Z-Image Base & Turbo Pro Grade Workflow I2I/T2I (Low or High VRAM) — V6.2 Z-Image Base

LC AV Nodes: https://github.com/lonecatone23/ComfyUI_LC_AV_nodes

LC Maskmaker Nodes: https://github.com/lonecatone23/ComfyUI_LC_MaskMaker_nodes

All LC Notes now translate to the following:

English, 中文, 繁體中文, Русский, 日本語 ,한국어, Français, Español, عربي, Türkçe, Português (BR), فارسی, עברית, Italiano

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 😉

Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules. Most issues can be resolved by updating everything

⛔⚠️🛑✋ Read the notes completly before using. Most common install and node problems are listed in the directions

A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civitai.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown

This is most likely my final version of this workflow. I get zero credit from CivitAI for this work anymore, so I'm letting it, and most of my other ones fade away.

V31.1

added Vision Assistant . Click on muy icon in teh sidebar for a helpful assistant and virtual tour. Read about it here: https://civitai.red/articles/36595/vision-assistant-your-workflow-sidekick

V31:

I literally forgot to hook up Speed Boost on the last version 🚀🙄. Fixed

Lots of changes:

Removed Ultimate Upscaler. Why? VOSR2 does a better job and skin upscaler picks up the slack, plus paster processing times

Better Detailers. They now have tone match and talk to each other

VOSR2 (my version). Super fast upscale without the loss of quality. It alsop talks to my detailers so it doesn;t do the work twice

Skin upscale and skin texture now talk to the Detailers

minor adjustments to settings and bug fixes, especially DepthFx. now the haze works the way I want it to and rolls off

LC Natural Look 🍃: Removes the "AI" look from an image by pulling back the loudest colors and fixing the orange tint

V30:

I literally forgot to hook up speed boost! 🙄

It will be fixed in V31, but if you want to now, it goes between LC sigmas and the first sampler.

Installed Speed boost 🚀 Read about it here https://civitai.red/articles/36132/speed-boost

Moved the detailer daemon to the lower sigmas

I wasn't happy with some thing below speed wise, so I tweaked them, especially DepthFX. Now it's about 20x faster

new sliders for the detailers

a timer that actually does something.

V29

"Many a Bothan died to bring you this workflow"

I started building my own nodes a while back. I was tired of the crap the community or ComfyUi offered.

So I looked at everyones. Weeks of proof sheets and tests, several articles, and somethign like 180 nodes built later, I can safely say that I have the best out there. Why? Because I took the best of what people had to offer and threw away what didn't work.

Are they the easiest? No. The fastest? Sometimes. Do they deliver the best quality? Without a doubt.

What I changed:

Notes in 16 different languages

Just click on a note dropdown and change it, or go into settings and change every single note to your language

Model Optimizer

All the speedups optimized for your computer witha full report and suggestions

It also will download the model for you if you want

All new sampler configure.

I took the best psrts of my old one and made it so they actually speak to each other. Smoother transition.

all of the original settings are now presets that actually do something

New Detailers

The old ones had a bug, plus they didn't work as well as they shoudl have.

My new ones are skin aware. They do an exceptional job

Allpaint

Inpaint, outpaint, rotate, change clothes, swap heads, expose ...ummm.. skin!

it does it all and all on the face of the node. No mask editor to open

All in one group.

