Encodes a prompt with CLIP and outputs CONDITIONING. RAW: uses text1 as-is. EDIT: uses text_edit as-is. front: places text2 (or text_edit) before text1. back…

Drop a ComfyUI PNG/WebP/JSON onto the node to instantly extract and apply checkpoint, VAE, and prompts from embedded metadata. Supports ComfyUI, SD WebUI, SD Forge neo, Fooocus, SDXLPromptStyler, and Lora Loader (LoraManager). Includes LoRA from Metadata and CLIP Text Encode edit+ nodes.

Model and Prompt from Metadata

clip

text_edit

mode

text1

text2

Encodes a prompt with CLIP and outputs CONDITIONING. RAW: uses text1 as-is. EDIT: uses text_edit as-is. front: places text2 (or text_edit) before text1. back: places text2 (or text_edit) after text1.

Name	Type	Description
clip	CLIP	—
text_edit	STRING	—
mode	COMBO	4 options: RAW, EDIT, front, back
text1opt	STRING	—
text2opt	STRING	—

Name	Type	Description
conditioning	CONDITIONING	—
text	STRING	—

CLIP Text Encode edit+

Inputs (5)

Outputs (2)