Documentation Index
Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
Use this file to discover all available pages before exploring further.
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe CLIP Text Encode for Lumina2 node encodes a system prompt and a user prompt using a CLIP model into an embedding that can guide the diffusion model to generate specific images. It combines a pre-defined system prompt with your custom text prompt and processes them through the CLIP model to create conditioning data for image generation.
Inputs
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
system_prompt | STRING | Yes | "superior""alignment" | Lumina2 provides two types of system prompts: “superior” generates images with superior image-text alignment; “alignment” generates high-quality images with the highest degree of image-text alignment. |
user_prompt | STRING | Yes | N/A | The text to be encoded. Supports multiline input and dynamic prompts. |
clip | CLIP | Yes | N/A | The CLIP model used for encoding the text. |
clip input is required and cannot be None. If the clip input is invalid, the node will raise an error indicating that the checkpoint may not contain a valid CLIP or text encoder model.
Outputs
| Output Name | Data Type | Description |
|---|---|---|
CONDITIONING | CONDITIONING | A conditioning containing the embedded text used to guide the diffusion model. |
Source fingerprint (SHA-256):
e9d5f685a666a4f0737739e56afa3eb854a4abcbd8a76480c7a050cd503b53b2