ComfyUI nodes to use Depth Anything V3 - the latest depth estimation model from ByteDance. For now monocular depth, camera pose estimation and 3D point clouds/gaussians are supported. Models autodownload from HuggingFace (depth-anything org). This is a first draft, let me know if you have any feedback! :)

ComfyUI-DepthAnythingV3


Create camera parameters for conditioning DA3 depth estimation.

Provides known camera pose to improve depth estimation accuracy.

Parameters:
- cam_x/y/z: Camera position in world space
- rot_x/y/z: Camera rotation (Euler angles in degrees)
- focal_length: If > 0, uses this value. Otherwise uses fov_degrees.
- fov_degrees: Field of view in degrees (used if focal_length is 0)

Output:
- CAMERA_PARAMS: Dictionary with extrinsics (4x4) and intrinsics (3x3) matrices


ComfyUI Node: DA3 Create Camera Parameters

Category

Inputs

Outputs

Extension: ComfyUI-DepthAnythingV3

Run ComfyUI workflows in the Cloud!