This is an advanced workflow for those who want to dail in an image at pro level grade. A simple version can be found <a target="_blank" rel="ugc" href="https://civarchive.com/models/2600919/lonecats-simple-zitilluanimaflux-workflows?modelVersionId=2922921">HERE</a>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<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>LC123 Nodes: <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC123_nodes">https://github.com/lonecatone23/ComfyUI_LC123_nodes</a>LC note, which is tied to my LC vision pack, will automatically translate any to the following:<ul><li>English</li><li>中文</li><li>繁體中文</li><li>Русский</li><li>日本語</li><li>한국어</li><li>Français</li><li>Español</li><li>عربي</li><li>Türkçe</li><li>Português (BR)</li><li>فارسی</li><li>עברית</li><li>Italiano</li></ul><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 /><h3 id="v19">V19</h3>Qwen broke all of my workflows, So I am going through and updating them as well as taking time to add new features (or better nodes)<ul><li>fixed Qwen break</li><li>Removed unnecessry LLM instructions. it is now built into Qwen</li><li>Replaced the save nodes with a significantly better system</li><li>Minor clean up.</li></ul><h3 id="v17.1">V17.1</h3>You'll need to update the node pack<ul><li>Change to Color match</li><li>Change to LC Sharpen Pro</li><li>Change to Lut</li><li>Lut folder now auto downloads</li><li>Other tweaks</li><li>Updated Notes</li></ul><h3 id="introducing-lc123-nodes"> Introducing LC123 Nodes</h3>Edie VRAM settings in the ComfyUI settings menu:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c124a015-246b-40c0-a8b1-7c7a070744b3/original=true/c124a015-246b-40c0-a8b1-7c7a070744b3.jpeg" />Smart Denoise (LCImageDenoise)<ul><li>Removes noise while trying to keep detail</li></ul>Color Match (LCColorMatch)<ul><li>Matches colors to a reference image (usually Image 2)</li></ul>Bloom (LCBloom)<ul><li>Soft glow on bright areas (camera light bloom)</li></ul>Vignette (LCVignette)<ul><li>Darkens (or lightens) the edges</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></ul>Auto White Balance (LCAutoWhiteBalance)<ul><li>Tries to neutralize overall color cast</li></ul>Vibrance (LCVibrance)<ul><li>Boosts muted colors without destroying already-saturated areas</li></ul>Chromatic Aberration (LCChromaticAberration)<ul><li>Shifts RGB channels for a 3-D / vintage lens look</li></ul>Sharpen Pro (LCSharpenPro)<ul><li>Adaptive mid-tone contrast / micro-contrast</li></ul>Image Adjust (LCImageAdjust)<ul><li>Brightness, Contrast, Saturation, Sharpness, Blur</li></ul>Lens FX (LCLensFX)<ul><li>General lens distortion and optical effects</li></ul>Lens Profile (LCLensProfile)<ul><li>Applies real lens characteristics (e.g. Canon 50mm f/1.8)</li></ul>Film Stock B&amp;W (LCFilmStockBW)<ul><li>Converts to black &amp; white using real film responses</li></ul>Film Stock Color (LCFilmStockColor)<ul><li>Applies classic color film response (Ektachrome, Portra, etc.)</li></ul>Film Grain (LCFilmGrain)<ul><li>Realistic film grain with lots of control</li></ul>Desaturate (LCImageDesaturate)<ul><li>Partial or full desaturation.</li></ul>Apply LUT (LCApplyLUT)<ul><li>Applies a 3D LUT (.cube file)</li></ul>Image Crop (LCImageCrop)<ul><li>Inline crop tool</li></ul>Text Overlay (LCTextOverlay)<ul><li>Adds text on the final image</li></ul>LC Watermark 💧(LCWatermark)<ul><li>dynamically adds any image as a watermark</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><h3 id="v16">V16</h3>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></ul><h3 id="v15">V15</h3><ul><li>I have been messing around with Anima regional Prompt and got so frustrated, I made my own nodes set <a target="_blank" rel="ugc" href="https://github.com/lonecatone23/ComfyUI_LC123_nodes">https://github.com/lonecatone23/ComfyUI_LC123_nodes</a><ul><li>use an image 🖼️as the background or plain white ⬜</li><li>dynamic canvas means you do not need to open up mask editor</li><li>Plug in a global prompt or enter it here</li><li>works with Controlnet now (Kinda. Still beta )</li><li><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6bf00124-5fd7-49fe-b9a4-8add2449ceae/original=true/6bf00124-5fd7-49fe-b9a4-8add2449ceae.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/985043be-32df-4fdf-b975-36d09a1cb741/original=true/985043be-32df-4fdf-b975-36d09a1cb741.jpeg" /></li></ul></li><li>Vastly Improved Image control<ul><li>added my own set of nodes including 📐 Aspect Ratio Simplifier which saves a boatload of time trying to get the right image size</li></ul></li><li>Other minor OCD tweaks</li></ul><h3 id="v14">V14</h3><ul><li>Vastly improved Controlnet<ul><li>also addresses the break that I was unaware of because hey.. stuff updates 🤔</li><li>⚠️ Controlnet file location has changed. See notes.