SDXL 1.0 - SUPER FAST Render Times + Google Colab Guide

SDXL 1.0 ComfyUI Guide. Render SDXL images much faster than in A1111. Only 9 Seconds for a SDXL image. Also: Google Colab Guide for SDXL 1.0 with ComfyUI. No GPU needed!!!!

#### Links from the Video ####

00:00 Intro
00:35 ComfyUI Setup
02:41 Load SDXL Nodes in ComfyUI
04:04 Loading ComfyUI Models
05:50 SDXL 1.0 Node Build Explained
10:20 Google Colab Units
11:09 Google Colab ComfyUI Setup
13:43 Load ComfyUI SDXL Build into Google Colab

[wpahp]

this json file doesn't have a lora node, is there an sdxl json that has lora?

[burghardvonkarger]

How can I upscale with SDXL? I tried adding a second pair of KSamplers, but when I feed the output of the first refiner (after VAE Decode, Upscale and VAE Encode) into the second BASE KSampler, first thing I notice, there is no denoise setting. Second thing, If I run it I get a runtime error.
So has anybody worked out already, how to upscale to 4k? Right now, the only way I know how is to use Ultimate SD Upscale with an 1.5 model, but that is, of course, not ideal.

[MysteryGuitarMan]

Thank you for talking about our model! Glad you're a fan, and glad you're talking about Comfy! This is by far the preferred way from us.

This, coming from an Auto1111 fanboy who has recently switched over...

[petEdit-hl]

Pls how can i add the comfyui manager to the Google colab comfyui, pls help😢

[carnacthemagnificent]

I have a 3080ti (laptop version) with 16 GB VRAM and A1111 was choking on SDXL for some reason. It ran great ... until it didn't. Then reload, go for a while until the memory filled up, etc. So I tried Comfy UI. Running with the checkpoint and the refiner at same time and VRAM utilization is only around 35-40%. Amazing improvement for memory and speed when you consider it includes the refiner in each pass as well. Not sure I can stick with this UI and figure out things like extensions when we get them but for now I'm a believer.

[KeredaSmile]

Rember, after change path you have to "restart gui", co X and run gpu again.... a was use refresh and lost 2 hours to find a bug in my path...

[Illusiongraphy]

How train models using SDXL1.0 with Automatic1111? I can't figure it out.. is there any way to train models with SDXL1.0?

[Elwaves]

Nice video Olivio. FYI, if you don't want to drag and drop an image into the workspace, you can use the Load button.

[kinijustforfun]

How can i add face correction? That is really a problem? Hallo Olivio, bin ein großer Fan von Dir. Wie kann ich die Facekorrektur hinzufügen. Ich finde die Augen teilweise katastrophal, genauso wie die Hände leider auch noch nix sind...

[kelvinzhao]

Does anyone know if there is a way to train a Lora or Dreambooth for SDXL on collab?

[ragnarlothbrok]

i dont like comfyui, it is not comfy at all

[grantmccotter]

Thanks for the great video!

Do you know how to load in models that aren't a part of the original list? I tried pasting the url in the section with all the models and left out the #. It downloaded but it's not showing as an option in the load base checkpoint window. only the sd xl base and refiner is showing as an option

[benoitcorvol]

Hello everyone, wondering why it took 25s for him with a V100 and myself 1min with an A100 ? ^^thank's for the video as usual it's very helpfull

[Steamrick]

Hey Olivio - check out changes in how prompts are weighed in SDXL.
In SD1.5 giving a token a weight of 2 was asking for trouble - in SDXL you can go as far as a weight of 5 for some tokens and at least 3 for most.

[TheAries]

Unfortunately i get repeated images.. Would lowering the denoising in the ksampler fix this problem?

[krystiankrysti]

Comfy is slower than AUTO!11 by half, it does not use xformers properly or at all, i get 1.7 secs in auto11 but get 3.50 in comfy, same setings

[shabadooshabadoo]

I have a 1080Ti and this is taking 115 seconds to render.. hmm I wonder if its just a card difference or something else.

[OnyxLee]

How to download checkpoints and lora from civitai to Google colab? Does this eat up your Google drive space?

[KarolDecyk]

When i render this standard prompt with this bottle then it render really fast (i have geforce 3080 in my laptop) but as soon i change prompt then its take way way longer to render. Can someone explane me why? Can i fix it or am i doing sm wrong?

[xlpcx]

Hi, how can I load some LORAS from cvitai for SDXL in the colab notebook?