sexual situations

physical violence

disturbing

male nudity

extremist

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

suggestive

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

sexy

nsfw

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

TRPCError

<h1 id="sdxl-flux-ultimate-workflow-khbcj8mb5">SDXL FLUX ULTIMATE Workflow</h1>Everything you need to generate amazing images! Packed full of useful features that you can enable and disable on the fly. Contains multi-model / multi-LoRA support, Ultimate SD Upscaling, Segment Anything, and Face Detailer.<h2 id="version-5.0.3-has-fixed-the-generation-issue-with-5.0.-x10oco9sz">Version 5.0.3 has fixed the generation issue with 5.0.</h2><h2 id="version-5.0-now-has-flux-support-and-img2img-upscaling-along-with-all-previous-features!-q4s45p0p7">Version 5.0 now has FLUX support and img2img upscaling, along with all previous features!</h2><h2 id="community-discord-6viad5bnm">Community Discord</h2>Come join me in my Discord server to ask any questions you may have, make suggestions for future versions of this workflow, or post your creations!<a target="_blank" rel="ugc" href="https://discord.gg/y8C5ACnBnG">https://discord.gg/y8C5ACnBnG</a><h2 id="ultimate-sd-upscaler-exrkfxyd7">Ultimate SD Upscaler</h2>With the Ultimate SD Upscaler, you can push your images to much higher resolution without needing a supercomputer to run it. 2x, 3x, 4x, you can do it all! This uses a tiled approach to upscaling, where each tile is the original txt2img resolution.<h2 id="-cln1jo69g"></h2><h2 id="after-detailer-st7540e0v">After Detailer</h2>Ever generate an amazing image, only to have the face be sub-par? With the Face Detailer extension, you can swap that face out with a new one! This extension has it's own positive and negative prompts, as well as seed and sampler, so you can tweak it until it's just right. To add to the customizability, it also supports swapping between SDXL models and SD 1.5 models. With this, you can get the faces you've grown to love, while benefiting from the highly detailed SDXL model.<h2 id="face-restore-mh74nc2ut">Face Restore</h2>Similar to Automatic1111, you can now run face restore after each module. Toggle it on and off without having to regenerate the image! It only takes a few seconds to run.<h1 id="setup-sddjhmjem">Setup</h1><h2 id="download-comfyui-windows-portable-8u9v8j759">Download ComfyUI Windows Portable</h2>Skip this step if you already have it downloaded, unless you would like to do a fresh reinstall.<ol><li>Go to: <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#windows">https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#windows</a></li><li>Use the <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_cu121_or_cpu.7z">Direct link to download</a></li><li>Extract the zip file with <a target="_blank" rel="ugc" href="https://7-zip.org/">7-Zip</a> or <a target="_blank" rel="ugc" href="https://www.win-rar.com/start.html?&amp;L=0">WinRar</a> - If you run into issues due to max path length, you can try WinRar instead of 7-Zip.</li></ol><h2 id="update-comfyui-and-python-dependencies-wwkb3ksvk">Update ComfyUI and Python Dependencies</h2>You may run into errors due to outdated dependencies if you do not do this. This will update ComfyUI and the embedded Python environment modules to the latest version.<ol><li>Goto <code>update\</code></li><li>Run <code>update_comfyui_and_python_dependencies.bat</code></li></ol><h2 id="update-model-paths-kykgih2ho">Update Model Paths</h2>If you have a previous installation of ComfyUI with Models, or would like to use models stored in an external location, you can use this method to reference them instead of re-downloading them.<ol><li>Goto <code>ComfyUI_windows_portable\ComfyUI\</code></li><li>Rename <code>extra_model_paths.yaml.example</code> to <code>extra_model_paths.yaml</code></li><li>Open the YAML file in a code or text editor</li><li>Change the <code>base_path</code> value to the location of your models</li></ol><h3 id="example-3xhf47dcl">Example</h3>base_path: C:\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\models\checkpoints: checkpointsconfigs: configsvae: vaeloras: |lorasupscale_models: |upscale_modelsembeddings: embeddingshypernetworks: hypernetworkscontrolnet: controlnetultralytics: ultralytics<h2 id="install-comfyui-manager-31vwqw4vt">Install ComfyUI Manager</h2><ol><li>Follow instructions to install <a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Manager?tab=readme-ov-file#installationmethod2-installation-for-portable-comfyui-version-comfyui-manager-only">ComfyUI Manager Installation Method 2</a></li></ol><h2 id="install-custom-nodes-ekar0cmk2">Install Custom Nodes</h2><ol><li>Launch ComfyUI using <code>run_nvidia_gpu.bat</code> (preferred) or <code>run_cpu.bat</code></li><li>Open ComfyUI Manager</li><li>Goto Install Custom Nodes (not Install Missing Nodes)</li><li>Use the Custom Nodes List below to install each of the missing nodes</li></ol><h2 id="install-missing-models-pc2lpn3gd">Install Missing Models</h2><ol><li>Open ComfyUI Manager</li><li>Goto Install Models</li><li>Use the Models List below to install each of the missing models</li></ol><h2 id="relaunch-comfyui-to-test-installation-mmfshis3s">Relaunch ComfyUI to test installation</h2><ol><li>Close ComfyUI and kill the terminal process running it</li><li>Launch ComfyUI again to verify all nodes are now available and you can select your checkpoint(s)</li></ol><h2 id="usage-instructions-dzi463usa">Usage Instructions</h2>This is under construction... I will leave you with a few high-priority usage notes for now.