Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The TextGenerateLTX2Prompt node is a specialized version of a text generation node. It takes a user’s text prompt and automatically formats it with specific system instructions before sending it to a language model for enhancement or completion. The node can operate in two modes: text-only or with an image reference, using different system prompts for each case.

Inputs

ParameterData TypeRequiredRangeDescription
clipCLIPYesThe CLIP model used for text encoding.
promptSTRINGYesThe raw text input from the user that will be enhanced or completed.
max_lengthINTYesThe maximum number of tokens the language model is allowed to generate.
sampling_modeCOMBOYes"greedy"
"top_k"
"top_p"
"temperature"
The sampling strategy used to select the next token during text generation.
imageIMAGENoAn optional input image. When provided, the node uses a different system prompt that includes a placeholder for image context.
Note: The behavior of the node changes based on the presence of the image input. If an image is provided, the generated prompt will be formatted for an image-to-video task. If no image is provided, the formatting will be for a text-to-video task.

Outputs

Output NameData TypeDescription
outputSTRINGThe enhanced or completed text string generated by the language model.