🛠️ 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.
⚠️ 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.
🤝 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
FAQ
Comments (10)
v13 uploaded
Tip for getting around the workflow easy:
Since my workflow uses rgthree's custom node pack: try using numbers 1 through 9 to help navigate the workflow if you don't like scrolling.
Thank you!!!
v13
you have RES4LYF installed based on the error I am seeing. That custom node pack's sampler/schedulers have some sort of conflict with this workflow. This is also mentioned in the "about this version notes".
@Gladas thanks for your amazing work!
@Gladas new day, new bugs, now with the Impact Pack and the latest comfyui updates https://github.com/ltdrdata/ComfyUI-Impact-Pack/issues/1113 https://github.com/ltdrdata/ComfyUI-Impact-Pack/pull/1115
FaceDetailer (on the newest Impact Pack version as of 1 Oct 2025) seems to drastically behave differently with the same denoise settings that I used just one day prior.
I did some testing and shared my results with my buddy ChatGPT and it seems to be possibly affected by changes to Differential Diffusion (even though it's not used in the workflow). From what ChatGPT says, detailer nodes borrow pieces of Differential Diffusion's logic.
Turning off force_inpaint doesn't change the behavior either.
I did have some moderate success with using very low denoise settings (0.01 to 0.1), but YMMV and could just be something weird with my install.
Saw the big disclaimer re: RES4LYF. Were there some compatibility issues introduced with version 13? I've been using it for quite some time without anything going wrong.
I have had a lot of people who use RES4LYF complain about compatibility issues with certain nodes such as Sampler Scheduler Settings (JPS) and Basic Scheduler in my workflows. If you haven't had issues, then I think you're one of the few (or maybe they are the vocal few).
The "fix" has generally been them uninstalling RES4LYF or disconnecting things on their own.
I have had at least one person per version that use these node complain about it and then when they link the error, the common factor always contains the schedulers from RES4LYF.
I was able to recreate the issue myself when installing RES4LYF as well, but didn't really go any deeper than that as far as troubleshooting goes. I just uninstalled it and the issue went away for me. Maybe there's something on the backend causing issues for them (and me) when having RES4LYF installed?
Ugh. I accidentally removed my own comment when editing it. Smart.
Anyway, you're right on the money. Tried the v13 workflow and the error occurs precisely where you had mentioned. I tried to troubleshoot myself but after uninstalling it, the issue resolved itself.
I was using res_2s and bong_tangent fairly early on in the workflow, then using res_2s and Karras in the detailer for hands because it made a significant difference in my findings. None of this is a dealbreaker though. I use the RES4LYF stuff in another workflow when generating items with Qwen for LoRA training. I can just split the installations of ComfyUI up so I can continue to enjoy your offerings, and have the RES4LYF offerings when I need them.
Appreciate the response as always. Have a great weekend! :)