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>Comfy Manager is SLOW to upload. sometimes a day or so. If you get ANY missing nodes, just getthem from my repo Here: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23">https://github.com/lonecatone23</a> 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<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="v32">V32</h3>You'll immediatly notice changes. I have redone how images are displayed and checked on the face of the nodes<ul><li>On Node Previews: Click once to get a 100% section of the image. This means you are comparing against the finished product, not a preview. I am the only one who does this.</li><li>I halved some of the settings: I had a lot of nodes I'd have set at 0.2 or 0.3 which meant that there was not any room for meaningful adjustment.<ul><li>the old 1.0 is now 2.0, so whatever setting you are used to, double it.</li><li>Notes on which nodes are on the workflow</li></ul></li><li>Skin Master. read about it Here: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/37274/skin-realism-what-works-what-doesnt-and-a-free-node-to-achieve-it">https://civarchive.com/articles/37274/skin-realism-what-works-what-doesnt-and-a-free-node-to-achieve-it. </a>It's just good.</li></ul><h3 id="v31.1">V31.1</h3><ul><li>added Vision Assistant. Click on muy icon in teh sidebar for a helpful assistant and virtual tour. Read about it here: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/36595/vision-assistant-your-workflow-sidekick">https://civarchive.com/articles/36595/vision-assistant-your-workflow-sidekick</a></li></ul><h3 id="v31:">V31:</h3>I literally forgot to hook up Speed Boost on the last version 🚀🙄. FixedLots of changes:<ul><li>Removed Ultimate Upscaler. Why? VOSR2 does a better job and skin upscaler picks up the slack, plus paster processing times</li><li>Better Detailers. They now have tone match and talk to each other</li><li>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</li><li>Skin upscale and skin texture now talk to the Detailers</li><li>minor adjustments to settings and bug fixes, especially DepthFx. now the haze works the way I want it to and rolls off</li><li>LC Natural Look 🍃: Removes the "AI" look from an image by pulling back the loudest colors and fixing the orange tint</li></ul><h2 id="v30:">V30:</h2><h3 id="i-literally-forgot-to-hook-up-speed-boost!">I literally forgot to hook up speed boost! 🙄</h3>It will be fixed in V31, but if you want to now, it goes between LC sigmas and the first sampler.<ul><li>Installed Speed boost 🚀 Read about it here <a target="_blank" rel="ugc" href="https://civarchive.com/articles/36132/speed-boost">https://civarchive.com/articles/36132/speed-boost</a></li><li>Moved the detailer daemon to the lower sigmas</li><li>I wasn't happy with some thing below speed wise, so I tweaked them, especially DepthFX. Now it's about 20x faster</li><li>new sliders for the detailers</li><li>a timer that actually does something.</li></ul><h3 id="v29"> V29</h3>"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:<ul><li>Notes in 16 different languages<ul><li>Just click on a note dropdown and change it, or go into settings and change every single note to your language</li></ul></li><li>Model Optimizer<ul><li>All the speedups optimized for your computer witha full report and suggestions</li><li>It also will download the model for you if you want</li></ul></li><li>All new sampler configure.<ul><li>I took the best psrts of my old one and made it so they actually speak to each other. Smoother transition.</li><li>all of the original settings are now presets that actually do something</li></ul></li><li>New Detailers<ul><li>The old ones had a bug, plus they didn't work as well as they shoudl have.</li><li>My new ones are skin aware. They do an exceptional job</li></ul></li><li>Allpaint<ul><li>Inpaint, outpaint, rotate, change clothes, swap heads, expose ...ummm.. skin!</li><li>it does it all and all on the face of the node. No mask editor to open</li><li>All in one group.</li></ul></li><li>Skin texture (beta)<ul><li>builds skin pores and skin off of an image.</li><li>still beta, but tests are promising</li></ul></li><li>Optical realism<ul><li>depth aware node</li><li>pro mist on the Bloom filters</li><li>all the toys</li></ul></li></ul><h3 id="v25">V25</h3>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: <a target="_blank" rel="ugc" href="https://github.com/ylchen333/ComfyUI-VOSR2">https://github.com/ylchen333/ComfyUI-VOSR2</a>What I've changed:<ul><li>minor cleanups and organization</li><li>Added VOSR2 Upscaler</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/49726cd6-138f-4d0b-bd49-9e9ddd957901/original=true/49726cd6-138f-4d0b-bd49-9e9ddd957901.jpeg" /><h3 id="v23">V23</h3><ul><li>Swapped out 🎨 Post processing suite for my overhauled Krea2 one</li><li>Added Skin Upscaler</li><li>reworked the nodes so that they are categorized and in the proper order</li></ul><h3 id="v22">V22</h3>Qwen VL broke my workflows, forcing me to update them<ul><li>repaired Qwen break</li><li>Added a better save w/metadata block</li><li>updated notes</li></ul><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 | 专业级工作流 w/ Speed Boost 🚀 I2I/T2I (Low or High VRAM)

V32You'll immediatly notice changes. I have redone how images are displayed and checked on the face of the nodes<ul><li>On Node Previews: Click once to get a 100% section of the image. This means you are comparing against the finished product, not a preview. I am the only one who does this.</li><li>I halved some of the settings: I had a lot of nodes I'd have set at 0.2 or 0.3 which meant that there was not any room for meaningful adjustment.<ul><li>the old 1.0 is now 2.0, so whatever setting you are used to, double it.</li><li>Notes on which nodes are on the workflow</li></ul></li><li>Skin Master. read about it Here: <a target="_blank" rel="ugc" href="https://civitai.red/articles/37274/skin-realism-what-works-what-doesnt-and-a-free-node-to-achieve-it">https://civitai.red/articles/37274/skin-realism-what-works-what-doesnt-and-a-free-node-to-achieve-it. </a>It's just good.</li></ul>

Files with SHA256: 347e0083c67a7103e322ccc4e3f990b72b88a35274ac50184a882ecaf26401a0