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
Added markdown notes with basic info on Epsilon Scaling, CFG Zero Star, and Batch Resize w/Lanczos.
Added Fast Groups Bypasser (rgthree) to toggle on/off groups easier.
Note about the two text boxes for the Positive Prompt:
This is not concat conditioning. The two text boxes both feed into the Positive CLIP Text Encode node.
This is set this way so I can just plug my prompt in without messing with my quality tags repeatedly.
Tested with Concat Conditioning again and hated it.
The default settings are set to what I use. Feel free to adjust to your flavor.
I recommend setting your ālive preview methodā to ātaesdā in order to see your images being generated as they happen.
As always, feel free to modify the workflow to suit your needs. The nodes are not pinned and no reroutes are being used.
As previously mentioned:Ā
The Global Seed and Global Sampler nodes will override any of the settings related to them across the workflow.Ā
Using a sampler or scheduler not compatible with any of the nodes will result in an error.
You can bypass or delete these two nodes if you want to do these settings manually on each node.
CFG is tied to the āCFGā node to the left of the KSampler.
Delete this node if you want to set CFG manually on each node.
The detailers can be used for whatever you want as long as you have the detections models.
The detailer nodes used in this workflow take all detected items and do them at the same time.
You can use whatever detection model you want. You don't have to use what I use.
If youāre using the Nodes 2.0 feature: you are on your own.
Custom nodes used in this workflow:
FAQ
Comments (6)
Oh hell yes! WB G :)
lol thanks! I'm still not planning any major changes until things get more stable with comfy and their updates (wishful thinking).
Hey I need some help with the detailers. When enabled, I run into the error message when detailers are enabled.
UltralyticsDetectorProvider
invalid load key, 'v'.
I ran the command, git clone https://huggingface.co/ashllay/YOLO_Models Ā and placed the files into the Comfyui/models/ultralytics/ folder location.
Edit I think I fixed it, needing to cd into the folder and then run git lfs pull NOTE this doesn't have the correct Eye_V2 for the detailer2, so you have to change it to _paired or eyes.
Glad you got it figured out.
Regarding detection models:
You can use whatever detection model you want (pretty sure I mentioned that somewhere).
I use the Individual model. The paired model (for me) sucks. The way those SEG detailer nodes work is they detail whatever is detected at once. So if I use the individual eye model, it detects both eyes individually and details them at once.
@GladasĀ TBH I normally used the super simple checkpoint > lora > postive > image; set up, but I wanted to learn to use the more complex things like this one. Haven't used a detailer until "today". Can you link the individual model? I'd be down to try it.
@shargothsĀ https://civitai.com/models/178518?modelVersionId=582139
I use the v2 - Individual. Like I said though, you can use whatever you prefer.
If this workflow was using the standard "FaceDetailer" nodes, then the paired option might be better for some people.
As far as simple workflows go (IMO): sometimes simple is best.