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
About this version
Finally got off my butt and put in the time to gut and overhaul the Controlnet:
Now you can select the aspect ratio of the original image without having to "guess" it with the aspect ratio node
Left room for the resize node so you can choose which side to crop the image by
Redid the dependencies so that every tie you shut it on and off, you don;t need to reset the switches so it will not give you an error 😡
Massively improved the notes throughout
added super secret nodes ...shhh.... (you'll thank me)
Minor layout tweaks
FAQ
Comments (15)
how can i fix this error ? : simpleeval.NameNotDefined: 'b' is not defined for expression 'a/b '
which version? I thought I fixed that?
It's fixed. I must have uploaded the wrong one
@lonecatone23 I downloaded version V10.1.1 of Cnet Overhaul about an hour ago
I've now downloaded version V10.1.2 and it works perfectly. Thank you—the result is amazing. Thank you so much. Thanks for the quick reply. I'll share my first generated image here.
@LFPerfect awesome 🙏
I have enabled the following: Load Image, Img Prompt, Hi Rez Upscale, Eyes Detailer, Face Detailer, Create Subfolder, Save Draft, Save Mask, Save Metadata --> Everything runs smoothly with these settings; it's wonderful.
But when I also enable the Hand Detailer, I get an error message from the Face Detailer: ypeError: FaceDetailer.doit() missing 1 required positional argument: ‘model’, or am I only allowed to enable 2 of the detailers?
@LFPerfect fuuuuuuuck. Hold on.
Hook teh LoRA loader tpo teh model at teh last detailer. It broke during the last Comfy and I thought I grabbed it. I've also updated the workflow
All right, thanks so much for your quick help—you're a lifesaver. Do you think there might be a Feet Detailer coming out soon? :D I'm trying out your workflow right now; if I find anything else, I'll let you know. You're really good at this.
@LFPerfect you can literally swap out and SEGs or BBOX model for the feet one and it would work. I'm working on a more powerful suite soon. It's in my sandbox.
Oh, okay, thanks for the tip.
That sounds really interesting—I'm super excited about it!
Quick question: Is there any way I can use T2i? Because when I turn off “Load Image,” I get an error message saying that Florence is reporting the image is missing.
Okay, I have to disable the img prompt too—then it works. My bad.
@LFPerfect well if there is no image, how do you expect Florence to read it?
Florence is prompt assist. Turn it off as well
I had “Load Image” and “Image Prompt” enabled the whole time, and I used that with an uploaded image, but now I just wanted to use t2i text. However, I had only disabled “Load Image,” which is why I got the error message (the image was still loaded). I've now disabled “Image Prompt” as well, and it works perfectly—i.e., T2i. ;)
@LFPerfect I built the damn thing and do that all the time 🤔
Yeah, but I didn't get why it didn't work—it was my fault.