This is an advanced workflow designed for those familiar with ComfyUI who want pro grade results. It is node heavy and has numerous options. I encourage you to take the time to learn it. If you feel overwhelmed, you can start with my simple model <a target="_blank" rel="ugc" href="https://civarchive.com/models/2600919/lonecats-simple-zitilluanimaflux-workflows?modelVersionId=2921851">HERE</a>LC123 Nodes: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC123_nodes">https://github.com/lonecatone23/ComfyUI_LC123_nodes</a>也有中文说明<hr />Instagram: <a target="_blank" rel="ugc" href="https://www.instagram.com/synth.studio.models/">https://www.instagram.com/synth.studio.models/</a>Buy me a☕ <a target="_blank" rel="ugc" href="https://ko-fi.com/lonecatone">https://ko-fi.com/lonecatone</a>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 😉<hr />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 directionsA complete user and troubleshooting guide inclusing a list of common error messages can be found here<a target="_blank" rel="ugc" href="Here"> </a><a target="_blank" rel="ugc" href="https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown">https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown</a><h3 id="20.2">20.2 </h3><h3 id="you'll-need-to-update-my-node-pack">You'll need to update my node pack</h3><h3 id="v20">V20</h3><h3 id="introducing-lc123-nodes">Introducing LC123 Nodes</h3>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 adjustVRAM settings can be adjusted in the ComfyUi settings menu:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/022c72ef-c533-49f2-bf77-016526b6ed68/original=true/022c72ef-c533-49f2-bf77-016526b6ed68.jpeg" />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&amp;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: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC123_nodes">https://github.com/lonecatone23/ComfyUI_LC123_nodes</a><h3 id="v19">V19</h3>Major Overhaul<ul><li>Gutted and simplified the aspect ratio and image area.</li><li>Better latent control</li></ul>Complete redo of the 🎨 Post Processing SuiteIt was long overdue. The nodes I used did not really align with Krea2 (or Zit for that matter)What I changed<ul><li>removed the Optical Realism section. The quality dropped and I get better results from individual nodes</li><li>Added white balance</li><li>Updated the color match node to V2</li><li>Added a skin preserving vibrance node</li><li>Added lens profile</li><li>Added radial blur</li><li>Added pro film grain</li><li>Added a better B&amp;W desaturation node</li><li>MASSIVE update of the notes.</li><li>Added new and some custom made LUTS</li></ul><h3 id="v14.0">V14.0</h3>Because it is not in my nature to leave things alone....<ul><li>Gutted the stock face detailer nodes and replaced them with a SEGS suite for infinately better results<ul><li>Note: Yes, I will be going through all my workflows and replacing them, including teh NSFW ones</li></ul></li><li>Controlnet Update.</li><li>Added local bypass nodes so you don't have to zoom and scroll</li><li>Major update to notes, especially for detailers</li></ul><h3 id="v13.0">V13.0</h3>Overhauled the Controlnet:<ul><li>Now you can select the aspect ratio of the original image without having to "guess" it with the aspect ratio node</li><li>Left room for the resize node so you can choose which side to crop the image by</li><li>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 😡</li></ul>Massively improved the notes throughoutMinor layout tweaks<h3 id="v11.3">V11.3</h3><ul><li>Detailers are now able to handle float32 models, so I rewmoved the SDXL Based checkpoint.<ul><li>Please give me feedback with any issues on this, especailly RAM related.</li></ul></li><li>Added a crop section so you can...well... crop images easily</li><li>Updated several areas</li><li>Added the ability to use a simple date with the metadata folder</li><li>added a "remove banned tags" node</li></ul><h3 id="v8.0">V8.0</h3><ul><li>Removed Florence Prompt assist and replaced it with Qwen Advanced.</li><li>Reorganized the controlnet section because it bugged me. Now it's easier to use.</li><li>Added a LoRa controller for the detailer for better character facial and eye consistency as well as a localized prompt</li><li>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</li><li>Added a 📂 subfolder generator that seperates the metadata files according to the name you give the file for easier use.</li></ul><h3 id="v7.0">V7.0</h3><ul><li>Added KSampler Configure Nodes so you can leave the setting in place for both ZIT and base without having to change them</li><li>Removed some problematic nodes</li><li>Removed Qwen Prompt enhancer. I refuse to put an API one in there.</li><li>global scheduler and samplers for consistency</li><li>Better math</li><li>Improved notes throughout.</li></ul>All in 1 workflow:<ul><li>Controlnet</li><li>Checkpoint option for merged models</li><li>I2I</li><li>Prompt generation</li><li>Prompt enhancement</li><li>Lora Loader</li><li>Advanced KSampler</li><li>Draft mode for making corrections without having to rerun the workflow.</li><li>Seed variance enhancer</li><li>Ultimate Upscaler for prescaling and hi res fix</li><li>Detailing Suite for face, hands, eyes, and expressions</li><li>Seed VR2 Upscaler to get 4k on low VRAM</li><li>Massive Post Production Suite</li><li>JPEG Scrubber</li><li>Smart Noise scrubber</li><li>Full tutorial available.</li><li>也有中文说明</li></ul>Check out my other models:My NSFW version with Anantomy Correctors:<a target="_blank" rel="ugc" href="https://civarchive.com/models/2270894/zit-nsfw-anatomy-corrector">https://civarchive.com/models/2270894/zit-nsfw-anatomy-corrector</a>For ultimate Anime detail and control: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations">https://civarchive.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations</a> For Realism and variety over the base model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2231181/z-image-ultra-real-workflow">https://civarchive.com/models/2231181/z-image-ultra-real-workflow</a> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/319710eb-8780-4566-96c2-45e679a8b20c/original=true/319710eb-8780-4566-96c2-45e679a8b20c.jpeg" />

