Visit ComfyUI Online for ready-to-use ComfyUI environment
Generate detailed image prompts with reference text for AI artists using Stable Diffusion to enhance creativity and stylistic consistency.
The LayerUtility: UserPromptGeneratorTxt2ImgPromptWithReference
node is designed to assist AI artists in crafting detailed and visually inspired prompts for generating images using Stable Diffusion. This node enhances the creative process by allowing you to incorporate a reference text that describes a visual style, which can be used to influence the final image output. By combining a basic description of the desired image content with a reference text, this node helps you create more nuanced and stylistically consistent prompts. The node ensures that the generated prompt is polished and embellished, adhering to a specified word limit to maintain clarity and focus. This functionality is particularly beneficial for artists looking to achieve a specific aesthetic or thematic consistency in their AI-generated artwork.
The template
parameter specifies the type of prompt you are creating. In this node, the available option is 'SD txt2img prompt'
, which indicates that the prompt is intended for generating images using Stable Diffusion. This parameter helps the node understand the context and format of the prompt it needs to generate.
The reference_text
parameter is a string input that provides a description of the visual style or elements you wish to incorporate into the generated image. This text serves as a guide for the node to align the prompt with the desired aesthetic. It is a required field and must be provided to ensure the prompt reflects the intended style.
The describe
parameter allows you to input a basic description of the main subject or content you want in the image. This string can be multiline and serves as the foundational element of the prompt. The default value is "1 girl"
, but you can customize it to fit your specific needs. This description is then polished and embellished by the node to create a more detailed prompt.
The limit_words
parameter sets the word limit for the generated prompt. It is an integer value with a default of 200, a minimum of 2, and a maximum of 999. This parameter ensures that the prompt is concise yet detailed enough to convey the necessary information for image generation. The node adjusts the word count to be between 70% and 110% of the specified limit to maintain balance.
The user_prompt
output parameter is a string that contains the final generated prompt. This prompt is crafted based on the input description and reference text, polished to fit within the specified word limit. It is the key output of the node, ready to be used in Stable Diffusion for generating images. The prompt is designed to be clear and focused, without any extraneous information, ensuring it is directly applicable for image creation.
reference_text
is descriptive and aligns with the visual style you wish to achieve, as it significantly influences the final prompt.describe
inputs to see how variations in the main subject description affect the generated prompt and resulting images.reference_text
parameter is required and must be provided for the node to function correctly.reference_text
parameter before executing the node.limit_words
parameter is set too low for the complexity of the description.limit_words
parameter to accommodate more detailed descriptions, ensuring the prompt remains within the desired length.RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Playground, enabling artists to harness the latest AI tools to create incredible art.