<ol><li>Ensure that a valid model is selected for each enabled loader (ie. checkpoint loaders, lora loaders, ultralytics loaders, etc.)- If there is an invalid one selected, you will get an error. This error will show you where it has failed. - Even if you see the name of a model, click on the dropdown to select one yourself.</li><li>There are some basic usage instructions in the workflow itself discussing how to use the "modules". Please read them and follow them.- Once you get the hang of it, it really is easy to use. I use this workflow personally for ALL generations.</li><li>If you un-bypass a module it will un-bypass all subsections of the module. You may need to re-bypass a subsection (ie. ControlNet LLLite).</li></ol><h2 id="flux-models-rttwhq1ul">FLUX Models</h2><a target="_blank" rel="ugc" href="https://civitai.com/models/618692">FLUX Dev | Schnell model</a><a target="_blank" rel="ugc" href="https://civitai.com/models/619150/flux1-dev-vae">FLUX Dev VAE</a><a target="_blank" rel="ugc" href="https://civitai.com/models/619167/flux1-schnell-vae">FLUX Schnell VAE</a><a target="_blank" rel="ugc" href="https://huggingface.co/lllyasviel/flux_text_encoders/blob/main/t5xxl_fp16.safetensors">FLUX FP16 CLIP</a><a target="_blank" rel="ugc" href="https://huggingface.co/lllyasviel/flux_text_encoders/blob/main/t5xxl_fp8_e4m3fn.safetensors">FLUX FP8 CLIP</a><a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors">FLUX CLIP_L</a><h2 id="custom-nodes-list-fs2a155x7">Custom Nodes List</h2><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Pack">ComfyUI Impact Pack</a><a target="_blank" rel="ugc" href="https://github.com/Fannovel16/comfyui_controlnet_aux">ComfyUI's ControlNet Auxiliary Preprocessors</a><a target="_blank" rel="ugc" href="https://github.com/jags111/efficiency-nodes-comfyui">Efficiency Nodes for ComfyUI Version 2.0+</a><a target="_blank" rel="ugc" href="https://github.com/Derfuu/Derfuu_ComfyUI_ModdedNodes">Derfuu_ComfyUI_ModdedNodes</a><a target="_blank" rel="ugc" href="https://github.com/WASasquatch/was-node-suite-comfyui">WAS Node Suite</a><a target="_blank" rel="ugc" href="https://github.com/BadCafeCode/masquerade-nodes-comfyui">Masquerade Nodes</a><a target="_blank" rel="ugc" href="https://github.com/tinyterra/ComfyUI_tinyterraNodes">tinyterraNodes</a><a target="_blank" rel="ugc" href="https://github.com/ssitu/ComfyUI_UltimateSDUpscale">UltimateSDUpscale</a><a target="_blank" rel="ugc" href="https://github.com/melMass/comfy_mtb">MTB Nodes</a><a target="_blank" rel="ugc" href="https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes">Comfyroll Studio</a><a target="_blank" rel="ugc" href="https://github.com/evanspearman/ComfyMath">ComfyMath</a><a target="_blank" rel="ugc" href="https://github.com/twri/sdxl_prompt_styler">SDXL Prompt Styler</a><a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">rgthree's ComfyUI Nodes</a><a target="_blank" rel="ugc" href="https://github.com/kohya-ss/ControlNet-LLLite-ComfyUI">ControlNet-LLLite-ComfyUI</a><a target="_blank" rel="ugc" href="https://github.com/storyicon/comfyui_segment_anything">segment anything</a><a target="_blank" rel="ugc" href="https://github.com/jitcoder/lora-info">LoraInfo</a><a target="_blank" rel="ugc" href="https://github.com/alexopus/ComfyUI-Image-Saver">ComfyUI Image Saver</a><a target="_blank" rel="ugc" href="https://github.com/throttlekitty/SDXLCustomAspectRatio">SDXLCustomAspectRatio</a><a target="_blank" rel="ugc" href="https://github.com/failfa-st/failfast-comfyui-extensions">failfast-comfyui-extensions</a><h2 id="models-list-3sr0rx6n9">Models List</h2><a target="_blank" rel="ugc" href="https://github.com/madebyollin/taesd">TAESDXL Decoder</a><a target="_blank" rel="ugc" href="https://github.com/madebyollin/taesd">TAESDXL Encoder</a><a target="_blank" rel="ugc" href="https://github.com/madebyollin/taesd">TAESD Decoder</a><a target="_blank" rel="ugc" href="https://github.com/madebyollin/taesd">TAESD Encoder</a><a target="_blank" rel="ugc" href="https://github.com/facebookresearch/segment-anything#model-checkpoints">ViT-H SAM model</a><a target="_blank" rel="ugc" href="https://github.com/facebookresearch/segment-anything#model-checkpoints">ViT-B SAM model</a><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/tree/main">face_yolov8n (bbox)</a><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/tree/main">hand_yolov8n (bbox)</a><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/tree/main">person_yolov8m (segm)</a><h2 id="suggested-settings-23p9i4hw8">Suggested Settings</h2>Enable Image Feed - Disabled (will destroy performance if enabled)Link Render Mode - Straight(rgthree) Optimize ComfyUI's Execution - Enabled(rgthree) Prompt Progress Bar - Enabled(rgthree) Auto Nest Subdirectories - Enabled(rgthree) Show fast toggles in Group Headers - Enabled (bypass only)

