ComfyUI Workflows

Workflow

ZImageTurbo

[ZIT] 🎨 Anime <-> Real: ⚡"Pro-Detailer & High-Res Transformer"⚡

🏗️ [AuraFlow] Versatile Realism &amp; Anime Transformer (Bi-Directional)This high-performance architecture is designed for seamless transitions between Anime/Manga styles and Hyper-Realism. It works both ways: turn your sketches or anime prompts into photos, or "anime-fy" real photos with perfect anatomical consistency.🌟 Key Features:Character-Ready Dual Circuit: Both the main generation and the Detailer circuits are Character LoRA compatible. This ensures that your character's identity remains perfectly consistent from the base composition to the final micro-details (eyes, skin, features).Dual-Circuit Independent Detailer: Features separate, dedicated circuits for Face and Hands (BBox + SEGS). The Detailer uses its own dedicated LoRA stack, allowing you to inject skin textures or character-specific refinements during the inpainting phase.SeedVR2 High-Res Upscale: Includes a high-fidelity SeedVR2 upscale pass. This ensures your final output isn't just larger, but enriched with the sharpest, most realistic details possible.Human-in-the-Loop Interaction: Includes a Preview Image with Pause node. The workflow stops after the base generation so you can validate the composition before the GPU-heavy detailing and upscaling starts. Save time and VRAM!Clean LoRA Management: Powered by rgthree's Power Lora Loader to stack and control multiple LoRAs (Style, Character) for the main pass, and a separate one for the Detailer pass.Fully Bi-Directional: * Realism Mode: Use a lower denoise (0.45-0.55) to inject skin textures and lighting into anime bases.Anime Mode: Use a higher denoise (0.6+) to let the AI "draw" over real-life photo structures.Color-Coded Organization: Every section is grouped by color for easy navigation and logic understanding.🛠️ Required Custom Nodes:rgthree-comfy (Power Lora Loader, Context)ComfyUI-Custom-Scripts (Preview Image with Pause)Impact Pack (Face Detailer, BBox Detectors)AuraFlow (Base Model setup)SeedVR2 Nodes (for the High-Res Upscale pass)💡 Pro Tips:The Detailer Trick: Load your Character LoRA in both the main loader AND the Detailer loader to ensure the face doesn't "drift" during the enhancement phase.The Pause: The workflow halts after the first KSampler. Check the silhouette—if it’s a winner, hit Resume to trigger the Detailers and High-Res fix.

