<h1 id="how-to-use-(updated-10.11.2026)-:">HOW TO USE (UPDATED 10.11.2026) :</h1><a target="_blank" rel="ugc" href="https://civarchive.com/articles/21795/comfyui-tutorial-dynamic-multi-character-workflow-workflow-guide">https://civarchive.com/articles/21795/comfyui-tutorial-dynamic-multi-character-workflow-workflow-guide</a><h1 id="update-highlights-version-2.1">- Update Highlights – Version 2.1</h1><ul><li>True per-character LoRAs, with zero bleeding. Each character now has its own LoRA Stacker: its LoRAs are applied only inside that character's mask, never on the other characters. Attention Couple is kept for the prompts, so you keep the same precision and coherence, even when characters touch or interact. Characters without a LoRA add no extra generation time.</li><li>Per-character trigger words. Each character gets its own TriggerWord Toggle: the trigger words of its LoRAs are added automatically to its own prompt, and you can switch each word on or off.</li><li>Completely rebuilt the Detailer section around the characters. Body, Face and Eyes detailers now run separately for each character, only inside its mask, with its own prompt and its own LoRAs. No more eye colors, hair or faces swapped between characters. Hands and NSFW detailers stay global.</li><li>Detailers now use a clean model (without the Attention Couple / ControlNet patches), giving much more accurate results on cropped areas.</li><li>One switch per character. Bypassing a "Character" group in the control center now disables everything for that character: prompt, mask, LoRAs and detailers.</li><li>Faster and lighter pipeline: removed the second sampler, which was only used as a color reference. Color correction now uses the first sampler image.</li><li>Bug fixes:</li><li>Fixed masks not matching the image size after the Hi-Res Fix.</li><li>Characters 3 and 4 now receive the global LoRAs (style, sliders, lighting…) like characters 1 and 2.</li><li>The Image Saver now writes the real metadata: model, prompts, seed, steps, CFG, sampler and scheduler.</li><li>Detailer seeds are now linked to the main Seed, so every image can be reproduced exactly.</li><li>Cleaned up the workflow: removed unused nodes, fixed inconsistent node titles, and all labels are now in English.</li><li>New test material: 5 ready-to-use color masks with matching prompts (duo, height difference, trio, quartet, hug) to check your setup in one click.</li><li>Note: this version requires a small new custom node pack (Character Mask Hook – included in the download), and a recent version of ComfyUI (hooks support).</li></ul><h1 id="update-highlights-version-1.7">- Update Highlights – Version 1.7</h1><ul><li>Completely revamped the ControlNet section, providing much more precise control, better reference handling, and a more efficient workflow for multi-character generations.</li><li>Rebuilt the masking system from the ground up, now using color-based masks for significantly more accurate character and area separation.</li><li>Added FL Photopea integration, allowing you to directly paint and edit masks on your image for much finer control over individual characters and regions.</li><li>Fully reworked the Detailer section, improving precision, reliability, and ease of use when refining multiple characters.</li><li>Improved the overall workflow structure and user experience, making the setup cleaner, more intuitive, and easier to navigate while keeping the flexibility needed for advanced users.</li><li>Various quality-of-life improvements and refinements across the workflow for a smoother, more precise, and more efficient generation experience.</li></ul><h1 id="update-highlights-version-1.6">- Update Highlights – Version 1.6</h1><ul><li>Fully reworked the Detailer section, featuring better model selection and a cleaner, more readable display. This results in sharper outputs and a smoother experience when fine-tuning details.</li><li>Revamped the Preview system, making it more responsive and easier to read at a glance, improving iteration speed during generation.</li><li>Enhanced the Color Correction and Final Image pipeline, providing more consistent tones, better lighting balance, and overall higher-quality outputs.</li><li>Improved the overall workflow structure and visual clarity, making the setup more intuitive and user-friendly while keeping full flexibility for advanced users.