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
Upgraded samplers to Clownshark ones
added a denoise
FAQ
Comments (10)
hey , i got on v12 an error named : UnboundLocalError: cannot access local variable 'ci' where it is not associated with a value , when im try to using euler_ancestral + normal or simple.
try a different sampler specifically. That's a mismatch between how clownshark names their sampler_names.
Did I not put a note on the workflow about that?
Oh, okay, got it. I was just wondering because it worked perfectly in the last version of your workflow.
@LFPerfect I swapped out Ksamplers for shark samplers. Try the denoise slider and I2I and you'll understand why. also, run the same everything on both and see the quality diffeence.
Lol, I like messing with stuff and options. You should know that by now 🤔
Okay, but as you know, I'm a complete beginner and I'm not exactly sure which denoise slider you're referring to. I'm sorry. I actually only ever use t2i.
There are quite a few denoise sliders, even just among the detailers.
@LFPerfect so in teh brains area, there is a new slider that was not there before. locate it.
Now do the following;
Seed: new fixed random
Prompt assist on
load an image
make sure the main prompt box is empty
turn on I2I
Hit run and see what generates
now lower teh slider to .9 and without changing any settings, hit run again
Okay, I tried it out and I have to say, I'm thrilled—the result is really better. I'm uploading my original image first, followed by the first image I generated with a denoise setting of 0.9, and then the second image I generated with a denoise setting of 0.5.
Is there any way to use this with a T2i as well?
@LFPerfect denoise works either way, just understand the lower you go, the more noise you leave in the image.
If you go to the first node of my Post profuction Suite, you will see a "smart denoise" node. A low setting there will clean up the image. Just be careful as too much starts to smooth the image, then the contrast adaptive sharpen" node (or sharpen in the image adjust node) is also useful.
If you are doing realism, you will hear peopel say they want a little noise. That just makes teh image blurry. Use LensFX or Optical realism to adjust for that.
Thanks for coming to my TED talk...
Thank you so much for your brief explanations. I’ve spent at least 6 hours working on this, trying everything out, adjusting the sliders, and testing—I’ve generated quite a few images.
For me, the combination of i2i + denoise + detailer + hirezfix/upscaler + seedvr2 + contrast adaptive sharpen is the best choice so far.
I think I’ll still be experimenting a lot, but for now I’ve found my default settings that really work for me, and I can start playing around with the checkpoints.
This is truly a great workflow—thanks for sharing it; I’m thrilled!
I’ll donate the remaining 500 Buzz I have to you. Keep it up—you’re doing a great job!
When I’m ready, I’ll post a few more photos below. ;)
Mate I sooo dream to see it with control net and regional prompt. It will be the killer workflow!