ComfyUI Node: Prompt Dupe Remover V2

Prompt Dupe Remover V2:

PromptDupeRemoverV2 is a sophisticated node designed to enhance text processing by eliminating duplicate words from a given input. This node is particularly beneficial for AI artists and content creators who need to refine and streamline their text prompts, ensuring clarity and uniqueness. By leveraging advanced text parsing techniques, PromptDupeRemoverV2 efficiently identifies and removes repeated words, while offering options to preserve the original case of the text and to maintain specific terms through a customizable whitelist. This functionality is crucial for maintaining the integrity of creative prompts, allowing users to focus on the originality and impact of their content without the distraction of redundancy.

Prompt Dupe Remover V2 Input Parameters:

text

The text parameter is the primary input for the node, where you provide the string of text from which duplicates need to be removed. This parameter supports multiline input, allowing you to process extensive text blocks. The effectiveness of the node's duplicate removal process hinges on the content provided in this parameter, as it directly influences the output's clarity and conciseness.

preserve_case

The preserve_case parameter is a boolean option that determines whether the original case of the text should be maintained during processing. By default, this is set to True, meaning the node will retain the original capitalization of words. This is particularly useful when the case of words carries significance, such as in proper nouns or stylistic choices. If set to False, the node will convert all words to lowercase, which can be useful for uniformity in certain contexts.

whitelist

The whitelist parameter allows you to specify a list of terms that should be exempt from duplicate removal. This is a string input where terms are separated by commas, and multi-word terms should be enclosed in quotes. This feature is essential for preserving specific words or phrases that are intentionally repeated for emphasis or stylistic reasons. By default, this parameter is an empty string, meaning no terms are whitelisted unless specified.

Prompt Dupe Remover V2 Output Parameters:

STRING

The output of the node is a single STRING type, which is the cleaned version of the input text with duplicates removed. This output retains the structure and flow of the original text while ensuring that each word appears only once, unless specified otherwise by the whitelist. The cleaned text is crucial for creating concise and impactful prompts, free from unnecessary repetition.

Prompt Dupe Remover V2 Usage Tips:

• Utilize the whitelist parameter to protect specific terms or phrases that are crucial to your prompt's meaning or style, ensuring they are not removed during processing.
• Consider setting preserve_case to False if you require a uniform text case, which can be beneficial for certain types of text analysis or when case sensitivity is not a concern.
• Regularly review and update your whitelist to adapt to changing creative needs or to incorporate new terms that should be preserved in your prompts.

Prompt Dupe Remover V2 Common Errors and Solutions:

Invalid Whitelist Format

• Explanation: This error occurs when the whitelist is not formatted correctly, such as missing commas between terms or not using quotes for multi-word terms.
• Solution: Ensure that each term in the whitelist is separated by a comma and that multi-word terms are enclosed in quotes. For example, use "term1", "multi word term2".

Text Input Too Large

• Explanation: If the input text is excessively large, it may cause performance issues or exceed processing limits.
• Solution: Break down large text inputs into smaller segments and process them individually to ensure efficient handling and avoid overloading the node.