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fa1a37b5-f5f3-43a4-93e2-a213c922290e/original=true/fa1a37b5-f5f3-43a4-93e2-a213c922290e.jpeg" /></li></ul></li><li>Added I2I 🖼️ and a denoise slider to support it</li><li>Updated the 🧠brains a bit, mainly to work with the slider<ul><li>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)</li></ul></li><li>Minor OCD stuff.</li></ul><h3 id="v10-and-11">V10 &amp; 11</h3><ul><li>Swapped out the detailers to SEGS detailers for significantly better control and quality</li><li>Updated the notes</li><li>Added a GGUF Qwen VL Prompt Enhancer for fast prompts.<ul><li>it's also abliterated, so does NSFW incredibly well 🤔</li></ul></li><li>Added the ability to color match to the original image without having to reload it.</li><li>Updated Hi-res fix</li></ul><h3 id="v9.0">V9.0</h3>Note: Both Controlnet &amp; 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.<ul><li>Added back draft mode by request</li><li>added shhh.. nodes (You'll thank me)</li><li>Made it so you can use the original image ratio.<ul><li>Super good for regional prompts and Controlnet</li></ul></li><li>Added Regional Prompt (BETA)<ul><li>I'm still testing this out. Not sure how I feel about it.</li><li>what it does do well: ART</li><li>what is sucks at: people</li></ul></li><li>Replaced math nodes to be compatible with Linux users</li><li>Tweaks here and there.</li></ul><h3 id="ver-8.0">Ver 8.0</h3><ul><li>added controlnet</li><li>added Klein enhancement</li><li>reworked Post Production Suite</li><li>Minor tweaks.</li></ul><h3 id="ver-6.0">Ver 6.0</h3><ul><li>Upgraded Prompt assist.</li><li>Added an inline crop tool for easier image editing.</li><li>inmproved the save option to include the option to add a date to the metadata file. name for beter organization.</li><li>Minor note tweaks.</li></ul><h3 id="ver-5.2">Ver 5.2</h3><ul><li>Updated for Comfyui changes</li><li>Added sentence remover to prevent CivitAi flags</li><li>Made some optimazation changes for Anima 3 preview</li><li>reworked the user settings area.</li></ul><h3 id="ver-4.0:">Ver 4.0:</h3><ul><li>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</li><li>Added a detailer suite based on SDXL or Illustrious for realistic options<ul><li>Note: It's not gonna beat ZIT, but with the prompt adherence, It's cool for semi-realistic</li></ul></li><li>Included my full detailer suite</li><li>Included my full Post production suite<ul><li>Fine tuned Optical Realism to work with this model (in other words, don't mess with the settings)</li></ul></li><li>Ver 3.0 included in download for straight Anime</li><li>I had to make modifications as to how the Savenodes worked. ComfyUi broke them (again 🙄)</li></ul><h3 id="what-this-workflow-contains:">What this workflow contains:</h3><ul><li>Sage Attention: Speeds up production</li><li>Ultimate Upscaler for prescaling and hi res fix</li><li>Detailing Suite for face, hands, eyes</li><li>Seed VR2 Upscaler to get 4k on low VRAM</li><li>Essential Post Production Suite</li><li>JPEG Scrubber</li><li>Full tutorial available.</li><li>也有中文说明</li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d034cfe2-0c09-4421-acd6-48b7f32d3556/original=true/d034cfe2-0c09-4421-acd6-48b7f32d3556.jpeg" />

ANIMA Pro Grade workflow with speed boost 🚀 , controlnet, regional prompt, detailers, upscalers, & post process

V24You may notice a lot of changes to this version. That's because I decided I needed a version that was true to the model, not just for features. What's Removed:<ul><li>cfg norm. it never really worked the way I wanted anyway</li><li>NSFW detailers. Let's face it. They sucked. They are hit &amp; miss. Use a LoRA. They also do not represent what type of product I am trying to put out there.</li><li>Klein_9b inpaint. It never worked right.</li><li>skin upscalers and realism nodes. It's an Anima workflow</li></ul>What's Added:<ul><li>Speed boost 🚀: My own node that cut's generation time by 50%<ul><li>Note: it does not work when denoise is above 90%, so it is not for I2I</li><li>You can read about it in my article.</li></ul></li><li>Advanced Sigmas: Massivly improve the control you ave over your final product</li></ul>Your feedback is welcome and you can always just plug the modules back in.

Files with SHA256: 721c02b68732fc014804cf1540fc15bf1df1ace7546e87d13c64037b441e84df