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
v4g changes:
Generation time from start to finish on a 3060 RTX:
With the default settings and most of the extra stuff turned off: 165 seconds (including checkpoint loading time).
With everything enabled: 200 seconds (including checkpoint loading time).
Added Image Saver nodes back in and dropped ComfyUI-ImageMetadataExtension
This was primarily due to compatibility issues with the SamplerCustom node.
Added ImpactWildardEncode nodes back in and dropped the split positive prompt nodes and Efficiency Nodes.
This is for compatibility with the Image Saver nodes and to keep the lora/embedding info present in the resources shown when posting to civitai.
The first KSampler has been swapped to SamplerCustom
This was a choice based on preference and wanting to be able to use ComfyUI-Detail-Daemon from the beginning of the process.
Added a 2nd USDU (ComfyUI_UltimateSDUpscale) node for a 2nd pass.
IMO, USDU seems to strip out some details on the 1st pass.
The 2nd pass seems to help add details back in.
Adjusted the layout (again).
I will be removing the Alternative Watermark Removal portion of the workflow if I update this workflow again, since I do not use it (ever).
Included 2 versions of the JSON file. One with all the extras turned off and using Euler Karras. The other with everything on and using CFG++ sampler.
FAQ
Comments (8)
What is the main difference in ComfyUI between a standard pony/SDXL1.0 workflow and an Illustrious workflow? Sorry for basic question, but google has not been able to provide me with an answer to this question.
Probably no real difference other than prompting, but that's not a workflow difference. I haven't tested on Pony or SDXL on the newer versions of the workflow, but it should work
@GladasĀ Ok thanks, so I'll stick to my own workflow then. ComfyUI usually put up workflows for new models, but they have so far omitted a particular workflow for Illustrious. I just don't want to miss out on any bells and whistles (if there are any) compared to pony/SDXL.
@snobbias124Ā yeah for sure, use what works best for you ^^
Really nice workflow though, been playing with it for a few hours. I'm not an advanced user, so maybe you'd care to explain a few things: I notice the first result is a bit blurry/lowres, looking just like when the VAE is not added (although the end result is fine later on). Also, you have selected some schedulers and samplers that are less common. I tried to set them back to standards (euler/normal), but that didn't work well in this workflow. I'm trying to figure out why.
Anyway, I've learnt a great deal now and will start to experiment with some new nodes, namely samplerCustom, DetailDaemon and dynamicThresholding. This rabbit hole goes deep :)
If you are using the newest version, enabling "add noise" on the 1st KSampler (Sampler Custom) can help. Some models work better with it on.
I mostly use the CFG++ samplers, but it works fine with the "normal" samplers also. You would have to make sure to adjust the CFG to a higher value and adjust the CFG settings on Dynamic Thresholding as well. You may also need to adjust the steps depending on the sampler being used as well.
I'll generate an image using "normal" sampler/schedulers and post it under the latest version's gallery in a bit just to provide a visual example.
Here's a post with the results using DPMPP 2M Karras with both an image and a screenshot of the workflow. As mentioned in my previous reply, I enabled "add_noise" on the 1st SamplerCustom and adjust the CFG values. The other thing to keep in mind is that you may need to adjust the denoise values higher/lower on the later portions of the workflow depending on the sampler/scheduler combo as well.
@GladasĀ Thanks a lot for your explanation. I'm experimenting more. I had a plan to recreate your workflow from scratch, but realized there are too many nodes I simply don't understand (and some sneaking once hiding behind others :). Keep up the good work!