CLIPTextEncodeSDXL - ComfyUI Built-in Node Documentation

This node is designed to encode text input using a CLIP model specifically customized for the SDXL architecture. It uses a dual encoder system (CLIP-L and CLIP-G) to process text descriptions, resulting in more accurate image generation.

Inputs

Parameter	Description	Data Type
`clip`	CLIP model instance used for text encoding.	CLIP
`width`	Specifies the image width in pixels, default 1024.	INT
`height`	Specifies the image height in pixels, default 1024.	INT
`crop_w`	Width of the crop area in pixels, default 0.	INT
`crop_h`	Height of the crop area in pixels, default 0.	INT
`target_width`	Target width for the output image, default 1024.	INT
`target_height`	Target height for the output image, default 1024.	INT
`text_g`	Global text description for overall scene description.	STRING
`text_l`	Local text description for detail description.	STRING

Outputs

Parameter	Description	Data Type
`CONDITIONING`	Contains encoded text and conditional information needed for image generation.	CONDITIONING

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

CLIPTextEncodeSD3 - ComfyUI Built-in Node Documentation

CLIPTextEncodeSDXLRefiner - ComfyUI Built-in Node Documentation

​Inputs

​Outputs

Inputs

Outputs