This is an advanced workflow for those who want to dail in an image at pro level grade. A simple version can be found HERE
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.
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
也有中文说明
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 😉
V16
Complete redo of the 🎨 Post Processing Suite
It was long overdue. The nodes I used did not really align with Krea2 (or Zit for that matter)
What I changed
removed the Optical Realism section. The quality dropped and I get better results from individual nodes
Added white balance
Updated the color match node to V2
Added a skin preserving vibrance node
Added lens profile
Added radial blur
Added pro film grain
Added a better B&W desaturation node
MASSIVE update of the notes.
V15
I have been messing around with Anima regional Prompt and got so frustrated, I made my own nodes set https://github.com/lonecatone23/ComfyUI_LC123_nodes
use an image 🖼️as the background or plain white ⬜
dynamic canvas means you do not need to open up mask editor
Plug in a global prompt or enter it here
works with Controlnet now (Kinda. Still beta )
Vastly Improved Image control
added my own set of nodes including 📐 Aspect Ratio Simplifier which saves a boatload of time trying to get the right image size
Other minor OCD tweaks
V14
Vastly improved Controlnet
also addresses the break that I was unaware of because hey.. stuff updates 🤔
⚠️ Controlnet file location has changed. See notes.
Added I2I 🖼️ and a denoise slider to support it
Updated the 🧠brains a bit, mainly to work with the slider
I'll probably do a gut redo soon. I want dual samplers, but to properly build them and still have denoise, they are custom (see Krea2 workflow)
Minor OCD stuff.
V10 & 11
Swapped out the detailers to SEGS detailers for significantly better control and quality
Updated the notes
Added a GGUF Qwen VL Prompt Enhancer for fast prompts.
it's also abliterated, so does NSFW incredibly well 🤔
Added the ability to color match to the original image without having to reload it.
Updated Hi-res fix
V9.0
Note: Both Controlnet & Regional Prompt nodes are in Beta testing. You will not find these to be as rigid as SDXL or Flux based ones, but they are fun to mess with.
Added back draft mode by request
added shhh.. nodes (You'll thank me)
Made it so you can use the original image ratio.
Super good for regional prompts and Controlnet
Added Regional Prompt (BETA)
I'm still testing this out. Not sure how I feel about it.
what it does do well: ART
what is sucks at: people
Replaced math nodes to be compatible with Linux users
Tweaks here and there.
Ver 8.0
added controlnet
added Klein enhancement
reworked Post Production Suite
Minor tweaks.
Ver 6.0
Upgraded Prompt assist.
Added an inline crop tool for easier image editing.
inmproved the save option to include the option to add a date to the metadata file. name for beter organization.
Minor note tweaks.
Ver 5.2
Updated for Comfyui changes
Added sentence remover to prevent CivitAi flags
Made some optimazation changes for Anima 3 preview
reworked the user settings area.
Ver 4.0:
On a neverending quest for opions, I decided to tweak my Anima workflow to get relism and semi-realism out of it for the Anima2 model
Added a detailer suite based on SDXL or Illustrious for realistic options
Note: It's not gonna beat ZIT, but with the prompt adherence, It's cool for semi-realistic
Included my full detailer suite
Included my full Post production suite
Fine tuned Optical Realism to work with this model (in other words, don't mess with the settings)
Ver 3.0 included in download for straight Anime
I had to make modifications as to how the Savenodes worked. ComfyUi broke them (again 🙄)
What this workflow contains:
Sage Attention: Speeds up production
Ultimate Upscaler for prescaling and hi res fix
Detailing Suite for face, hands, eyes
Seed VR2 Upscaler to get 4k on low VRAM
Essential Post Production Suite
JPEG Scrubber
Full tutorial available.
也有中文说明
Description
Swapped out for Sam3 detailers
added word ✂️ nodes to lose the "there appears to be a watermark..." crap that Florence loves so much 🙄
Added better CivitAi 🚩removers
Tweaks throughout
FAQ
Comments (18)
Um, i'm a newbie in img gen, and i'm curious about PostProcessing block. It's stated that this workflow is for pros. Aren't pros using more versatile and effective external image editing software for final postprocessing? Or is it just personal preference of the author to have it inside Comfy?
As a pro, why would I transfer an image to another set of software when I can get better results inline? For base adjustment, dragging it out and going to Krita or Photoshop is a pain. For what 99% of people need, my post processing suite is ample enough.
@lonecatone23 how much process time needed for those post processing? Let say I don`t have great GPU resources but I think I have knowledge in Photoshop or other image editor. Do yo say it worth the time ?
@juvesatriani it image adjusts, crops, add vignette, dearpens, color corrects, adds a vignette, etc. and uses very little CPU. It is automated. It does it in seconds.
Just try it.
@lonecatone23 to get better control over the output using better tools? I fail to see what so painful to get the picture into external suite, and personally i can't see some essential tools here, and i find using LUTs is a bit restricting, but if it works for you, great.
And thanks for sharing your workflow, i appreciate the exchange of skills and views.
@sten4950 Really? Which essential conntrols would that be? I'm curious
@lonecatone23 WB correction tools for example.
@lonecatone23 But then again, i'm using completely different software so my work is fundamentally different than yours.
@sten4950 Literally have a node for it.
@lonecatone23 yep, with insufficient level of control, that what i'm saying, from my work habits.
But as you said previously - "For what 99% of people need, my post processing suite is ample enough."
@sten4950 No, there are literally pro nodes for that that mimic Photoshop, but again, it works for 99% of people.
If you think somethign is missing, please let me know. I always strive to put out the best workflows
@lonecatone23 Well, i doubt Comfy could handle whole Color page from Davinci Resolve ;)
@sten4950 Look, I get that you are new, but it can do more. Lightroom nodes exist, primary and secondary nodes exist, 3 way lift/ gamma/ gain nodes exist. All of this is possible, inline, and smart adaptive. You can even save to your Resolve media pool directly from ComfyUI in one step. I used to use photoshop. I no longer do except for layering and such.
@lonecatone23 I'll look into it, thanks for the tip.
@sten4950 it's just a preference. if you know you'll be fine doing post-processing out of comfy, go for it. from the author's responses I feel like he just loves to keep everything in comfy, which is fine, though as a power comfy user myself, i would still prefer to do some work in davinci/photoshop just because i like it more, just like i like it more to use stable diffusion forge/invokeAI for initial image generations. comfy is amazing if you want to make fully automatized workflows that will do multiple things by one click, so you'll be just fine using photoshop if you want keeping comfy just a part of your pipeline. no need to cover the whole pipeline by comfy.
@slayerdude The single biggest part of doing it this way is that it is free and easy for new users. Nobody wants to pay for another subscription (especially Adobe) when they can do it internally.
I love good art. However you do it is fine by me. I'm just giving everyone local options
This workflow is absolutely unparalleled—a veritable aircraft carrier of operational efficiency!
Thank you 🙏