**FIXED VERSION**Now with FLUX Support and img2img!v5.0.3<ul><li>img2img module added</li><li>FLUX txt2img module added</li><li>FLUX img2img upscaling module added</li></ul>

v5.0.3

Now with FLUX Support and img2img!v5.0<ul><li>img2img module added</li><li>FLUX txt2img module added</li><li>FLUX img2img upscaling module added</li></ul>

v5.0

Complete rebuild to support easier use and extension!v4.0<ul><li>TXT2IMG, Ultimate SD Upscaler, After Detailer, and Segment Anything</li><li>Writes generation params, models, and loras to metadata for full CIVITAI support</li><li>Easy to extend with your own functionality</li></ul>

v4.0

SDXL ULTIMATE V3.2<ul><li>Improved Control System!</li><li>Face Restore (like Auto1111)</li><li>Prompt Styler<ul><li>Pick a style to influence your generations</li></ul></li><li>Metadata Extractor<ul><li>Drag-and-drop your image to view the prompt details and save it in A1111 format so CivitAI can read the generation details</li></ul></li></ul>

v3.2

SDXL ULTIMATE V3.1<ul><li>Bug fixes!</li><li>Canny / Depth / OpenPose ControlNet</li><li>Full SD 1.5 support</li><li>More memory efficient</li><li>Clean install script included</li></ul>

v3.1

SDXL ULTIMATE V3.0<ul><li>New easier to use and understand UI</li><li>Canny &amp; Depth ControlNet</li><li>Inpainting</li><li>Ultimate SD Upscaling</li><li>img2img Upscaling</li><li>AfterDetailer (Face / Hand / Body)</li><li>Customize your own image processing pipeline</li></ul>and so much more....

v3.0

SDXL ULTIMATE V2.4<ul><li>Added ability to adjust image contrast</li><li>Added img2img generation as optional input to Ultimate SD Upscaler</li><li>Fixed alternative VAE selector (0 = base | 1 = alternative)</li><li>Replaced image aspect ratio selector to support custom sizes</li><li>Adjusted AfterDetailer module default settings to improve quality</li></ul>

v2.4

SDXL ULTIMATE V2.3<ul><li>Support for both SDXL Base-only and Base + Refiner flows</li><li>Support for alternate VAE loading</li><li>Support for loading outside images for upscaling</li></ul>

v2.3

SDXL ULTIMATE V2.1<ul><li>Fixed issue where images were regenerating when using same seed and prompt</li></ul>

v2.1

SDXL ULTIMATE V2.0<ul><li>New module-based layout giving far more flexibility!</li><li>AfterDetailer (Face, Hand, Person)</li><li>Inpainting (draw custom masks)</li><li>Inpainting (segmentation)</li></ul>

v2.0

SDXL ULTIMATE V1.2<ul><li>LoRA &amp; Lycoris support for txt2img, img2img, and Ultimate SD Upscaler</li><li>Face detailer now properly works with img2img</li><li>Face detailer has LoRA &amp; Lycoris support</li></ul>

v1.2

Complete SDXL 1.0 Workflow<ul><li>txt2img</li><li>img2img upscaling</li><li>Ultimate SD Upscaler</li><li>FaceDetailer</li><li>Toggle anything on and off</li></ul>

v1.0

SDXL FLUX ULTIMATE Workflow v5.0