CLIPTextEncodeSD3 - ComfyUI Built-in Node Documentation

Complete documentation for the CLIPTextEncodeSD3 node in ComfyUI. Learn its inputs, outputs, parameters and usage.

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

The CLIPTextEncodeSD3 node processes text inputs for Stable Diffusion 3 models by encoding multiple text prompts using different CLIP models. It handles three separate text inputs (clip_g, clip_l, and t5xxl) and provides options for managing empty text padding. The node ensures proper token alignment between different text inputs and returns conditioning data suitable for SD3 generation pipelines.

Inputs

Parameter	Data Type	Required	Range	Description
clip	CLIP	Yes	-	The CLIP model used for text encoding
clip_l	STRING	Yes	-	Text input for the local CLIP model. Supports multiline text and dynamic prompts.
clip_g	STRING	Yes	-	Text input for the global CLIP model. Supports multiline text and dynamic prompts.
t5xxl	STRING	Yes	-	Text input for the T5-XXL model. Supports multiline text and dynamic prompts.
empty_padding	COMBO	Yes	"none" "empty_prompt"	Controls how empty text inputs are handled. When set to “none”, empty text inputs for clip_g, clip_l, or t5xxl will result in empty token lists instead of padding. This is an advanced parameter (default: “none”).

Parameter Constraints:

• When empty_padding is set to “none”, empty text inputs for clip_g, clip_l, or t5xxl will result in empty token lists instead of padding
• The node automatically balances token lengths between clip_l and clip_g inputs by padding the shorter one with empty tokens when lengths differ
• All text inputs support dynamic prompts and multiline text entry

Outputs

Output Name	Data Type	Description
CONDITIONING	CONDITIONING	The encoded text conditioning data ready for use in SD3 generation pipelines

---

Source fingerprint (SHA-256): 2086e7c0fe910a94c04173ecfe35a2e04ecb306526b9089c527bb874e97b20c4