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
Workflow built and tested while using comfyui (portable) 0.3.76 and comfyui-frontend v1.34.6
This workflow is simple by my standards, but it does the basics:
Generate Image
Upscale
Detailer
Color Correction
Save Image
There is only one upscale group and one detailer in this workflow. Since the workflow is relatively small (by my standards) it should be much easier for people to add whatever they want to the workflow.
I incorporated an upscale node normally used in video workflows (from Whiterabbit) to upscale the image prior to being fed into Ultimate SD Upscale. This is experimental, but I have been very satisfied with the results. No need for upscale models!
None of the nodes or groups are pinned in this version, so it will be easy to move things around to suit your needs.
I'm using 4 Load Lora nodes from good old Comfyroll Studio. Feel free to change these out for your preferred Lora loader. I'm basically done with stacker type nodes while things are breaking on the daily with each comfyui update.
Detailer behavior seems different, but that could just be me. I have found that I have to use more aggressive detection thresholds more often than not, but YMMV.
Just like with the Nodes 2.0 workflow, this will be using the standard Save Image node.
This means you will have to add your resources manually.
AFAIK all of the custom save image nodes are busted as far as being able to take your generated image and dropping into comfy to load up the workflow.
The way it behaves now is like if you took and image you generated in A1111 and dropped it into comfy.
FAQ
Comments (22)
v15 uploaded
Small workflow by my standards and should be easy to modify as desired.
No notes all over on this one since they are bugged (for me). Folks will have to hit up project pages for info on the few custom nodes used if they can't figure it out.
Glad to see you're still around, thank you for all your work.
V13 was my favorite, I don't really understand those little ball-nodes but V15 is just using normal connections, I might be able to insert all the stuff missing from V13 back into it
@paulonunesbazilio729Ā the "balls" are just reroutes, but yeah v15 is easier to add on stuff to
V15 installed correctly, I'm only missing BatchResizeWithLanczos. Any idea what I need to do? Thanks
Yeah you need WhiteRabbit and any dependencies it might require
If it becomes too much, you can always replace it with the normal Load Upscale Model, Upscale Image with Model, and Upscale Image nodes.
@GladasĀ Thanks a lot !
damn its exactly like what im do after wwant to simplified.. XD but the different i remove the second USDU and redone to make it simple.. but still using your v13 workflow as base.... and add SMZ nodes since im dragg image from Forge to comfyUi it has SMZ nodes. which is have same behavioir with Forge.. (that what im experience.. probably different than you..)
Yeah I just made it simpler because of the recent comfyui updates breaking a lot of things for custom nodes and the load workflow via drag/drop image function. That was more important to me than the convenience of anything I dropped in v15.
Works perfectly! I had completely given up on SDXL, Illustrious, etc. I think your workflow will help me rediscover it. Now I just need to see which checkpoints suit it best. Thanks for the troubleshooting and for sharing your workflow.
v13 is still my favorite
What is your favorite version of the 13?
Can you add controlnet to v14 please?)
I'm traveling rn, so I'm not updating anything this week.
As far as ControlNet goes: you can just add it yourself? If you know how to use it, you should be able to easily add it.
Unfortunately, I have no plans on adding ControlNet or anything that I am not using. Especially when the recent comfyUI updates have really messed a lot of things up.
Well since the new frontend fixed Image Saver, I am in a better mood. I'll add ControlNet like how I had it before, but again it will be very basic.
@GladasĀ thx alot )
can you design a workflow for img2img of lora+controlnet?
Nah, I don't have a need for that. You can modify any of my existing workflows for that.
Plus I'm basically not doing any major updates while comfy is so bugged now for the custom nodes I use.
Looks like we can drag and drop images into comfy using images saved on Image Saver again if you use the latest comfyui-frontend version (v1.35.0). You can use the latest version (at your own discretion) by adding this to your bat file command line arguments: --front-end-version Comfy-Org/ComfyUI_frontend@latest
Just wanted to add that the fix for this issue seems to have been added to 1.34.7 and has been backported to 1.33.13 which the latest comfyui now uses (v0.4.0/nightly/main branch)
oh very cool. Glad they fixed it. I was contemplating on quitting comfyui