Skip to main content
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

ParameterDescriptionData TypeRequiredRange
clipThe CLIP model used for text encodingCLIPYes-
clip_lText input for the local CLIP model. Supports multiline text and dynamic prompts.STRINGYes-
clip_gText input for the global CLIP model. Supports multiline text and dynamic prompts.STRINGYes-
t5xxlText input for the T5-XXL model. Supports multiline text and dynamic prompts.STRINGYes-
empty_paddingControls 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”).COMBOYes"none"
"empty_prompt"
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 NameDescriptionData Type
CONDITIONINGThe encoded text conditioning data ready for use in SD3 generation pipelinesCONDITIONING
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256): 2086e7c0fe910a94c04173ecfe35a2e04ecb306526b9089c527bb874e97b20c4