š ļø Purpose & Design Philosophy
This workflow is a high-fidelity environment built for Illustrious. It prioritizes stability and professional texture over generation speed. It follows an "all-in-one" philosophy: configure your prompts, hit queue, and let the workflow handle the multi-stage refinement from start to finish.
Not for Speed: This is a heavy-duty refinement tool. If you want 2-second previews, use a basic workflow.
Personal Use: Built for my specific production needs. It is shared as-is for those who want a "set-and-forget" pipeline for Illustrious. Adjust the settings and models to fit your needs. The defaults on v19+ will be what I used for the sample images.
All-in-One Logic: The workflow handles generation, detailing, and upscaling in one continuous pass.
If you're needing something with more features: Try checking out Silly All-in-one, Multiple Characters With Regional Loras which is on civitai. I have no plans to implement additional features.
ā ļø Disclaimer & Compatibility
Install at Your Own Risk: Custom nodes can break your environment. I am not responsible for troubleshooting your specific installation.
ComfyUI: Built and tested on the non-app version. Desktop app users may face additional hurdles.
The "Your Version" Factor: Your node versions and environment are 99.9% likely to differ from mine.
Nodes 2.0: I do not recommend using Nodes 2.0. It creates unpredictable UI behavior; I will not provide support for issues involving this feature.
š¤ Support & Boundaries
I have not and never will monetize my workflow. CivitAI is the only platform I am maintaining this workflow on. If you find a version of my workflow posted and/or monetized anywhere and use it, then whoever posted it is responsible for providing you any support. This is the main reason why I don't monetize this: I don't want to be or feel obligated to provide support.
No DMs: DMs are disabled due to repeat spam. Please check the Discussions tab below; most questions have already been answered.
Modifications: You are free to hack this workflow apart. However, you are responsible for fixing it if it breaks.
Custom Requests: I do not make private workflows. If you need a custom solution, post a Bounty on CivitAI. There are many talented creators ready to help you for a fee.
Description
v5c changes:
Dropped the Color Match node before the USDU nodes.
Nice feature, but not being able to bypass it was pretty annoying for me.
Using the Color Correct node at the end of the workflow works good enough and it can be bypassed.
Dropped ControlNet and IMG2IMG.
I do not use these enough to justify making everyone deal with the hassle of putting an image in the Load Image nodes. If you liked those functions, you can easily add those into this workflow or continue using v5b and older versions.
Added Dynamic Thresholding back in.
If you are not familiar with how to use this node, you can just leave it disabled or read up on it here.
TL;DR this allows you to use higher CFG values while it mimics whatever value you put in on the node. (e.g. CFG 10 on the normal CFG setting with CFG 6 on the Dynamic Thresholding node.)
I prefer this version over v6, even though it can be slower.
Workflow default settings use Euler A sampler settings with everything enabled.
FAQ
Comments (9)
Hi, great workflow, I learned a lot of useful things for myself. But still I have a question, why are you using gits Scheduler? According to my observations, at least for IL with hires.fix, there are significant problems when choosing it, unlike normal. It would be interesting to know why you chose him
It's just a preference for me after trying lots of sampler/scheduler combos. I think the gits scheduler I use is from comfyui-ppm. Not sure if it works the same as the built-in gits scheduler 'gits (coeff=1.2)" or whatever it is called. The ppm author's cfg++ samplers are supposed to be fixed versions. Not sure if that applies to the schedulers as well. For me, it gives more stable results.
@GladasĀ I just didnt understand why to use gits, when it was made for 20 steps, and if you use the values above (as I saw you have 28), then it will just simulate ays. Why not just use the same ays in this case?
@GladasĀ And as far as I know gits is not very suitable for ancestral samplers. Although this may not be true, I would be glad if you have any information on this matter.
@degurshaftĀ sorry I'm not a technical expert when it comes to samplers/schedulers. For a more detailed reason, you can check out that article mentioned in my Suggested Resources. Personally, I mostly use CFG++ samplers only, but I have been asked previously to show examples with "normal" samplers. In one case, they suggest Euler A + GITS at less than 30 steps but don't specify 20 steps as a hard number.
In my results you can see there are no issues with the sampler/scheduler combos I am using. At least, I am happy with the results. Just because I use a specific combo does not mean anyone using this workflow must use the same. What works for me might not work for you necessarily as a matter of preference.
I have used AYS and it gave me issues when used with Ultimate SD Upscale. Results are more stable (for me) when using gits. CFG++ samplers are supposedly best with DDIM Uniform or SGM Uniform (according to some sources), but I like the results I get with gits.
@GladasĀ Got it, good luck with future work
I got an error that node CFGPPSamplerSelect was missing when I imported v5c today, but I fixed it by rolling back ComfyUI-ppm to v1.0.23 from the latest v1.0.25, just in case anyone else gets this error.
Something I have been trying out:
Not having Detail Daemon connected to USDU seems to be working pretty nicely. Might post the workflow as a very minor update after checking to see if I have any other nodes behind the main nodes.
Sweet. Looking forward to testing it out. :)