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


Convert DA3 depth map to textured 3D mesh (GLB format).

Uses grid-based triangulation to create a clean mesh from the depth map.
Automatically filters invalid regions (sky, low confidence, depth discontinuities).

Inputs:
- depth_raw: Metric depth map (from DepthAnything_V3 with normalization_mode="Raw")
- confidence: Confidence map
- intrinsics: Camera intrinsics (REQUIRED - connect from DepthAnything_V3)
- sky_mask: Sky segmentation (recommended - excludes sky from mesh)
- source_image: Source image for mesh texture

Parameters:
- confidence_threshold: Filter vertices below this confidence
- depth_edge_threshold: Skip triangles across large depth jumps (prevents artifacts)
- downsample: Reduce mesh density (higher = fewer triangles, faster)
- filename_prefix: Output filename prefix

Output: GLB file path


ComfyUI Node: DA3 to Mesh

Category

Inputs

Outputs

Extension: ComfyUI-DepthAnythingV3

Run ComfyUI workflows in the Cloud!