just so happens that the two events of 1) a leaked stable diffusion xl (which is only running on comfy.ui and vlad (a1111 fork) for now) coincided with 2) your return to the community. but you should definitely update your sdwebui :)

@Zidane852 11 ай бұрын

The SDXL model cant using it on A1111?

@vallejomach6721 11 ай бұрын

Not this version...but this is not the full final release version of SDXL. That releases next week.

@KolTregaskes 11 ай бұрын

The "MY SDXL Comfui Build" link goes to a photo, a very nice photo but I was expecting a JSON file perhaps? Or am I misunderstanding?

@Schattenmeister 11 ай бұрын

me too

@OlivioSarikas 11 ай бұрын

watch my video ;) You need to drag it into the canvas to load the build

@KolTregaskes 11 ай бұрын

@@OlivioSarikas Oh OK, that's weird that works.:-) Ta.

@TurbineFlyer 11 ай бұрын

Incoming all the comments of "I will just wait for A1111"

@alexgilseg 11 ай бұрын

Thats me...

@wedontexist369 11 ай бұрын

What is A1111

@Steamrick 11 ай бұрын

Alternatively, "I will just wait for the SDXL 1.0 model"

@TheSpaceman1972 11 ай бұрын

I‘m using Vlad with SDXL right now. 😜😅

@raioxnoticias 11 ай бұрын

I just want to know how to run the refine without my pc going crazy and slow and glitch......gtx 2060 super 8gb, any config or tricks please ?

@OlivioSarikas 11 ай бұрын

in A1111 use the SD upscale in scripts, because that will render it in smaller tiles

@metanulski 11 ай бұрын

Still, If I see ComfyUI, I see Chaos

@JoseGabrielMattaGonzales 11 ай бұрын

¿cuanta vram pide?

@yourvenparianen5390 11 ай бұрын

Idk....i would prefer a simpler more user friendly interface like automatic 1111 for this.

@23dsin 11 ай бұрын

Ok but how/how much is better than SD 1.5? It's for sure better but will be great to see some SD battle side by side. ;)

@ozerune 11 ай бұрын

It's better than base 1.5 but I don't believe it's anywhere near the quality of the things FOR 1.5. If we come back in a couple weeks we'll have some amazing SDXL models

@x1c3x 11 ай бұрын

If I'm not mistaken SDXL is a 1024 model, no? A lot of quality comes just from that too.

@ozerune 11 ай бұрын

@@x1c3x Yes but you can already get to 1024x1024 easily in 1.5 with upscaling. Especially Ultimate SD Upscaler

@x1c3x 11 ай бұрын

@@ozerune is not just about the final res, but base res of 1024 is high. Specifically, when i prompt at 1024x1024 in normal SD the double heads and double everything is very common, and needs neg prompts. Base 1024 does not.

@oaahmed7515 11 ай бұрын

But is it possible to work in a way other than the nodes, these lines bother me. Is there a way like SD?

@OlivioSarikas 11 ай бұрын

you can also run it in vlad diffusion

@adventuresinportland3032 11 ай бұрын

Lookingforward to when this becomes available for Automatic1111. Unfortunately ComfyUI is just too complicated for me.

@mirek190 11 ай бұрын

LOL A111 is to too complicated

@adventuresinportland3032 11 ай бұрын

@@mirek190 For me it's all the node based stuff with the hundreds of connections. Can't seem to wrap my head around it. Might be a generational thing though, not sure (older Millennial here).

@akairas6 11 ай бұрын

@@adventuresinportland3032 i dont like comfyUI either

@Barbaqur 11 ай бұрын

How did you add text input to cliptextencodesdxl module? I can't wrap my head around it, I'm trying to do Clip area composition with no luck. thanks for the video

@dcpuzzles2990 11 ай бұрын

If you right click on any of the nodes with parameters the right click menu gives you the ability to change any of those parameters into inputs - I struggled with this to start with. Hope this helps.

@rando6836 11 ай бұрын

There's zero point in using the base model right now vs SD 1.5.

@mschf_nft2581 11 ай бұрын

SDXL not worth it if you're a casual (yet). slow even on 4080. Literally 5 minutes for this image above and ended up with 4 arms

@qaesarx 11 ай бұрын

I dont want Comfy... as long as A1111 is not updated i dont switch.

@maxstepaniuk4355 11 ай бұрын

Trash all those upscalers. Connect the resulting image to Swinir upscaler and run upscaled result through skindiffdetail 1x upscaler.

@55bess 11 ай бұрын

This is macrame.

@OlivioSarikas 11 ай бұрын

almost, yes 😂

@samuelk.2793 11 ай бұрын

@OlivioSarikas, it seems that your goal of posting a video every day is not benefiting you. This particular video exemplifies a focus on quantity over quality, as it lacks any meaningful content. It appears that you are simply reading comments from the ComfyUI nods, and it's doubtful whether you prepared for this or found inspiration from the Discord community. Please understand that my intention is not to offend you, but rather to provide an observation based on your channel over the past few months.

@frankschannel2642 11 ай бұрын

Olivio, I luv ya but you are really >>>TERRIBLE

@OlivioSarikas 11 ай бұрын

bro, i even put the calculation into the video: 25 - 20% = 20 If you are as good at math as you think, you should probably know that a minus percentage is always lower than a plus percentage because the total that the percentage is applied to is larger... duh

@deema7345 11 ай бұрын

well those examples at the beginning aint amazing at all tbo))

@OlivioSarikas 11 ай бұрын

only the best for you, my friend

@vallejomach6721 11 ай бұрын

Don't forget that a) this isn't a final release build and b) it's the bog-standard base model. You need to base your quality comparison with it to what the base SD1.5 model can produce. (v1-5-pruned-emaonly.ckpt or w/e it's called)

@deema7345 11 ай бұрын

@@vallejomach6721 yes yes, i will patiently wait until that shiet drops))