ComfyUI  >  Nodes  >  ComfyUI Bringing Old Photos Back to Life >  Load Restore Old Photos Model

ComfyUI Node: Load Restore Old Photos Model

Class Name


cdb-boop (Account age: 1213 days)
ComfyUI Bringing Old Photos Back to Life
Latest Updated
Github Stars

How to Install ComfyUI Bringing Old Photos Back to Life

Install this extension via the ComfyUI Manager by searching for  ComfyUI Bringing Old Photos Back to Life
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI Bringing Old Photos Back to Life in the search bar
After installation, click the  Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Load Restore Old Photos Model Description

Facilitates restoration of old photos using advanced AI models for enhanced quality and imperfection removal.

Load Restore Old Photos Model:

The BOPBTL_LoadRestoreOldPhotosModel node is designed to facilitate the restoration of old photos by leveraging advanced AI models. This node is part of a comprehensive system aimed at bringing old photos back to life, enhancing their quality, and removing scratches or other imperfections. By loading the necessary models and applying them to the input images, this node helps you achieve high-quality restoration results. The primary goal of this node is to simplify the process of photo restoration, making it accessible even to those without a deep technical background. It ensures that the complex operations required for restoring old photos are handled seamlessly, providing you with enhanced and restored images with minimal effort.

Load Restore Old Photos Model Input Parameters:


The image parameter is the input image that you want to restore. It should be provided as a tensor, typically in the format of a PyTorch tensor. This image will undergo various transformations and enhancements to restore its original quality. The image should be in RGB format and can be of any size, although larger images may require more processing time.


The bopbtl_models parameter is a tuple containing the models and transformations required for the restoration process. This includes the restoration model, image transformation functions, and mask transformation functions. These models are pre-trained and optimized for restoring old photos, ensuring high-quality results. The tuple typically includes options, the model itself, and the necessary transformations.


The scratch_mask parameter is an optional tensor that represents the mask for scratches or other imperfections on the photo. If provided, this mask will guide the restoration process to focus on specific areas that need repair. The mask should be of the same dimensions as the input image and can be used to enhance the quality of the restoration by targeting specific defects.

Load Restore Old Photos Model Output Parameters:


The restored_images parameter is the output of the node, which consists of the restored version of the input image. This output is a list of tensors, each representing a restored image. The restored images are enhanced to remove scratches, improve quality, and bring the old photos back to life. The output images are in RGB format and retain the original dimensions of the input image.

Load Restore Old Photos Model Usage Tips:

  • Ensure that the input image is in RGB format and properly pre-processed before feeding it into the node for optimal results.
  • Utilize the scratch_mask parameter if your photo has specific areas that need targeted restoration. This can significantly improve the quality of the restoration.
  • Experiment with different models and transformations included in the bopbtl_models tuple to find the best combination for your specific photo restoration needs.

Load Restore Old Photos Model Common Errors and Solutions:

"Model loading failed"

  • Explanation: This error occurs when the node is unable to load the required models for the restoration process.
  • Solution: Ensure that all model files are correctly placed in the specified directories and that the paths provided in the bopbtl_models tuple are accurate.

"Input image format not supported"

  • Explanation: This error indicates that the input image is not in the expected format (e.g., not an RGB image or not a tensor).
  • Solution: Convert your input image to an RGB format and ensure it is provided as a PyTorch tensor before feeding it into the node.

"Scratch mask dimensions mismatch"

  • Explanation: This error occurs when the dimensions of the scratch_mask do not match the dimensions of the input image.
  • Solution: Ensure that the scratch_mask tensor has the same width and height as the input image to avoid this error.

Load Restore Old Photos Model Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI Bringing Old Photos Back to Life

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.