⭐ 0.0 ⬇ 178

Workflow

AuraFlow

ComfyUI beginner friendly AuraFlow Text-to-Image GGUF Workflow by Sarcastic TOFU

This is a very simple ComfyUI beginner friendly Text-to-Image workflow that will work with a single AuraFlow GGUF model with multiple LORAs (This workflow does require ComfyUI's LORA Manager plugin to function. It is a good idea to install both ComfyUI manager and LORA Manager plugin to help you easily download and manage Checkpoints, LORAs and other resources. Not only these two are helpful for this workflow but they will help you a lot in any other cases). You need a Hugging Face account to download your necessary AuraFlow model files (Details are mentioned below). Make sure you install GGUF addon for ComfyUI using ComfyUI manager and place the correct files in correct places. Also check out my other workflows for SD 1.5 + SDXL 1.0, WAN 2.1, WAN 2.2, QWEN, HiDream, KREA, Chroma and Flux. In my personal experience I have found this AuraFlow model a good middle-ground model between SDXL 1.0 models and Flux models. AuraFlow is a fully open-source, flow-based text-to-image generation model with 6.8 billion parameters, developed by Fal AI. It achieves state-of-the-art results on GenEval, a benchmark for measuring text-to-image model performance. The model is currently at version 0.3 and is licensed under Apache 2.0, making it completely free to use and modify. This can generate nearly as good quality image output as Flux can (it's quality is more like SDXL, but better especially for generating better texts within output image) with less resources than Flux. It gives prompters options to provide negative prompts for some additional control of output (like SDXL). This uses regular SDXL VAE (you can use existing one for SDXL) and sometimes work very well with your existing SDXL LORAs (only with few lucky LORAs, you may encounter many issues with most). This is definately worth trying!How to use this -#1. Just select your desired AuraFlow GGUF model first and then load#2. one or multiple matching LORA(s) from LORA Manager to start#3. then input your positive and negative prompts.#4. select how many images you want (Change the number besides the "Run" button)#5. select image output dimensions, sampling methods, CFG, steps etc. settings and any other optional settings#6. finally press the run button to generate. That's it..*** This workflow will also function if you know how to properly disable the LORA Node and bypass it.Enjoy!### To use this workflow you need to log into huggingface and download necessary files from there (I also included a text file on the archive that has the workflow file, in which you will find even more links for essential downloads for my other workflows) -## Required Models=========================================================================================================================### Download Links for AuraFlow Checkpointshttps://huggingface.co/city96/AuraFlow-v0.3-gguf/resolve/main/aura_flow_0.3-Q4_K_S.gguf### Download Links for AuraFlow Encodershttps://huggingface.co/fal/AuraFlow-v0.3/resolve/main/text_encoder/model.safetensors### Download Links for SDXL VAE (Note - AuraFlow uses the standard SDXL VAE)https://huggingface.co/stabilityai/sdxl-vae/resolve/main/sdxl_vae.safetensors% LORA Used in this Workflow example (you can use this or other LORAs or no LORAs)----------------------------------------------------------------------------------PVC style LoRA for AuraFlow v0.3 - https://civitai.com/models/1103752?modelVersionId=1239914

⭐ 0.0 ⬇ 67

Workflow

Flux.1 S

Mode [Flux,SD3,SDXL,AURA,HYD,SD1,SC]

系统根据模型通过5个特别优化的工作流程自动重新路由。编写prompt并加载模型。点击播放。就是这样。SD1、SDXL、SD3、FLUX、AURAFLOW、HUNYUANDIT和~eh Stable Cascade。您需要更新选择器节点https://github.com/exdysa/comfyui-selector（它们在ComfyOrg注册表中，而不是在CivitAI上）。Dev不会检测到Schnell。模块化绿松石组可以拖动，方便重新路由和诊断。采样器输入是彩色编码的。调度器、求解器和方向可以洗牌与模型兼容的设置。OLLAMA LLM prompt。输出端口已准备好进行升级和细节化。注意：这个项目已经被放弃。有人告诉我，像这样自动化ComfyUI是不可能的。不，但ComfyUI不适用于复杂的应用程序。超过300个节点填满了屏幕。系统跟不上。自动切换极难测试。这是不可持续的，但它可能会提供信息、动力和教育。探索ComfyUI的局限性。没有支持。我不知道它是否还能用。我不在乎。我现在在用扩散器。请期待它。˶𝞢⤬⫒ⵖsᐼ˶ ⠑⠭⠙⠽⠎⠁The system automatically reroutes according to the model through 5 specially optimized workflows. Write prompts and load the model. Click to play. That's it.SD1, SDXL, SD3, FLUX, AURAFLOW, HUNYUANDIT and ~eh Stable Cascade. You need to update the selector node https://github.com/exdysa/comfyui-selector (they are in the ComfyOrg registry, not on CivitAI). Schnell will not be detected from Dev.The modular turquoise group can be dragged, which is convenient for re-routing and diagnosis. The sampler input is color-coded. Schedulers, solvers and orientation can shuffle model-compatible settings. OLLAMA LLM Prompt. The output port is ready for upgrading and detailing.Note: This project has been abandoned.Someone told me that it is impossible to automate ComfyUI like this. No, but ComfyUI is not for complex applications. More than 300 nodes filled the screen. The system can't keep up. Automatic switching is extremely difficult to test. This is unsustainable, but it may provide information, motivation and education. Explore the limitations of ComfyUI.There is no support. I don't know if it can still be used. I don't care. I'm using diffusers now. Please look forward to it.˶Σ⤬⫒ⵖsᐼ˶ ⠑⠭⠙⠽⠎⠁

⭐ 0.0 ⬇ 97