WorkflowListedExternal

Wan 2.2 Detailer

TaskMultiCapabilitiesImage to image · UpscalingFamilyWanEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Jul 18, 2026

Source description

This is a pretty simple workflow. Wan 2.2 T2V low noise model makes an awesome post detailer , since it's designed to detail the composition of the high noise model. Just drop your image into the load image node, script the composition of your image in the 'Prompt' text box (or get an LLM to do it for you) and watch Wan level up your image.

I've added a few options to help with detailing and scene/character consistency:

Wan NAG - direct Wan to the elements of the image you'd like it to focus on.

Reactor FaceSwap - for increased character consistency from original image.

I've also added directions in workflow for refining your output to increase either consistency or divergence from original image.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

Wan 2.2 Detailer is a workflow for adding detail to an input image with the Wan 2.2 T2V low-noise model. Enter an image and composition prompt to create a detailed image, with options for focus and character consistency.

Flow

Load your image into the LoadImage node and describe its composition in the Prompt text box; an LLM can help write the prompt.
Suggestion · not verified
The workflow includes directions for refining the result toward greater consistency or greater divergence from the original image.

Inputs and outputs

The main inputs are an image and a composition prompt, and the output is a more detailed version of the image.

Setup

The workflow is published by DirkDigitaller and uses Wan Video 2.2 T2V-A14B as its base model.

Dependencies

Model files named by the workflow are facetest-000007.safetensors, low_noise_model.safetensors, SmoothMixStyle_Low.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wan_masterpieces_v2.safetensors, and wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors.
Node packs named by the workflow are comfyui_layerstyle, comfyui-kjnodes, comfyui-rmbg, RES4LYF, rgthree-comfy, and was-ns.

Configuration

Use Wan NAG to direct focus toward the image elements you want emphasized.
Suggestion · not verified
Use Reactor FaceSwap when you want increased character consistency from the original image.
Suggestion · not verified

Cautions

Before using the workflow, verify that the named model files and node packs are available in your setup.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimaryVersion 2754214

civitai.com/models/2449454

Verified Jul 18

Source excerpts

1 excerpt

NoteJul 18civitai.com/models/2449454

Source context: 327 downloads · Type Workflows · Base model Wan Video 2.2 T2V-A14B