Visit ComfyUI Online for ready-to-use ComfyUI environment
Overlay text on images with control over font, size, color, and position for AI artists and creators.
The ImageAddText
node is designed to overlay text onto an image, providing a versatile tool for AI artists to add captions, annotations, or any textual content to their visual creations. This node allows you to specify various parameters such as the text content, font type, font size, position, and color, giving you full control over the appearance and placement of the text. Whether you are creating memes, adding watermarks, or simply enhancing your artwork with descriptive text, this node simplifies the process by handling the complexities of text rendering and image manipulation. The node can work with an existing image or create a new one if no image is provided, ensuring flexibility in its application.
This parameter specifies the text content that you want to overlay on the image. It can be any string of characters, including letters, numbers, and symbols. The text will be rendered exactly as provided.
Defines the width of the image in pixels. If an image is provided, this parameter will be automatically set to the width of the provided image. Otherwise, it determines the width of the new image to be created.
Defines the height of the image in pixels. Similar to the width parameter, if an image is provided, this parameter will be automatically set to the height of the provided image. Otherwise, it determines the height of the new image to be created.
Specifies the font type to be used for rendering the text. This should be the name of a font file available in the system or a custom font path. The choice of font can significantly impact the visual style of the text.
Determines the size of the font in points. Larger values will result in bigger text, while smaller values will produce smaller text. This parameter allows you to control the prominence of the text on the image.
Sets the horizontal position (in pixels) where the text will start on the image. This allows you to precisely place the text along the x-axis.
Sets the vertical position (in pixels) where the text will start on the image. This allows you to precisely place the text along the y-axis.
Defines the color of the text. This should be provided in a format that the system recognizes, such as an RGB tuple. The color choice can affect the readability and aesthetic of the text.
A boolean parameter that, when set to True
, inverts the mask of the text. This can be useful for certain visual effects or when integrating the text with other image processing nodes.
An optional parameter that allows you to provide an existing image onto which the text will be added. If no image is provided, a new image will be created based on the specified width and height.
The resulting image with the overlaid text. This output is a tensor representing the image data, which can be further processed or saved as needed.
A mask tensor that represents the area where the text has been added. This can be useful for further image processing tasks, such as blending or masking operations.
The original text string that was added to the image. This is returned for reference or further use in subsequent nodes.
© Copyright 2024 RunComfy. All Rights Reserved.