Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Overview

This node performs depth estimation on equirectangular panorama images. It works by splitting the panorama into 12 perspective views, running the MoGe depth estimation model on each view, and then merging the results back into a single, complete depth map for the original panorama.

Inputs

ParameterData TypeRequiredRangeDescription
moge_modelMOGE_MODELYesThe MoGe model to use for inference.
imageIMAGEYesEquirectangular panorama image (any aspect ratio).
resolution_levelINTYes0 to 9Per-view detail level. Higher values produce more detailed depth maps (default: 9).
split_resolutionINTYes256 to 1024Resolution of each perspective view after splitting the panorama (default: 512).
merge_resolutionINTYes256 to 8192Long-side resolution of the final merged equirectangular depth map (default: 1920).
batch_sizeINTYes1 to 12Number of perspective views to process in each inference batch. The total number of views is 12 (default: 4).

Outputs

Output NameData TypeDescription
moge_geometryMOGE_GEOMETRYA dictionary containing the estimated geometry: points (3D point cloud), depth (depth map), mask (valid area mask), and image (the input image).

Source fingerprint (SHA-256): 3a701e3679bc35cd5fddc54868ac9c4bc9b4e23a5b97bbf61e46b7309e43600b