Reference Image Selector (参考图选择器):
The ReferenceImageSelector node is designed to streamline the process of selecting and organizing reference images based on their angles. This node is particularly beneficial for AI artists who work with multiple reference images from different perspectives and need to filter and sort them efficiently. By utilizing an angle map, the node can determine the optimal arrangement of images, ensuring that the most relevant images are prioritized according to specified angles. This functionality is crucial for tasks that require precise image alignment or comparison, such as pose estimation or 3D modeling. The node's ability to handle both filtering and sorting operations makes it a versatile tool in any AI artist's workflow, enhancing productivity and ensuring that the best reference images are always at the forefront.
Reference Image Selector (参考图选择器) Input Parameters:
reference_images
This parameter accepts a batch of reference images that you wish to filter and sort based on their angles. The images should be provided in a format that allows the node to process them effectively. The primary function of this parameter is to serve as the dataset from which the node will select the most relevant images according to the specified angle map. There are no specific minimum or maximum values for this parameter, but it is essential to ensure that the images are of sufficient quality and relevance to your task.
angle_map
The angle_map parameter is a JSON string that specifies the angles or ranges associated with each reference image. This map is crucial for the node's filtering and sorting operations, as it determines how each image is evaluated and prioritized. The default value is an empty string, and it is important to ensure that the JSON format is correct and that the angles correspond accurately to the images provided. This parameter allows for precise control over the selection process, enabling you to tailor the output to your specific needs.
yaw_angles
This optional parameter is an array of float values representing the target yaw angles for each frame. The yaw_angles parameter is used to filter the reference images to find the best match based on the specified angles. The values can range from -180.0 to 180.0, with a default of 0.0. This parameter is particularly useful when you need to align images with a specific orientation, ensuring that the selected images match the desired perspective.
select_references
The select_references parameter is a boolean option that determines whether the node should filter and sort the reference images or only sort them. When set to True, the node will perform both filtering and sorting based on the angles, while setting it to False will result in sorting only, without filtering. The default value is True, and this parameter allows you to control the level of processing applied to the reference images, depending on your requirements.
background_images
This optional parameter allows you to provide a batch of background images that will be appended after the selected reference images. The inclusion of background images can enhance the visual context of the output, making it more comprehensive. There are no specific constraints on this parameter, but it is important to ensure that the background images are relevant and complement the reference images effectively.
Reference Image Selector (参考图选择器) Output Parameters:
selected_images
This output consists of the reference images that have been filtered and sorted according to the specified angles. The selected_images are arranged in a manner that prioritizes the most relevant images, ensuring that they are ready for further processing or analysis. This output is crucial for tasks that require precise image alignment or comparison.
raw_reference_images
The raw_reference_images output provides the original reference images without any sorting or filtering applied. This output is useful for maintaining a complete set of images for reference or for use in other processes that may require the original order and content.
info
The info output contains debugging and status information related to the node's operations. This information can be invaluable for troubleshooting and understanding the node's behavior, providing insights into the filtering and sorting process and any issues that may have arisen.
reference_angle_map
This output provides the validated angle map in JSON format, which can be used for further processing or as a reference for other nodes or operations. The reference_angle_map ensures that the angles used in the selection process are accurately represented and can be reused or modified as needed.
Reference Image Selector (参考图选择器) Usage Tips:
- Ensure that your angle_map JSON is correctly formatted and accurately represents the angles associated with each reference image to achieve optimal filtering and sorting results.
- Utilize the select_references parameter to control the level of processing applied to your images, depending on whether you need both filtering and sorting or just sorting.
- Consider providing background_images to enhance the visual context of your output, especially if the reference images are intended for presentation or further analysis.
Reference Image Selector (参考图选择器) Common Errors and Solutions:
"参考图为空"
- Explanation: This error occurs when the reference_images parameter is empty or not provided.
- Solution: Ensure that you have supplied a valid batch of reference images for processing.
"yaw_angles 未接入, 直接输出全部参考图"
- Explanation: This message indicates that the yaw_angles parameter is not connected, resulting in the output of all reference images without filtering.
- Solution: Connect the yaw_angles parameter if you wish to filter images based on specific yaw angles.
"angle_map 无效, 直接输出全部参考图"
- Explanation: This error suggests that the angle_map is invalid or not correctly formatted, leading to the output of all reference images without sorting.
- Solution: Verify that your angle_map JSON is correctly formatted and corresponds to the reference images provided.