</li><li>Various quality-of-life improvements and refinements across the workflow for a smoother and more efficient experience.</li></ul><h1 id="update-highlights-version-1.5">- Update Highlights – Version 1.5</h1><ul><li>Added LoRA Manager integration, allowing users to easily load, organize, and blend multiple LoRAs without clutter. This makes character and style creation much faster and more intuitive.</li><li>Improved stability and layout readability, refining the node flow to make it more logical and beginner-friendly while preserving full modular control.</li><li>Updated tutorial and usage guide, including a full step-by-step explanation on how to install, configure, and use the workflow efficiently.</li><li>Minor adjustments to default samplers and CFG values for better consistency across multi-character generations.</li></ul><h1 id="update-highlights-version-1.4">- Update Highlights – Version 1.4</h1><ul><li>Completely redesigned for better readability and ease of use, heavily inspired by vslinx’s workflow (shoutout to him).</li><li>The preview section has been revised for clearer and more intuitive feedback during generation.</li><li>The old dual-sampler setup has been replaced with a dedicated Hi-Res Fix node, improving image coherence and reducing anomalies during upscaling.</li><li>A new image filter now generates multiple base images depending on the batch size, allowing users to select the most suitable one before moving forward with detailing.</li></ul><h1 id="update-highlights-version-1.3">- Update Highlights – Version 1.3</h1><ul><li>Reverted some previous changes that didn’t provide meaningful benefits.</li><li>Improved readability: reorganized key sections of the workflow for better clarity and structure.</li><li>Enhanced usability: streamlined certain modules to make the workflow more beginner-friendly and intuitive.</li><li>Bug fixes:<ul><li>Fixed issues with image upscaling using a second sampler. The upscaling process is now smoother and more reliable.</li><li>Addressed various minor bugs to improve overall workflow consistency and stability.</li></ul></li></ul><h1 id="update-highlights-version-1.2">- Update Highlights – Version 1.2</h1><ul><li>Wildcard support added for more varied and automated prompt generation</li><li>Auto-masking system implemented → Automatically generates a base image to feed the mask detection logic</li><li>Manual masking system retained</li></ul><h1 id="update-highlights-version-1.1">- Update Highlights – Version 1.1</h1><ul><li>Added dedicated Detailer modules for: • Face • Eyes • Hands These provide better control and enhanced precision for high-focus areas</li><li>Introduced an optional NSFW Deta</li></ul>Introducing a powerful character design pipeline built around Illustrious — ideal for generating complex scenes with multiple precise characters, each with their own LoRA, styling, and pose masks.<h2 id="key-features:">✨ Key Features:</h2><h3 id="mask-guided-multi-lora-framework">▫ Mask-Guided Multi-LoRA Framework</h3><ul><li>Supports multiple distinct characters with independent LoRAs</li><li>Each character area is defined via custom mask drawing (manual or input-based)</li><li>Dedicated nodes for LoRA types (style, body, clothing, accessories)</li></ul><h3 id="optimized-illustrious-foundation">▫ Optimized Illustrious Foundation</h3><ul><li>Built on the Illustrious model family for rich detail and dynamic anatomy</li><li>Configured for stable multi-character composition</li><li>Modular design: easily customize scenes, lighting, camera, or prompt focus</li></ul><h3 id="creator-focused-workflow">▫ Creator-Focused Workflow</h3><ul><li>Enables high-precision, high-consistency character creation across generations</li><li>Ideal for multi-shot concepts, lineup renders, or consistent storytelling</li><li>Great for experimenting with pose, outfit swaps, or stylization</li></ul><h3 id="perfect-for:">▫ Perfect For:</h3><ul><li>Multi-character fanart creators</li><li>Professional concept artists</li><li>Users who want full prompt and visual control</li></ul><h3 id="download-includes:">▫ Download Includes:</h3><ul><li>Main JSON workflow (ComfyUI ready)</li><li>Pre-configured node templates for characters and ControlNet masks</li><li>Prompt/Negative prompt structure examples</li><li>Optional face detailer setup</li></ul><h1></h1><h1 id="feedback-and-feature-requests-:">Feedback &amp; Feature Requests :</h1>I’m still actively improving this workflow — if you have suggestions, requests, or feature ideas, I’d love to hear them. Whether it’s a bug, usability issue, or a new tool you’d like integrated, feel free to share your feedback directly on the Civitai post or by message. Community input is extremely valuable and helps shape future updates!