ComfyUI Node Runs on cloud
Run MoGe Inference
Run MoGe on a single image to estimate depth and geometry.
Run MoGe Inference
- moge_model
- image
- moge_geometry
◄resolution_level9►
◄fov_x_degrees0.0►
◄batch_size4►
◄force_projectiontrue►
◄apply_masktrue►
Categoryimage/geometry estimation
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| moge_model | MOGE_MODEL | — | |
| image | IMAGE | — | |
| resolution_level | INT | 90–9 | 0 = fastest, 9 = most detail. |
| fov_x_degrees | FLOAT | 0.00–170 | Horizontal field of view of the source camera. Sets the focal length used to unproject the depth map into 3D. 0 = auto-recover from the predicted points. |
| batch_size | INT | 41–64 | Images per inference call. Lower if you OOM on a long video / image set. |
| force_projection | BOOLEAN | true | — |
| apply_mask | BOOLEAN | true | Set masked-out (sky / invalid) pixels to inf in points and depth so meshing culls them. Disable to keep the raw predicted geometry everywhere; the mask is still returned separately. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| moge_geometry | MOGE_GEOMETRY | — |