Node packÜberprüftExtern

ComfyUI-DepthAnythingV3

ComfyUI support for DepthAnything V3 model

Quellegithub.com/PozzettiAndrea/ComfyUI-DepthAnythingV3

Betreuer@PozzettiAndreaUnratedBewertung

Paketprofil

Status: Überprüft
Verleger: @PozzettiAndrea
Quelle: GitHub

README

[!WARNING] Warning, uses experimental package comfy-env to attempt a one click isolated install. Will download and use pixi package manager.

ComfyUI Depth Anything V3

Installation

Three options, in order of speed → reliability:

ComfyUI Manager (recommended) — search for Depth Anything V3 in the Manager and click Install from the highest version displayed. If that doesn't work, try nightly.
Manager via Git URL — in ComfyUI Manager: "Install via Git URL" with https://github.com/PozzettiAndrea/ComfyUI-DepthAnythingV3.git.

Manual (most reliable):

cd ComfyUI/custom_nodes
git clone https://github.com/PozzettiAndrea/ComfyUI-DepthAnythingV3.git
cd ComfyUI-DepthAnythingV3
pip install -r requirements.txt --upgrade
python install.py

Please report any problems you hit during installation or use of my nodes — open a Discussion or Issue. Very grateful for your help! 🙏

Custom nodes for Depth Anything V3 integration with ComfyUI.

Simple workflow: simple

Advanced workflow: advanced

Single image to 3d: 3d

Multiple image to 3d: 3d_multiview

Single image to mesh: bas_relief_wf

Use multi attention node for smooth video depth! video

Demo Videos

You can use the multi-view node to use the cross attention feature of the main class of models. This is done to have a more consistent depth across frames of a video.

https://github.com/user-attachments/assets/058bd968-aae3-4759-887c-4c98132559f0

You can reconstruct 3D point clouds!

https://github.com/user-attachments/assets/8ef6e74b-c7c7-41e7-b1c6-de44733e6c61

Even from multiple views, with the option to either match them (with icp) or leave them to use the predicted camera positions. You also have a field on the point cloud to show you which view each point came from.

https://github.com/user-attachments/assets/6892313d-bcd8-44ec-9038-7d4d8915f59e

Description

Depth Anything V3 is the latest depth estimation model that predicts spatially consistent geometry from visual inputs.

Published: November 14, 2025 Paper: Depth Anything 3: Recovering the Visual Space from Any Views

Model Variants

Model	Size	Features
DA3-Small	80M	Fast, good quality
DA3-Base	220M	Balanced quality and speed
DA3-Large	350M	High quality, balanced
DA3-Giant	1.15B	Best quality, slower
DA3Mono-Large	350M	Optimized for monocular depth
DA3Metric-Large	350M	Metric depth estimation
DA3Nested-Giant-Large	1.4B	Combined model with metric scaling

Model Capabilities

Different models support different features:

Feature	Small/Base/Large/Giant	Mono-Large	Metric-Large	Nested
Sky Segmentation	❌	✅	✅	✅
Camera Conditioning	✅	❌	❌	✅
Multi-View Attention	✅	⚠️	⚠️	✅
3D Gaussians	✅*	❌	❌	✅*
Ray Maps	✅	❌	❌	✅