SDXL Base + Refiner workflow using ComfyUI | AI art generator

🙂‍ In this video, we show how to use the SDXL Base + Refiner model.
🤔 I also made the point that the refiner model does not improve my images much, so I don't use it. Whether or not you use it is entirely up to you.
🙃 I also introduce a few new options, such as clip last layer and KSampler advanced.

👉 Get ComfyUI SDXL workflow templates at this link,

👉 Get my personal ComfyUI SDXL workflow template at this link,

Chapters
00:00 Introduction
02:08 A1111 and ComfyUI documentation
02:54 Let's work with SDXL using ComfyUI default workflow - SDXL base
05:31 Remember always to use the recommended image dimensions of the model
06:09 A fantastic outcome without the need for the refiner or fancy workflows
06:32 What about using a latent image larger than the dimensions of training images?
08:55 Horsing around with the different options
15:31 What is the meaning of the clip last layer?
19:58 Let's add the refiner step
27:49 To refine or not-to-refine?
29:32 Advanced Ksampler options
32:48 Let's add some order to our canvas
33:39 Let's use the fancy SDXL refiner workflow
38:26 Visitinragain the SDXL model card - Recommended refiner values
42:02 Final remarks

SDXL-Turbo Model Card

ComfyUI

ComfyUI Community Manual

A1111 Features - Some documentation

ComfyUI Workflows

Custom Nodes, Extensions, and Tools for ComfyUI

Other links:

****************************************************************************

Wolʇ Dynamics, your reliable partner for CAE solutions,
CAD and solid modeling → Meshing → Simulations → Automation and optimization → Post-processing → Data analytics and ML → Reporting

Why Wolʇ Dynamics? Simply look at our banner - notice how the F appears backwards.

Wolʇ Dynamics ↔ Flow Dynamics 😯+💣=🤯

****************************************************************************

👉 Subscribe and hit the bell to see new videos:

🖖 Join our channel to help us create more content. By joining our channel, you can also get access to perks:

Follow us:

#ai #aiart #aiartgenerator #SDXL

[TectonicTechnomancer]

Commas are extremely important, mostly where you place them, putting them at the beginning or at the end change the image a little but overall still the same.
Hair Red, Jacket
and
Hair, Red Jacket
creates completely different images, if you use large prompts is useful to separate the different ideas.