Two workflows for refining auto-detected segments in ComfyUI using the mask editor node.
Perfil de ejecución
Descripción de la fuente
Two workflows for refining auto-detected segments in ComfyUI using the mask editor node.
One workflow helps subtract unwanted areas,
while the other allows adding missing areas to your manual masks for more precise segmentation results.
ComfyUI 수동 마스크 보정 워크플로우
ComfyUI에서 자동 검출된 세그먼트를 마스크 에디터 노드로 보정하는 두 가지 워크플로우입니다.
하나는 원하지 않는 영역을 제거하고, 다른 하나는 누락된 영역을 수동으로 추가하여 더 정확한 세그멘테이션을 만들 수 있습니다.
A1 [contact & follow & like & Buzz]
Mail :
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
This ComfyUI workflow set is for refining auto-detected segments and manual masks with a mask editor: it removes unwanted areas or adds missing areas, producing more precise segmentation results.
Use the subtract workflow to remove unwanted areas, or the add workflow to add missing areas to a manual mask.
Sugerencia · sin verificar
It works with auto-detected segments or manual masks and produces a more precise segmentation result.
Find it at https://civitai.com/models/1139526; the publisher is A01demort.
The workflow requires these ComfyUI-Impact-Pack nodes: AddMask, MaskToSEGS, SegmDetectorSEGS, SegsToCombinedMask, and SubtractMaskForEach.
It also requires UltralyticsDetectorProvider from ComfyUI-Impact-Subpack and MaskPreview+ from ComfyUI_essentials.
Check that Label (rgthree), LoadImage, and segm/person_yolov8m-seg.pt are available in your ComfyUI setup before use.
Sugerencia · sin verificar
The title labels the two workflows Mask+Mask and Mask-Mask.
The listing names Flux.1 D as its base model.
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
1 extractoSource context: 484 downloads · Type Workflows · Base model Flux.1 D
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/
Requisito de VRAM estimado
Estimación no disponible
Los tamaños de los modelos aún no están lo bastante completos para calcular este requisito.
Requisitos
10 requisitosObject Detector · Hugging Face · segm/person_yolov8m-seg.pt
Paquete de nodos · Unknown
Label (rgthree)
No resueltoPaquete de nodos · Unknown
LoadImage
PosiblePaquete de nodos · Unknown
Paquete de nodos · Unknown
Paquete de nodos · Unknown
Paquete de nodos · Unknown
Paquete de nodos · Unknown
Paquete de nodos · Unknown
Paquete de nodos · Unknown