Nodes/ComfyUI/CLIP Text Encode (Lumina 2)
ComfyUI Node Runs on cloud

CLIP Text Encode (Lumina 2)

Encodes a system prompt and a user prompt using a CLIP model into an embedding that can be used to guide the diffusion model towards generating specific images.

By Comfy-Org·Created 4 years ago·Updated 16 days ago· 121,575
CLIP Text Encode (Lumina 2)
  • clip
  • CONDITIONING
system_prompt
user_prompt
Categorymodel/conditioning/lumina

Inputs (3)

NameTypeDefaultDescription
system_promptCOMBOLumina2 provide two types of system prompts:Superior: You are an assistant designed to generate superior images with the superior degree of image-text alignment based on textual prompts or user prompts. Alignment: You are an assistant designed to generate high-quality images with the highest degree of image-text alignment based on textual prompts.
user_promptSTRINGThe text to be encoded.
clipCLIPThe CLIP model used for encoding the text.

Outputs (1)

NameTypeDescription
CONDITIONINGCONDITIONINGA conditioning containing the embedded text used to guide the diffusion model.