ComfyUI > Nodes > ComfyUI-Chord > ChordNormalToHeight

ComfyUI Node: ChordNormalToHeight

Class Name

ChordNormalToHeight

Category
Chord
Author
ubisoft (Account age: 3086days)
Extension
ComfyUI-Chord
Latest Updated
2025-12-24
Github Stars
0.24K

How to Install ComfyUI-Chord

Install this extension via the ComfyUI Manager by searching for ComfyUI-Chord
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-Chord 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
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ChordNormalToHeight Description

Converts normal maps to height maps using a Poisson solver for realistic 3D texture rendering.

ChordNormalToHeight:

The ChordNormalToHeight node is designed to convert a normal map into a height map using a sophisticated Poisson solver technique with overlapping subregions. This process is essential in 3D graphics and digital art, where height maps are used to simulate surface details and textures. By transforming normal maps, which represent surface normals, into height maps, this node allows for more realistic rendering of textures and surfaces. The use of a Poisson solver ensures that the conversion maintains the integrity of the surface details, providing a smooth and accurate height map. This node is particularly beneficial for artists and designers who need to create detailed and realistic textures for 3D models, as it automates a complex mathematical process, making it accessible without requiring deep technical knowledge.

ChordNormalToHeight Input Parameters:

normal

The normal parameter is an input image that represents the normal map to be converted into a height map. A normal map is a type of image that encodes surface normals, which are vectors perpendicular to the surface of a 3D object. This parameter is crucial as it serves as the basis for generating the height map. The normal map should be provided as a tensor with dimensions corresponding to the image's height, width, and color channels. The quality and accuracy of the resulting height map depend significantly on the input normal map, so it is important to use a well-defined normal map for optimal results. There are no specific minimum or maximum values for this parameter, but the input should be a valid image tensor.

ChordNormalToHeight Output Parameters:

height

The height parameter is the output image that represents the height map generated from the input normal map. A height map is a grayscale image where the intensity of each pixel corresponds to the height of the surface at that point. This output is essential for creating realistic textures and surface details in 3D models, as it allows for the simulation of depth and relief. The height map can be used in various applications, such as bump mapping or displacement mapping, to enhance the visual realism of 3D objects. The output is a tensor with dimensions matching the original input image, ensuring that the height map aligns perfectly with the original surface details.

ChordNormalToHeight Usage Tips:

  • Ensure that the input normal map is of high quality and accurately represents the surface normals to achieve the best results in the height map conversion.
  • Experiment with different normal maps to see how variations in surface normals affect the resulting height map, allowing for creative exploration in texture design.
  • Use the height map in conjunction with other texture maps, such as diffuse or specular maps, to create a more comprehensive and realistic material representation in 3D rendering.

ChordNormalToHeight Common Errors and Solutions:

AssertionError: Normal map batch size is not 1

  • Explanation: This error occurs when the input normal map tensor has a batch size other than 1, which is not supported by the normal_to_height function.
  • Solution: Ensure that the input normal map tensor has a batch size of 1. You may need to adjust the input tensor dimensions accordingly before passing it to the node.

ValueError: Invalid normal map dimensions

  • Explanation: This error arises when the input normal map does not have the expected dimensions, which should be a 4D tensor with a single batch, three channels, and height and width.
  • Solution: Verify that the input normal map is a 4D tensor with the correct dimensions. If necessary, reshape or permute the tensor to match the expected format before using the node.

ChordNormalToHeight Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-Chord
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

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.