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

Introducing LC123 NodesSmart Denoise (LCImageDenoise)<ul><li>Removes noise while trying to keep detail</li><li>Sigma: higher = smoother, lower = more detail</li><li>Threshold: how aggressive the denoise is</li><li>Radius Multiplier: higher for noisy images, lower for clean ones 💡 Start gentle. Only raise values if the image is actually noisy.</li></ul>Color Match (LCColorMatch)<ul><li>Matches colors to a reference image (usually Image 2)</li><li>Method: “adain” is the most common and stable</li><li>Strength: 0–1</li></ul>Bloom (LCBloom)<ul><li>Soft glow on bright areas (camera light bloom)</li><li>Intensity, threshold, and size controls 💡 A little makes it dreamy. A lot makes it foggy.</li></ul>Vignette (LCVignette)<ul><li>Darkens (or lightens) the edges</li><li>Amount, softness, and roundness 💡 Soft vignette looks more natural than hard black borders.</li></ul>Image RGB (LCImageRGB)<ul><li>Simple red / green / blue channel gain</li></ul>Lift / Gamma / Gain (LCLiftGammaGain)<ul><li>Classic three-way color corrector</li><li>Lift = shadows</li><li>Gamma = midtones</li><li>Gain = highlights 💡 This is where most “film look” color work happens.</li></ul>Auto White Balance (LCAutoWhiteBalance)<ul><li>Tries to neutralize overall color cast</li><li>Method: “Shades of Gray” is usually safest 💡 Effect is subtle — compare before/after.</li></ul>Vibrance (LCVibrance)<ul><li>Boosts muted colors without destroying already-saturated areas</li><li>Kinder to skin than normal saturation</li><li>Vibrance + Saturation + Strength 💡 Prefer this over regular saturation for portraits.</li></ul>Chromatic Aberration (LCChromaticAberration)<ul><li>Shifts RGB channels for a 3-D / vintage lens look</li><li>Separate horizontal/vertical amounts for R, G, B 💡 A little goes a long way. Try small opposite values (R +2, G –1, B –3).</li></ul>Sharpen Pro (LCSharpenPro)<ul><li>Adaptive mid-tone contrast / micro-contrast</li><li>Radius, strength, blend mode, shadow/highlight controls 💡 Super important node. Adds “pop” without the cardboard cut-out look.</li></ul>Image Adjust (LCImageAdjust)<ul><li>Brightness, Contrast, Saturation, Sharpness, Blur</li><li>Brightness center = 0</li><li>Contrast &amp; Saturation center = 1</li></ul>Lens FX (LCLensFX)<ul><li>General lens distortion and optical effects 💡 Pair with the next node for more realistic camera simulation.</li></ul>Lens Profile (LCLensProfile)<ul><li>Applies real lens characteristics (e.g. Canon 50mm f/1.8)</li><li>Optional aberrations 💡 Adds subtle optical imperfections that make AI images feel more photographic.</li></ul>Film Stock B&amp;W (LCFilmStockBW)<ul><li>Converts to black &amp; white using real film responses</li><li>50+ stocks (Ilford HP5+, Kodak Tri-X, Fuji Acros, etc.)</li><li>Strength + optional filter 💡 Leave this off if you want to keep color.</li></ul>Film Stock Color (LCFilmStockColor)<ul><li>Applies classic color film response (Ektachrome, Portra, etc.)</li><li>Strength is the main control 💡 0.6–0.9 often looks more natural than full strength.</li></ul>Film Grain (LCFilmGrain)<ul><li>Realistic film grain with lots of control</li><li>Power, scale, shadows/highlights, seed 💡 Fixed seed keeps the grain consistent. Slightly more grain in shadows usually looks better.</li></ul>Desaturate (LCImageDesaturate)<ul><li>Partial or full desaturation</li><li>Several methods (luminance Rec.709 is common) 💡 Useful right before a LUT if you want a muted base.</li></ul>Apply LUT (LCApplyLUT)<ul><li>Applies a 3D LUT (.cube file)</li><li>Strength 0–1</li><li>Log option for certain LUTs 💡 Free LUTs at <a target="_blank" rel="ugc" href="http://freshluts.com">freshluts.com</a>. Strength 0.3–0.7 is often nicer than 1.0. Put .cube files in the luts folder.</li></ul>Image Crop (LCImageCrop)<ul><li>Inline crop tool</li><li>X / Y / Width / Height or free mode 💡 Crop after all effects so you don’t lose edge treatments (vignette, bloom, etc.).</li></ul>Text Overlay (LCTextOverlay)<ul><li>Adds text on the final image</li><li>Font, size, color, position, opacity</li><li>applies on 2nd run</li></ul>LC Watermark 💧(LCWatermark)<ul><li>dynamically adds any image as a watermark</li><li>adjust size, location, and opacity</li><li>applies on the 2nd run</li></ul>Plus plenty of other options. Check them out here: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC123_nodes">https://github.com/lonecatone23/ComfyUI_LC123_nodes</a>

Files with SHA256: fb195e962ac7d03c95214de4d421ef967e46afc6f92aec2f7034547097dd480c