Introducing the One-Image Workflow: A Forge-Style Static Design for Wan 2.1/2.2, Z-Image, Qwen-Image, Flux2 & Others

Author: Iory98

Tested On: Windows 11, ComfyUI Version: v0.4.0 | Frontend Version: v1.33.13

 A full Guide is included inside the Workflow.

Introduction & Motivation: No More Noodle Soup!

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 Pipeline

This 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.

The "Stacked" Interface: How to Navigate

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.

The Control Panels (Subgraphs)

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.

Requirements & Installation

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.

Quick Start Guide

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.