From the course: Learning ComfyUI for Stable Diffusion
Unlock this course with a free trial
Join today to access over 25,500 courses taught by industry experts.
Workflow for SDXL - Stable Diffusion Tutorial
From the course: Learning ComfyUI for Stable Diffusion
Workflow for SDXL
- [Instructor] We've seen how if we use more than one sampler node connected in series one after another, we can refine an image. Well, there are specific models designed just for that. The SDXL model comes in two flavors, the base model, and the refiner. I've created this workflow to demonstrate how to set up the full version of SDXL with the base and the refiner models. First, I want to show you what this would look like if we just did it in the standard way with the base model. It's SDXL Base 1.0 and I've got a case sampler advanced node, but it's set up to act just like the ordinary case sampler node. We'll come back to the features of the case sampler advanced node in a moment. But first, I just want to show you what this looks like. If we run the queue, as if we were only going to use the base model, and this has got 30 steps. Okay, we've got a pretty illustration of a fantasy castle done in an ink and contemporary style. Once I've got that saved out on disk, I'm going to…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
Daisy-chaining samplers for refinement6m 11s
-
(Locked)
Upscaling the latent image6m 7s
-
(Locked)
Workflow for SDXL7m 12s
-
(Locked)
Workflow for Stable Diffusion 3.56m 3s
-
(Locked)
Workflow for FLUX4m 6s
-
(Locked)
Modular sampling with SamplerCustomAdvanced5m 44s
-
(Locked)
Image-to-image6m 47s
-
(Locked)
Image-to-image prompting and CFG6m 55s
-
-
-
-