CLIPTextEncodeKandinsky5 - ComfyUI Built-in Node Documentation - ComfyUI

The CLIP Text Encode (Kandinsky 5) node prepares text prompts for use with the Kandinsky 5 model. It takes two separate text inputs, tokenizes them using a provided CLIP model, and combines them into a single conditioning output. This output is used to guide the image generation process.

Inputs

Parameter	Description	Data Type	Required	Range
`clip`	The CLIP model used to tokenize and encode the text prompts.	CLIP	Yes
`clip_l`	The primary text prompt. This input supports multiline text and dynamic prompts.	STRING	Yes
`qwen25_7b`	The secondary text prompt. This input supports multiline text and dynamic prompts.	STRING	Yes

Outputs

Output Name	Description	Data Type
`CONDITIONING`	The combined conditioning data generated from both text prompts, ready to be fed into a Kandinsky 5 model 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

Source fingerprint (SHA-256): d988c47ab9a5f01549a3ae01b365d39e9fa2464bb69ea018ec20151939dcfc56