Skin texture (beta)

builds skin pores and skin off of an image.

still beta, but tests are promising

Optical realism

depth aware node

pro mist on the Bloom filters

all the toys

V25

I've been searching for a better solution for upscaling that SeedVR2 or PID (which suuuucks). After about a dozen different tries, I cam across this: https://github.com/ylchen333/ComfyUI-VOSR2

What I've changed:

minor cleanups and organization

Added VOSR2 Upscaler

V23

Swapped out 🎨 Post processing suite for my overhauled Krea2 one

Added Skin Upscaler

reworked the nodes so that they are categorized and in the proper order

V22

Qwen VL broke my workflows, forcing me to update them

repaired Qwen break

Added a better save w/metadata block

updated notes

V20

Introducing LC123 Nodes

These nodes are BETA. If you do not like them , simply delete it and paste the old pack back in. You will only need to change the "Org pic" name on the getnode for the color correct. Also, please provide me feedback so I can adjust

VRAM settings can be adjusted in the ComfyUi settings menu:

Smart Denoise (LCImageDenoise)

Color Match (LCColorMatch)

Bloom (LCBloom)

Vignette (LCVignette)

Image RGB (LCImageRGB)

Lift / Gamma / Gain (LCLiftGammaGain)

Auto White Balance (LCAutoWhiteBalance)

Vibrance (LCVibrance)

Chromatic Aberration (LCChromaticAberration)

Sharpen Pro (LCSharpenPro)

Image Adjust (LCImageAdjust)

Lens FX (LCLensFX)

Lens Profile (LCLensProfile)

Film Stock B&W (LCFilmStockBW)

Film Stock Color (LCFilmStockColor)

Film Grain (LCFilmGrain)

Desaturate (LCImageDesaturate)

Apply LUT (LCApplyLUT)

Image Crop (LCImageCrop)

Text Overlay (LCTextOverlay)

LC Watermark 💧(LCWatermark)

Plus plenty of other options. Check them out here: https://github.com/lonecatone23/ComfyUI_LC123_nodes

V19

Major Overhaul

Gutted and simplified the aspect ratio and image area.

Better latent control

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.

Added new and some custom made LUTS

V14.0

Because it is not in my nature to leave things alone....

Gutted the stock face detailer nodes and replaced them with a SEGS suite for infinately better results

Note: Yes, I will be going through all my workflows and replacing them, including teh NSFW ones

Controlnet Update.

Added local bypass nodes so you don't have to zoom and scroll

Major update to notes, especially for detailers

V13.0

Overhauled 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

Minor layout tweaks

V11.3

Detailers are now able to handle float32 models, so I rewmoved the SDXL Based checkpoint.

Please give me feedback with any issues on this, especailly RAM related.

Added a crop section so you can...well... crop images easily

Updated several areas

Added the ability to use a simple date with the metadata folder

added a "remove banned tags" node

V8.0

Removed Florence Prompt assist and replaced it with Qwen Advanced.

Reorganized the controlnet section because it bugged me. Now it's easier to use.

Added a LoRa controller for the detailer for better character facial and eye consistency as well as a localized prompt

Gutted the backend of the post production suite and added 📷optical realism , giving a significantly better way to fine tune your images. Fixed some backend math

Added a 📂 subfolder generator that seperates the metadata files according to the name you give the file for easier use.

V7.0

Added KSampler Configure Nodes so you can leave the setting in place for both ZIT and base without having to change them

Removed some problematic nodes

Removed Qwen Prompt enhancer. I refuse to put an API one in there.

global scheduler and samplers for consistency

Better math

Improved notes throughout.

All in 1 workflow:

Controlnet

Checkpoint option for merged models

I2I

Prompt generation

Prompt enhancement

Lora Loader

Advanced KSampler

Draft mode for making corrections without having to rerun the workflow.

Seed variance enhancer

Ultimate Upscaler for prescaling and hi res fix

Detailing Suite for face, hands, eyes, and expressions

Seed VR2 Upscaler to get 4k on low VRAM

Massive Post Production Suite

JPEG Scrubber

Smart Noise scrubber

Full tutorial available.

也有中文说明

Check out my other models:

My NSFW version with Anantomy Correctors: https://civitai.com/models/2270894/zit-nsfw-anatomy-corrector

For ultimate Anime detail and control: https://civitai.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations

For Realism and variety over the base model: https://civitai.com/models/2231181/z-image-ultra-real-workflow

comfyui_controlnet_aux

Node pack · Registry