⚡ Illustrious Workflow as of version 18

🛠️ Purpose & Design Philosophy

This workflow is a high-fidelity environment built for Illustrious XL. 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 SDXL 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.
All-in-One Logic: The workflow handles generation, detailing, and upscaling in one continuous pass.

🚀 Key Features & 2026 Logic

Global Model Patching (RescaleCFG): Includes a pre-configured RescaleCFG patch (Multiplier: 0.7) applied globally. This acts as "HDR Insurance," preventing the "deep-fried" or over-saturated look common in high-CFG Illustrious runs.
Detail Daemon Sampler: Integrated to enhance structural depth. In this version, it is tuned to start at 0.4 to preserve the core Illustrious character proportions while sharpening hair and eye details.
Hybrid Upscale Strategy: * Group Bypass Switch: Easily toggle between a Pixel-only (Lanczos) path for flat anime styles and an Upscale-Model path for 2.5D/highly detailed renders.
- Ultimate SD Upscale: Re-draws the upscaled canvas at a 0.35 denoise to lock in fine textures.
Power LoRA Loader: Manage multiple Illustrious-specific LoRAs without messy wiring.
Triple Detailer Groups: 3-stage targeted refinement for faces, hands, and clothing using standard detection models.
CivitAI Meta-Sync: Images are saved with full metadata (Model, LoRAs, Sampler info) for automatic site parsing.

⚠️ Disclaimer & Compatibility

Install at Your Own Risk: Custom nodes can break your environment. I am not responsible for troubleshooting your specific installation.
ComfyUI Portable: Built and tested on the Portable 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

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

Originally, this was built from scratch based on v11 and v12.

I ran into an issue where Image Saver just would not save any of the metadata, which is what my workflow is built around: making sure all the resource info, parameters, etc. are in a format that civitai can read without me having to manually do it.
After wasting 12 hours of my time on the original v13, I proceeded to dissect v11L and modify it to how my original v13 workflow was set up.
This came with the “fun” process of making sure that the metadata was saved and readable by civitai each time I made a change to the workflow.

6.5 hours later and here we are:

What does this workflow do?

Basic ControlNet at the start of the workflow

Supports up to 3 ControlNet(s) connected to the initial KSampler (SamplerCustomAdvanced)

Global Sampler / Seed

These provide an easy way to set these settings in one place
Note: Any Sampler / Scheduler selected that is not compatible with ALL nodes in the workflow will cause the workflow to error out.
To make use of this node across the whole workflow, the Sampler Scheduler Settings (JPS) node is attached to the KSamplerSelect and BasicScheduler nodes. This does not work with RES4LYF based on feedback from other users of my workflow.
If you are running into a random error that involves BasicScheduler, then chances are you have some custom node pack(s) that is/are not compatible with the nodes in my workflow and are causing a conflict. If that is a deal breaker for you, I totally understand: I also am unwilling to part ways with what works best for me.

Concat Conditioning

This is a Comfy Core function that can help you add flavor to your images. (Their words, not mine.)

Wildcards

Wildcards are able to be utilized easily via the ImpactWildcardProcessor node.
Install your wildcard files in your Impact Pack/wildcards folder before starting comfyui.

Dynamic Thresholding

2 separate nodes for the initial image and for upscaling.

Detail Daemon

Several Detail Daemon Sampler nodes are provided across the workflow for the initial image, upscale, and detailers.
Suggested settings are in a note near the start of the workflow.

Image Filter Adjustments

These nodes are available for use with Ultimate SD Upscale.
Notes are provided for suggested settings of these nodes.

Watermark Detection and Removal

Self-explanatory: it detects watermarks and removes them.
There is a CLIPSeg method of doing this, but that method is not for me.
My version of this is a slightly modified version of this workflow.

2x Upscaling (on default settings)

Upscaling is performed via upscale model and then fed into Ultimate SD Upscale.
You can go higher, but you will have to adjust the settings yourself.

3 (Face)Detailer nodes

I use these for the face, hands, and eyes.
Adding more on your own should not be a problem as long as you are comfortable with connecting/reconnecting things.
After the latest updates to comfyui and Impact Pack, I have had to drop the denoise way down when detailing the face. Just FYI in case you run into this.

ColorCorrect