Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
A ComfyUI node designed to clean VLM-generated captions for LoRA training. It automatically strips meta-descriptions (e.g., "The image is..."), removes subjective "vibe" sentences, and enforces custom trigger words...
Package profile
README
A ComfyUI node designed to clean VLM-generated captions for LoRA training. It automatically strips meta-descriptions (e.g., "The image is..."), removes subjective "vibe" sentences, and enforces custom trigger words for higher quality datasets.
Nodes in this pack
1 nodeSources
1 sourceSource excerpts
1 excerptSource context: Repo cristian1980/ComfyUI-Caption-Cleaner
CleanCaptionNode
A ComfyUI node that cleans captions for LoRA training by removing common "meta" descriptions (e.g., "The image is a digital illustration...").
LoRA/Text · 0 inputs · 3 parameters · 1 output
