Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.
This is an advanced workflow. It is node heavy and designed for multiple options and to return professional high quality results. If you are looking for simpler workflows, they are here:
An essentials one can be found here: https://civarchive.com/models/2349309/illustriousponysdxl-essentials
A simple one can be found here:
A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents hundreds of hours of work that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me. Also, feel free to ⚡tip 😉
也有中文说明
VER 10.1:
Got tired of having to always mess with resolution, so I gave you the option to make it automatic
Math node replacements to deal with the Linux errors
Added psst... fast bypassers (you'll thank me).
💡use the upgraded face yolo I added. much more accurate.
Improved notes throughout
Ver 8.0/ 9.0:
Major overhaul to bring it up to speed with my other workflows
Added second checkpoint metadata
added a prompt to hi-res fix
added Inpainting suite from the pro grade workflow by request.
V7.0
Apparantly , I forgot to hook up Face Swap in my last model and nobody told me until today, so a free major upgrade it is!
Installed a sentence remover in the prompt assist area to help eliminate CivitAI 🚩
Cleaned up some bugs
Resinstalled Qwen VL Prompt Enhancer
Upgraded Face Swap
also upgraded notes on how to remove it.
Minor changes to detailers
Added an inline crop tool in the post production suite.
Ver 6.0:
Major overhaul to bring it up to speed with my other workflows
Added a refiner checkpoint that can easily be switched on or off
Added FaceID as well as a style and composition IP Adapter for character consistency
Reowked the Detailers ro improve them
better version of Hi Rez fix
Reworked the Save with Metadata to align with CivitAi and fix the Comfy update bug 🙄
This is an all in one workflow:
Controlnet
I2I with prompt generation
Dual Model Loader: Better control
Sage Attention: Speeds up production
Ultimate upscaler: For prescale and hi-res fix
Detailers: Face, eyes, hand, expression
NSFW Detailers: Male & Female anatomy
Seed VR2 Upscaler: Get up to 4k pics, even on low VRAM
Post production suite: My pride and joy. Does everything.
Description
major upgrades:
Added optical realism for realistic images
added an I2I node
cleaned up features
swapped out Florence for Qwen Advanced
FAQ
Comments (14)
It is hoped that the author could create a dual-person workflow for SDXL. Thank you.
Hmmm..... I do have a regional prompt one that works "Okay"
There's a lot to it.
@MMJ123 Try this @MGHerder made it. It'll accomplish what i think you are looking for.
https://civitai.com/models/2383305?modelVersionId=2691587
@MMJ123 It made my day that @lonecatone23 recommended my workflow. It is img2img, but the latest versions absolutely let you prompt individual faces, and there's a preview node whereas earlier versions used a picker matrix which was a little tricky. V3 and up just scans from left to right. The great thing about img2img is you can take an existing multi-person image, and make it your own.
Another approach is to go straight for text2image, which is what most of us are doing (I think?) and my workflow for that is here https://civitai.com/models/2383305/img2img-sdxl-workflow-with-auto-resize-meta again with the individual SEGS detailers that take prompts. The rest of the workflow is really very simple, metadata and no frills.
Or, well, inpaint. It works, it's worth having in your arsenal, and for now Grok's your best alternative. I don't have an inpaint workflow out yet but Lonecat has this one: https://civitai.com/models/2252301/brushnet-inpaint-sfwnsfw
@MGHerder OK, thank you.
@lonecatone23 OK, thank you.
recently I got some ideas about a girl with a rifle. About this, I need more suggestions.
Sometimes when we use the checkpoint without weapon lora to draw the image like"girl holds assault rifle, two hands hold rifle", then the rifle looks so weird, just like some bones combine.
But if I use the special rifle lora, I clean the cash but it still doesn't look good, so is there any special func junction that can fix this bug or some skills to avoid this?
Thanks a lot~
I'd try several different models. One trained on weapons works best with another. Also, ZIT and Flux LoRas for weapons seem to work really well (SDXL is good).
Watch this video on detailer hooks. It might give you some ideas. https://www.youtube.com/watch?v=KE-2Kxy9NdQ
@lonecatone23
yeah~
ZIT due to the new module from ALI in 2025 performance well, but still some background knowledge I need to learn before (simply to say~ your ZIT workflow works well, but I don't know how to load the lora and cheakpoint in those junction, It seems more different from those illutrious types~lol......)
By the way, I prefer to take pictures like 2.5D anime style (or say the semi-real style). If you have more great lora or cheackpoint suggestions, thanks a lot~
@1648003234289 2.5D Amime is one of my favorites!!!
I use the Power LoRa loader. You just click (Load lora) on it. The weights are combined and you donlt need trigger words. In almost every workflow, it is right below the positive prompt in the iuser settings area (except the wildcard ones)
the workflow is almost identical to amn Illustrious workflow, except instead of just loading a checkpoint, you are loading a diffusion model, Clip, and a VAE seperately.
Professional as in being paid for work? What do you do?
Professona;l as in professional grade.
Problem installing ComfyUI-LevelPixel as a Portable user. fix is: open a command prompt window in comfyui folder and run these commands one by one: ".\python_embeded\python.exe -m pip install --upgrade pip setuptools wheel" then ".\python_embeded\python.exe -m pip install langdetect" leaving it here for the next person that might have the problem. Great workflow!
Hmm. I appreciate it. Thank you.