Comfy-Org/ComfyUI · error · ValueError

moge_geometry has no depth output.

Error message

moge_geometry has no depth output.

What it means

The MoGe render node treats moge_geometry as a dict of available outputs; requesting 'depth' or 'depth_colored' requires the 'depth' key to exist. An inference run configured to not produce depth (or a geometry dict from a source that only emits points/normals) triggers this check.

Source

Thrown at comfy_extras/nodes_moge.py:291

            description="Render a depth map or normal map from geometry data",
            category="image/geometry estimation",
            inputs=[
                MoGeGeometry.Input("moge_geometry"),
                io.Combo.Input("output", options=["depth", "depth_colored", "normal_opengl", "normal_directx", "mask"], default="depth",
                    tooltip="DirectX vs OpenGL controls the normal-map green-channel convention. DirectX: green = -Y down (Unreal). OpenGL: green = +Y up (Blender, Substance, Unity, glTF)."),
            ],
            outputs=[io.Image.Output()],
        )

    @classmethod
    def execute(cls, moge_geometry, output) -> io.NodeOutput:
        is_normal = output in ("normal_directx", "normal_opengl")
        opengl = output.endswith("_opengl")

        # Pick the input tensor for the chosen mode and validate availability.
        if output in ("depth", "depth_colored"):
            if "depth" not in moge_geometry:
                raise ValueError("moge_geometry has no depth output.")
            src = moge_geometry["depth"]
        elif is_normal:
            if "normal" in moge_geometry:
                src = moge_geometry["normal"]
            elif "points" in moge_geometry:
                src = moge_geometry["points"]
            else:
                raise ValueError("moge_geometry has neither normals nor points to derive normals from.")
        elif output == "mask":
            if "mask" not in moge_geometry:
                raise ValueError("moge_geometry has no mask output.")
            src = moge_geometry["mask"]
        else:
            raise ValueError(f"Unknown output mode: {output}")

        B = src.shape[0]
        pbar = comfy.utils.ProgressBar(B)
        out: list[torch.Tensor] = []

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Re-run MoGe inference with depth output enabled so 'depth' is present in moge_geometry.
2. Switch the render node's output to a mode the geometry actually contains (points, normal, mask).
3. Inspect the dict keys ('depth', 'points', 'normal', 'mask') before selecting the render mode.

Example fix

// before
out = MoGeRender.execute(geo, output="depth")     # geo lacks 'depth'

// after
out = MoGeRender.execute(geo, output="normal")    # or re-run inference with depth enabled

if output in ('depth', 'depth_colored') and 'depth' not in moge_geometry:
    raise UserFacingError('re-run inference with depth enabled')

def geometry_has(geo, key: str) -> bool:
    return key in geo

When it happens

Trigger: Calling the render node with output='depth' on a moge_geometry dict produced by an inference node run without depth output, or a hand-assembled dict missing the 'depth' key.

Common situations: Switching the render node's output combo after the inference node was configured for normals-only; chaining two render nodes off a geometry that lacks depth.

Related errors

• moge_geometry has neither normals nor points to derive norma
• moge_geometry has no mask output.
• Unknown output mode: {output}
• moge_geometry has no points output.
• MoGePanoramaInference takes a single image (got batch of {im

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/c1066444bc7b5672. Report an issue: GitHub.