ComfyUI  >  Nodes  >  ComfyUI-CCSR >  CCSR_Upscale

ComfyUI Node: CCSR_Upscale

Class Name


kijai (Account age: 2184 days)
Latest Updated
Github Stars

How to Install ComfyUI-CCSR

Install this extension via the ComfyUI Manager by searching for  ComfyUI-CCSR
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-CCSR 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

CCSR_Upscale Description

Enhance image resolution with advanced upscaling for AI-generated images, preserving fine details and textures.


The CCSR_Upscale node is designed to enhance the resolution of latent images, making it an essential tool for AI artists looking to improve the quality and detail of their generated images. This node leverages advanced upscaling techniques to increase the dimensions of latent images, which are intermediate representations used in the process of generating final images. By using this node, you can achieve higher resolution outputs without compromising on the quality, ensuring that the finer details and textures are preserved. This is particularly useful for creating high-definition artwork, animations, or any visual content that requires a high level of detail.

CCSR_Upscale Input Parameters:


samples is the latent image data that you want to upscale. This parameter is crucial as it serves as the input for the upscaling process. The quality and characteristics of the final output heavily depend on the initial latent samples provided.


upscale_method determines the algorithm used for upscaling the latent images. The available options are nearest-exact, bilinear, area, bicubic, and lanczos. Each method has its own advantages: nearest-exact is fast but may produce blocky results, bilinear and bicubic offer smoother transitions, area is good for downscaling, and lanczos provides high-quality results but is computationally intensive. Choosing the right method can significantly impact the visual quality of the upscaled image.


scale_by is a floating-point value that specifies the factor by which the latent image should be scaled. The default value is 1.5, with a minimum of 0.01 and a maximum of 8.0. This parameter allows you to control the degree of upscaling, enabling you to achieve the desired resolution for your images. Adjusting this value can help you find the perfect balance between image size and quality.

CCSR_Upscale Output Parameters:


The output samples is the upscaled latent image data. This parameter contains the enhanced resolution version of the input latent samples, ready for further processing or final rendering. The quality of this output is directly influenced by the input parameters and the chosen upscaling method.

CCSR_Upscale Usage Tips:

  • For high-quality results, consider using the lanczos or bicubic upscaling methods, especially when working with detailed images.
  • Adjust the scale_by parameter carefully to avoid excessively large images that may be computationally expensive to process.
  • Experiment with different upscale_method options to find the best balance between performance and visual quality for your specific use case.

CCSR_Upscale Common Errors and Solutions:

"Invalid upscale method"

  • Explanation: The upscale_method provided is not one of the accepted values.
  • Solution: Ensure that the upscale_method is set to one of the following: nearest-exact, bilinear, area, bicubic, or lanczos.

"Scale factor out of range"

  • Explanation: The scale_by value is outside the allowed range of 0.01 to 8.0.
  • Solution: Adjust the scale_by parameter to a value within the specified range.

"Input samples not provided"

  • Explanation: The samples parameter is missing or not correctly specified.
  • Solution: Ensure that the samples parameter is correctly set with valid latent image data before running the node.

CCSR_Upscale Related Nodes

Go back to the extension to check out more related nodes.

© 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.