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 aβ 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 πlike and post to my workflows. That is how you support me. Also, feel free to β‘tip π
δΉζδΈζθ―΄ζ
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).
π‘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 π©
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 π
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
One of the best parts of using Clownshark samplers is the numerous choices available for Samplers. However, they are not compatible with 75% of all other parts of a workflow (upscalers, detailers, etc. and the names do not always align)
I have corrected that as well as given you an option to use one of their settings.
Added word βοΈ nodes in teh Florence prompt assist area to eliminate any trace of watermark, signature, etc.
Repaired a break in optical realism caused by a ComfyUI update
minor tweaks
FAQ
Comments (3)
Hi @lonecatone23 !
I was testing the v13 and detected on the module "quality mod join" after Qwen assist is duplicated the outcome in "Qwen ππͺ" so in the final prompt get double prompt at the end.
Also, have you tried https://github.com/ethanfel/ComfyUI-LoRA-Optimizer this node? helps to use different loras with the best approach and think would be a nice addition.
Just looking at how detailed and how many steps go into this workflow, I can't wait to try it out.. I only have one problem, I don't know where to place the Qwen3-VL-8B-Instruct-c_abliterated-v3.f16.gguf file so that it is recognized, Ive searched online, Ive looked through the json file, I know it's a model, but I don't know where it should be, if you could help me with that, I'd greatly appreciate it, thank you.
That's the funny thing about clips π€
Place it in the exact same text encoder folder as you normally would BUT... You need to change the Load clip node to a Load clip (GGUF) node. The GGIF node works for standard clips, but not the other way around.
Why don;t I just install it, you ask? It sometimes crashes models (very testy on Klein) when using a standard model in lieu of a GGUF one. Krea2 does not seem to hav ethat issue that I am aware of.