ComfyUI Node
LC Depth Anything V2 🌊
Depth Anything V2 depth map, normalized 0-1 per image. Bright = near unless invert is on. Outputs a 3-channel image and a MASK of the same map.
LC Depth Anything V2 🌊
- image
- depth
- depth_mask
◄model▾►
◄resolution518►
◄invertfalse►
CategoryLC MaskMaker/depth
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | Image to estimate depth for. | |
| model | COMBO | Depth Anything V2 weights. The license is in the label: Small is Apache-2.0, Base / Large / Giant are CC-BY-NC-4.0 (non-commercial). Uses the file you already have (models/depthanything or comfyui_controlnet_aux), or downloads it the first time you run. | |
| resolution | INT | 518224–2044 | Size the shorter side is processed at (rounded to a multiple of 14). 518 is what the model was trained at; higher can add detail on big images. |
| invert | BOOLEAN | false | Off: bright = near (what Depth Anything and depth ControlNets use). On: bright = far. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| depth | IMAGE | — |
| depth_mask | MASK | — |