<h1 id="introducing-the-one-image-workflow:-a-forge-style-static-design-for-wan-2.12.2-z-image-qwen-image-flux2-and-others">Introducing the One-Image Workflow: A Forge-Style Static Design for Wan 2.1/2.2, Z-Image, Qwen-Image, Flux2 &amp; Others</h1>Author: Iory98Tested On: Windows 11, ComfyUI Version: v0.4.0 | Frontend Version: v1.33.13 A full Guide is included inside the Workflow.<h2 id="introduction-and-motivation:-no-more-noodle-soup!">Introduction &amp; Motivation: No More Noodle Soup!</h2>ComfyUI is a powerful platform for AI generation, but its graph-based nature can be intimidating. If you are coming from Forge WebUI or A1111, the transition to managing "noodle soup" workflows often feels like a chore. I always believed a platform should let you focus on creating images, not engineering graphs.I created the One-Image Workflow to solve this. My goal was to build a workflow that functions like a User Interface. By leveraging the latest ComfyUI Subgraph features, I have organized the chaos into a clean, static workspace.Why "One-Image"?This workflow is designed for quality over quantity. Instead of blindly generating 50 images, it provides a structured 3-Stage Pipeline to help you craft the perfect single image: generate a composition, refine it with a model-based Hi-Res Fix, and finally upscale it to 4K using modular tiling.While optimized for Wan 2.1 and Wan 2.2 (Text-to-Image), this workflow is versatile enough to support Qwen-Image, Z-Image, and any model requiring a single text encoder.Key Philosophy: The 3-Stage PipelineThis workflow is not just about generating an image; it is about perfecting it. It follows a modular logic to save you time and VRAM:·         Stage 1 - Composition (Low Res): Generate batches of images at lower resolutions (e.g., 1088x1088). This is fast and allows you to cherry-pick the best composition.·         Stage 2 - Hi-Res Fix: Take your favorite image and run it through the Hi-Res Fix module to inject details and refine the texture.·         Stage 3 - Modular Upscale: Finally, push the resolution to 2K or 4K using the Ultimate SD Upscale module.By separating these stages, you avoid waiting minutes for a 4K generation only to realize the hands are messed up. <h2 id="the-&quot;stacked&quot;-interface:-how-to-navigate">The "Stacked" Interface: How to Navigate</h2>The most unique feature of this workflow is the Stacked Preview System. To save screen space, I have stacked three different Image Comparer nodes on top of each other. You do not need to move them; you simply Collapse the top one to reveal the one behind it.·         Layer 1 (Top) - Current vs Previous – Compares your latest generation with the one before it. Action: Click the minimize icon on the node header to hide this and reveal Layer 2.·         Layer 2 (Middle): Hi-Res Fix vs Original – Compares the stage 2 refinement with the base image. Action: Minimize this to reveal Layer 3.·         Layer 3 (Bottom): Upscaled vs Original – Compares the final ultra-res output with the input. <h2 id="the-control-panels-(subgraphs)">The Control Panels (Subgraphs)</h2>The workflow is divided into 7 color-coded Subgraphs. Think of these as "Tabs" in a web browser. Expand them to change settings, then collapse them to keep your workspace clean.1. Wan_Main_Settings (The Dashboard)·         Status: Always Expanded·         Function: This is your home screen. It contains the parameters you change 90% of the time:o   Prompts: Positive text input.o   Generation Data: Seed, Sampler, Scheduler, CFG, and Steps.o   Image Size: Set your base resolution here.o   Toggle Switches: Quickly enable/disable the Refiner, Hi-Res Fix, or Upscaling stages without disconnecting wires.2. Wan_Model_Loaders (Changes Start Here)·         Function: Handles loading your checkpoints.·         Dual-Stage Loading: You can load a Main Model (High Noise) for structure and a Refiner Model (Low Noise) for details.·         Format Freedom: Supports mixing GGUF and Safetensors. You can even load the GGUF version as Main and Safetensors as Refiner to test quantization differences.3. Wan_Model_Parameters (Advanced Tuning)·         Function: Technical settings for the models.·         Features:o   Model Format Selection: Select model types (GGUF vs. Safetensors).o   MagCache Optimization: Settings to manage VRAM usage and speed.o   Default LoRA Stack: A bundle of 3 slots for "Always On" LoRAs (like Lightning or Turbo LoRAs).4. Wan_Unified_LoRA_Stack·         Function: A centralized LoRA loader.·         Logic: Instead of managing separate LoRAs for Main and Refiner models, this stack applies your style LoRAs to both. It supports up to 6 LoRAs. Of course, this Stack can work in tandem with the Default (internal) LoRAs discussed above.·         Note: If you need specific LoRAs for only one model, use the external Power LoRA Loaders included in the workflow.5. Wan_NAG_Settings (Negative Prompting)·         Function: Manages what you don't want in the image.·         Feature: Includes NAG (Normalized Attention Guidance) settings, which often provides better adherence to negative prompts than standard methods. Also handles image filename prefixes and saving paths.6. Wan_HiResFix_Settings (Stage 2)·         Function: Refines the image generated in Stage 1.·         Recommendation: Use this to scale up your chosen "Draft" image. It uses a re-noising technique to add details that didn't exist in the lower resolution version.7. Wan_Upscaler_Settings (Stage 3)Function: The final polish; upscale the image beyond the model’s resolution capabilities.Module: Uses Ultimate SD Upscale.Logic: This allows for Tiled Upscaling, essential for going to 4K resolutions without running out of VRAM. You can feed either the original image or the Hi-Res Fixed image into this module. <h2 id="requirements-and-installation">Requirements &amp; Installation</h2>To use this workflow, you must have the ComfyUI Manager installed. When you load the workflow, click "Install Missing Custom Nodes".Key Custom Nodes Used:·         rgthree-comfy: For the Mute switches and the Image Comparer nodes.·         ComfyUI Impact Pack: For advanced workflow logic.·         ComfyUI-Easy-Use: For streamlined parameter handling.·         ComfyUI-KJNodes: For UI enhancements.·         UltimateSDUpscale: For the Stage 3 upscaling.·         ComfyUI-GGUF: Required if using GGUF quantized models.·         Was Node Suite: For various I/O tasks. <h2 id="quick-start-guide">Quick Start Guide</h2>1.      Load Models: Open the Model_Loaders subgraph and select your Wan 2.1 (or other) checkpoints.2.      Set Resolution: In Main_Settings, set a fast preview resolution (e.g., 832x1216 or 1024x1024).3.      Prompt: Enter your text in Main_Settings or in the connected Positive Prompt Field.4.      Generate: Press Queue Prompt.5.      Review: Look at the top Current vs Previous preview.6.      Refine (Optional): If you like the seed, turn on "Enable Hi-Res Fix" in Main_Settings and generate again to polish the details. collapse the top preview to see the result.

The One-Image Workflow: A Forge-Style Static Design for Wan Image, Z-Image, Qwen-Image, Flux2 & Others

While optimized for Wan 2.1 and Wan 2.2 (Text-to-Image), this workflow is versatile enough to support Qwen-Image, Z-Image, Flux2, and any model requiring a single text encoder.For Flux2 generation, for some reasons, Flux2 ignores set resolution and always outputs at  2560 x1440. I'll to investigate this issue and solve it for v2.

Files with SHA256: 58a9c2d8962cb4466cbd2e0af2e0bc1a2ba4c34182c7c11df6850a51e81bc0b3