ComfyUI Node: SuperPrompter

SuperPrompter:

The SuperPrompterNode is designed to enhance and expand your text prompts by leveraging advanced natural language processing models. This node is particularly useful for AI artists who want to add more detail and depth to their prompts, thereby generating richer and more nuanced outputs. By utilizing the T5 model for conditional generation, the SuperPrompterNode can take a simple prompt and elaborate on it, making it more descriptive and engaging. This node automatically handles model loading and ensures that the necessary components are in place, providing a seamless experience for users. Its primary goal is to simplify the process of generating detailed text prompts, allowing you to focus on your creative work without worrying about the technical intricacies.

SuperPrompter Input Parameters:

prompt

The prompt parameter is a string input where you enter the initial text prompt that you want to expand. This is the starting point for the SuperPrompterNode to generate a more detailed and elaborate version of your input. The default value is "Enter prompt here".

max_new_tokens

The max_new_tokens parameter specifies the maximum number of new tokens (words or subwords) that the model can generate. This controls the length of the expanded prompt. The minimum value is 1, the maximum value is 2048, and the default value is 512. Adjusting this parameter allows you to control the verbosity of the generated text.

repetition_penalty

The repetition_penalty parameter is a float that helps to reduce the likelihood of repetitive phrases in the generated text. A higher value increases the penalty for repetition, making the output more diverse. The minimum value is 0.0, the maximum value is 2.0, and the default value is 1.2. This parameter is useful for ensuring that the generated text is varied and interesting.

remove_incomplete_sentences

The remove_incomplete_sentences parameter is a boolean that determines whether to remove incomplete sentences from the generated text. If set to True, any incomplete sentences at the end of the generated text will be removed, resulting in a cleaner and more coherent output. The default value is True. This is particularly useful for maintaining the quality and readability of the generated text.

SuperPrompter Output Parameters:

generated_text

The generated_text parameter is a string output that contains the expanded and detailed version of your initial prompt. This text is generated based on the input parameters and the model's capabilities. The output is designed to be more descriptive and engaging, providing you with a richer prompt to work with in your creative projects.

SuperPrompter Usage Tips:

• To generate more detailed and elaborate prompts, increase the max_new_tokens parameter, but be mindful of the maximum limit to avoid overly long outputs.
• Use the repetition_penalty parameter to fine-tune the diversity of the generated text. A higher value can help reduce repetitive phrases and make the output more interesting.
• If you notice incomplete sentences in the generated text, ensure that the remove_incomplete_sentences parameter is set to True for cleaner and more coherent results.
• Experiment with different initial prompts to see how the SuperPrompterNode can enhance and expand them in various ways.

SuperPrompter Common Errors and Solutions:

Model files not found. Skipping download.

• Explanation: This message indicates that the model files are already present in the specified directory, so the download step is skipped.
• Solution: No action is needed. This is an informational message confirming that the required model files are available.

Cannot execute because a node is missing the class_type property.

• Explanation: This error occurs when a node in the prompt does not have the class_type property, which is required for execution.
• Solution: Ensure that all nodes in the prompt have the class_type property correctly set. Check the prompt configuration for any missing or incorrect properties.

Cannot execute because node <class_type> does not exist.

• Explanation: This error occurs when the specified node class type does not exist in the NODE_CLASS_MAPPINGS.
• Solution: Verify that the node class type is correctly defined and mapped in the NODE_CLASS_MAPPINGS. Ensure that the node class is properly imported and registered.

Prompt has no outputs

• Explanation: This error occurs when the prompt does not have any output nodes defined.
• Solution: Ensure that at least one node in the prompt is designated as an output node. Check the prompt configuration to confirm that output nodes are correctly specified.

Failed to validate prompt for output <output_id>

• Explanation: This error occurs when the prompt validation fails for a specific output.
• Solution: Review the validation errors and ensure that all required properties and configurations are correctly set for the nodes in the prompt. Address any issues highlighted in the validation errors.