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
FAQ
Comments (8)
Okay so I have trouble Jnodes I'm not able to install them because they are incompatible with the current setup of comfyui apperantly
assuming it's this one
https://github.com/JaredTherriault/ComfyUI-JNodes
the node I'm missing is
Jnodes_TokenCounter
is there any replacement or workaround for theses tools because you use them a lot it. Thank you very much
sorry I updated this many times because I managed to fix other issues
I would say just delete the nodes related to the token counters. v17 no longer uses them, if you want to try that version.
Great workflow. Just a personal recommendation, you should use Lora Manager's Lora Loader and Triggerword Toggle instead of the rgthree Lora Loader, saves the hassle of putting in trigger words. Also consider adding the Impact Wildcard Processor. This workflow is the best, thanks for all your work.
Thanks for the suggestion! Lora Manager is a hard no for me, sorry.
ImpactWildcardProcessor was actually just added on v17.
@GladasĀ Damn... š I just finished modifying your v16 yesterday, guess I have something else to do now.
May I also ask why you don't like Lora Manager? I don't know much about it, just learnt about it yesterday and it seems to be more convenient.
@chillassdude67Ā I use Power Lora Loader due to it's compatibility with Image Saver (which my workflow is built around) and the only thing (if I recall) I liked about Lora Manager was behind a paywall and required installing a Chrome Extension. So that was a double "no" for me. If Power Lora Loader ever becomes broken, I'll switch back to using Impact Pack's Wildcard Encoder node instead.
@GladasĀ Oh yeah, I had an error previously when I tried switching them, I don't know if this is a solution to the problem you're specifically talking about, as I am still pretty new to this.
If you link the MODEL and CLIP from the Lora Manager to the Power Lora Loader, I think it acts as a gateway. It fixed the error I was getting, and everything is working perfectly.
https://ibb.co/x87nNmyX
This is the setup I have, if you're curious at all.
Keep up with the good work man!
The LoRa to String node requires the rgthree Power LoRA Loader specifically but thatās just encoding the LoRAs into a string for the positive prompt going into Image Saver. If you want to swap to LoRA Manager for your own setup then you can connect the LoRA string output from the LoRA Manager directly to the concatenate node leading into Image Saverās positive input (bypassing the LoRA to String node entirely). Though if youāre fine daisy chaining it with Power LoRA Loader and it still works then thatās a lot less rewiring.
I think Power LoRA Loader makes more sense for this workflow. I only swapped over on my personal setup because the LoRA Manager Loader makes it more convenient to add trigger words (either automatically or by right clicking + copy trigger words). For rgthree, you can view the LoRA info, click on the trigger word(s), then click copy, but thatās twice as many clicks if youāre frequently experimenting.