Skip to content
WorkflowListedExternal
Open source

Wan2.2 Image Refiner — v1.0

With this model you can create highly refined images using Wan2.2 it is a collection of multiple workflows, in addition of my own work on it, I have tried to make it easy for anyone with basic knowledge with Comfy Ui...

Sourcecivitai.com/models/2197051
TaskMultiCapabilitiesImage edit · Image to image · UpscalingFamilyWanVersionRelease 2473810 — Wan2.2_Refiner.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
Wan2.2_Refiner.json
Source
Civitai
Updated
Oct 18, 2026

Source description

With this model you can create highly refined images using Wan2.2 it is a collection of multiple workflows, in addition of my own work on it, I have tried to make it easy for anyone with basic knowledge with Comfy Ui to be able to modify add and remove any section of the workflow and replace it with quantized alternative to fit your Hardware.

The different detailers require separate models that should go in your ComfyUI /models/ultralytics/bbox folder. You can find these files here and here .

Inspired by GBRX

What you need

Model files
6.6 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

12

Node packs

3

  • comfyui-impact-pack

    Found

    Node pack · Registry

  • comfyui-impact-subpack

    Found

    Node pack · Registry

  • rgthree-comfy

    Found

    Node pack · Registry

AI-generated commentary

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

Purpose

  • Wan2.2 Image Refiner is a ComfyUI workflow for creating highly refined images with Wan2.2. It uses the Wan Video 2.2 T2V-A14B base model and separate detailer models, with highly refined images as its stated output.

Flow

  • It is a collection of multiple workflows for Wan2.2.

  • With basic ComfyUI knowledge, you can modify, add, or remove workflow sections.

Inputs and outputs

  • Different detailers require separate model files.

Setup

  • Place the separate detailer models in ComfyUI /models/ultralytics/bbox.

Dependencies

  • Listed model files include: wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors; wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors; umt5_xxl_fp8_e4m3fn_scaled.safetensors; wan_2.1_vae.safetensors; and gonzalomoXLFluxPony_v60PhotoXLDMD.safetensors.

  • Other listed model files include: xl-innie-biglove.safetensors; bbox/female_breast-v4.2.pt; bbox/face_yolov8m.pt; bbox/nipples_yolov8s.pt; bbox/Eyeful_v2-Paired.pt; bbox/vagina-v3.2.pt; and sam_vit_b_01ec64.pth.

  • Listed node packs include: rgthree-comfy, comfyui-impact-pack, and comfyui-impact-subpack.

Configuration

  • Workflow sections can be replaced with quantized alternatives to fit your hardware.

Cautions

  • No license is specified for this workflow.

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2473810
civitai.com/models/2197051

Verified Oct 18

Source excerpts

3 excerpts
NoteOct 18civitai.com/models/2197051

Source context: 438 downloads · Type Workflows · Base model Wan Video 2.2 T2V-A14B

NoteAug 9civitai.com/models/2197051

Source context: 391 downloads · Type Workflows · Base model Wan Video 2.2 T2V-A14B

NoteJul 19civitai.com/models/2197051

Source context: 375 downloads · Type Workflows · Base model Wan Video 2.2 T2V-A14B