Visit ComfyUI Online for ready-to-use ComfyUI environment
Automate professional ID photo creation with size and background adjustments for official documents.
The IDPhotos node is designed to facilitate the creation of professional ID photos by processing input images to meet specific size and background requirements. This node is particularly useful for generating standardized photos for various official documents, such as passports, visas, and identification cards. It offers capabilities to align and crop faces, adjust image dimensions, and remove or change backgrounds, ensuring that the final output adheres to the required specifications. By automating these tasks, the IDPhotos node simplifies the process of producing high-quality ID photos, saving time and effort for users who need to generate multiple images for different purposes.
This parameter accepts the input image that you want to process into an ID photo. The image should be in a format that the node can handle, such as JPEG or PNG. The quality and resolution of the input image will affect the final output, so it's recommended to use a high-resolution image for best results.
This parameter specifies the model used for removing the background from the image. You can choose from a list of available models, with "RMBG-2.0" being the default option. The choice of model can impact the accuracy and quality of the background removal process.
This boolean parameter determines whether the model should be unloaded from memory after processing. The default value is True, which helps free up system resources. If you plan to process multiple images in succession, you might set this to False to avoid reloading the model each time.
This parameter allows you to select the background color for the final ID photo. Options include "Alpha" (transparent), "black", "white", "gray", "green", "pure_blue", "pure_red", "cornflower_blue", "crimson_red", "dark_slate_blue", and "snow_white". The default is "Alpha", which means no background color is applied.
This parameter defines the size of the ID photo. You can choose from a predefined list of sizes, such as "一寸,413,295" or "美国签证,600,600". The size affects the dimensions of the output image and should be selected based on the specific requirements of the document for which the ID photo is intended.
This parameter controls the amount of padding around the face in the final image. It is a float value with a default of 1.0, a minimum of 0.0, and a maximum of 5.0. Adjusting this value can help ensure that the face is properly centered and sized within the ID photo.
This parameter adjusts the vertical position of the face within the image. It is a float value with a default of 0.0, a minimum of -0.5, and a maximum of 0.5. This can be useful for fine-tuning the alignment of the face in the final output.
This parameter allows you to adjust the angle of the face in the image. It is a float value with a default of 1.0, a minimum of -10.0, and a maximum of 10.0. This can help correct any tilt in the original image to ensure the face is level in the ID photo.
This parameter is not explicitly described in the context, but it likely refers to a setting related to the image processing, such as a quality or compression level. Adjusting this parameter can affect the final output's quality and file size.
This parameter sets the dots per inch (DPI) for the output image, with a default value of 300. DPI is a measure of image resolution, and a higher DPI can result in a clearer and more detailed photo, which is important for printing purposes.
This output is the processed ID photo with standard resolution and background adjustments applied. It is suitable for digital use or printing at standard sizes.
This output is a high-definition version of the ID photo, offering enhanced resolution and detail. It is ideal for situations where a higher quality image is required.
This output consists of the ID photo formatted for printing, ensuring that it meets the specified size and resolution requirements for physical copies.
face_reduction, face_up_down, and angle_offset parameters to fine-tune the alignment and positioning of the face in the image.unload_model to False if you are processing multiple images in a batch to save time on model loading.RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.