<h1 id="ressources-:">Ressources :</h1><h2 id="detailers-models-:">Detailers Models :</h2>FACE<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1222100/mask-adetailer-face-detailer-for-eyes-eyebrows-and-nose">Mask aDetailer – Specialized for enhancing eyes, eyebrows, and nose</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1076050/adetailer-anime-girl-face-segmentation">ADetailer Anime Girl Face</a></li></ul>EYES<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/camenduru/ultralytics/blob/main/PitEyeDetailer-v2-seg.pt">PitEyeDetailer v2</a></li></ul>LIPS<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/142240/adetailer-after-detailer-lips-model">ADetailer Lips Model</a></li></ul>NOSE<ul><li><a target="_blank" rel="ugc" href="https://www.mediafire.com/file/f6buda8p06cosn6/adetailerNose_.pt/file">ADetailer – Nose Model</a></li></ul>HANDS<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/blob/main/hand_yolov8s.pt">hand_</a><a target="_blank" rel="ugc" href="http://yolov8s.pt">yolov8s.pt</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/blob/main/hand_yolov9c.pt">hand_</a><a target="_blank" rel="ugc" href="http://yolov9c.pt">yolov9c.pt</a></li></ul>NIPPLES<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1132590/nipple-adetailer-for-anime-girls">Anime Girls Nipple Adetailer</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/490259/adetailer-nipples-model">ADetailer – Nipples Model</a></li></ul>VAGINA<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/1313556/anime-nsfw-detectionadetailer-all-in-one">All-in-One Anime NSFW Detection &amp; ADetailer</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/150234/pussy-adetailer">Pussy Adetailer</a></li></ul>PENIS<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/310687/cock-and-ball-detection-2d-edition-adetailer">Cock &amp; Ball Detection</a></li></ul><h2 id="nodes-used:">Nodes used:</h2><ul><li><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Pack">ComfyUI Impact Pack</a></li><li><a target="_blank" rel="ugc" href="https://github.com/pythongosssss/ComfyUI-Custom-Scripts">ComfyUI-Custom-Scripts</a></li><li><a target="_blank" rel="ugc" href="https://github.com/jags111/efficiency-nodes-comfyui">efficiency-nodes-comfyui</a></li><li><a target="_blank" rel="ugc" href="https://github.com/giriss/comfy-image-saver">Save Image with Generation Metadata</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Nourepide/ComfyUI-Allor">Allor Plugin</a></li><li><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Subpack">ComfyUI Impact Subpack</a></li><li><a target="_blank" rel="ugc" href="https://github.com/pamparamm/ComfyUI-ppm">ComfyUI-ppm</a></li><li><a target="_blank" rel="ugc" href="https://github.com/mirabarukaso/ComfyUI_Mira">ComfyUI_Mira</a></li><li><a target="_blank" rel="ugc" href="https://github.com/jamesWalker55/comfyui-various">Various ComfyUI Nodes by Type</a></li><li><a target="_blank" rel="ugc" href="https://github.com/alexopus/ComfyUI-Image-Saver">ComfyUI Image Saver</a></li><li><a target="_blank" rel="ugc" href="http://Eden.art">Eden.art</a><a target="_blank" rel="ugc" href="https://github.com/edenartlab/eden_comfy_pipelines"> nodesuite</a></li><li><a target="_blank" rel="ugc" href="https://github.com/chrisgoringe/cg-image-filter">cg-image-filter</a></li><li><a target="_blank" rel="ugc" href="https://github.com/M1kep/ComfyLiterals">ComfyLiterals</a></li><li><a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">rgthree's ComfyUI Nodes</a></li></ul><h2 id="join-the-discord!">Join the Discord!</h2> Come hang out, share your AI art, give feedback, ask questions, or just vibe with the community. It’s also the best place for troubleshooting, commissions, and sneak peeks of upcoming work.👉 <a target="_blank" rel="ugc" href="https://discord.gg/zBK8QNZ7xt">https://discord.gg/zBK8QNZ7xt</a>

Dynamic Multi-Character Workflow – ALL IN ONE Regional Prompts & Wildcards! (Comfyui)

Illustratious - Workflow - Multiple Person V2.1.zip

v2.1

v1.7

v1.6

v1.5

v1.4

v1.3

v1.2

v1.1

v1.0

Files with SHA256: c575b9f865977c175051f5c221d2199e381aa1b220f980d8905f8802794ec509