[Segment+Frequency] Sharp Without Distortion — v1.0
This workflow automatically enhances blurry images while preserving original details:
Runtime profile
- Access
- External workflow
- Status
- Listed
- Source
- Civitai
- Updated
- Oct 2, 2026
Source description
This workflow automatically enhances blurry images while preserving original details:
-
Detects specific areas using UltralyticsDetector
-
Applies frequency correction only to detected regions
-
Perfect for selective image enhancement without distortion
흐릿한 이미지를 자연스럽게 개선하는 워크플로우입니다:
-
UltralyticsDetector로 특정 영역을 자동 감지
-
감지된 부분에만 주파수 보정 적용
-
이미지 변형 없이 선택적으로 선명도를 높이는데 최적화
A1 [contact & follow & like & Buzz]
Mail : a01demort@gmail.com
CIVITAI : https://civitai.com/user/a01demort
Youtube : https://www.youtube.com/@A01demort
Instagram : https://www.instagram.com/a01demort/
Naver Cafe : https://cafe.naver.com/sdfkorea
sdhotline : https://sdhotline.com/
What you need
Hardware and download-size estimates are not available yet.
Requirements
Models
1- Not resolved
Object Detector · Hugging Face · segm/person_yolov8m-seg.pt
Node packs
13FrequencyCombination
FoundNode pack · Unknown
FrequencySeparation
PossibleNode pack · Unknown
- Found
Node pack · Unknown
Image Blending Mode
FoundNode pack · Unknown
Image Comparer (rgthree)
Not resolvedNode pack · Unknown
ImageCompositeMasked
PossibleNode pack · Unknown
ImpactSimpleDetectorSEGS
FoundNode pack · Unknown
Label (rgthree)
Not resolvedNode pack · Unknown
LoadImage
PossibleNode pack · Unknown
MaskPreview+
FoundNode pack · Unknown
SaveImage
PossibleNode pack · Unknown
SegsToCombinedMask
FoundNode pack · Unknown
UltralyticsDetectorProvider
FoundNode pack · Unknown
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
This workflow automatically enhances blurry images and is described as preserving their original details.
Flow
It detects specific areas with UltralyticsDetector, then applies frequency correction only to those regions.
Inputs and outputs
The described input is a blurry image; the intended output is an enhanced image, with original details described as preserved.
Dependencies
The workflow requires these node packs: ComfyUI_essentials, was-node-suite-comfyui, ComfyUI-Impact-Pack, ComfyUI-Impact-Subpack, ComfyUI-KJNodes, and comfyUI_FrequencySeparation_RGB-HSV.
Check whether the detector model file segm/person_yolov8m-seg.pt is available in your setup.
Suggestion · not verified
Configuration
The listed base model is SDXL 1.0.
Cautions
The listing does not specify a license; check its usage terms before using the workflow.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceSource excerpts
1 excerpt
Source excerpts
1 excerptSource context: 411 downloads · Type Workflows · Base model SDXL 1.0
