Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Depth Anything 3 (DA3-BASE)

by ByteDance Seed Team

Open-weights vision transformer that predicts depth maps, camera poses and 3D geometry from one or more images.

AI 3D model generators Open source

GitHub repoWebsite

2. Commercial use: README on GitHub

“| [DA3-LARGE-1.1](https://huggingface.co/depth-anything/DA3-LARGE-1.1) | 0.35B | ✅ | ✅ | ✅ | | | | CC BY-NC 4.0 |”

Allowed with DA3-BASE, DA3-SMALL, DA3METRIC-LARGE or DA3MONO-LARGE (Apache 2.0); not with the Giant, Large or Nested models.

README on GitHub

License checked Nov 10, 2026 against 2 official pages. Tap a verdict to see its source. How we checked Report an error

Depth Anything 3: depth and 3D scenes from photos

Depth Anything 3 is a free AI model from ByteDance that works out how far away each part of a photo is. From several photos or video frames of a place, it also finds where the camera stood and builds a 3D scene. This card is about the Base size, which is under Apache 2.0; most larger sizes are non-commercial.

Where you can use it

A 3D scene from a few photos

Take several photos of a room or an object and get one 3D scene file that a viewer or Blender can open.

Where the camera stood

Work out the camera position and lens of each photo in a set, for example to line up photos or add 3D objects into them.

Depth from a video

Run a phone video through the command line tool to get depth for its frames and a 3D view of the scene.

Plug into Blender or robots

Feed depth into tools people already built around it, such as a Blender add-on, image workflows, robots or a web VR viewer.

Blurred backgrounds and photo depth effects Idea

Use the depth map of one photo to blur the background behind a person or product, or to make a slight 3D motion effect.

Rough room measurements Idea

Get a first idea of room sizes from photos for a planning app, using the metric model that gives distances in meters.

As reported by ByteDance Seed Team: The Base model has 0.12B parameters; 44.3% better camera pose accuracy and 25.1% better geometric accuracy than VGGT on average, on the makers' own benchmark.

Depth Anything 3 (DA3-BASE) popularity

29 / 100
Gid Score, same scale as developer tools
6,712
GitHub stars
Depth Anything 3 (DA3-BASE): GitHub starsByteDance-Seed/depth-anything-3 6,712

How the Gid Score is calculated

How to start

Tell your AI assistant

“Install Depth Anything 3 from github.com/ByteDance-Seed/depth-anything-3 in a Python 3.10 virtual environment and run the depth-anything/da3-base model (Apache 2.0, not the Giant or Nested ones) on the photos in shots/, exporting a GLB scene to output/.”

Show codeStep 1 or Step 2 or Step 3

Get the code from GitHub and install it in a Python environment with PyTorch 2.

git clone https://github.com/ByteDance-Seed/depth-anything-3
cd depth-anything-3
pip install -e .

Mistakes to avoid

Copying the README example with depth-anything/DA3NESTED-GIANT-LARGE into a commercial product
from_pretrained("depth-anything/da3-base") (or DA3-SMALL, DA3METRIC-LARGE, DA3MONO-LARGE, all Apache 2.0)

The Nested Giant model is CC BY-NC 4.0, non-commercial only.

Treating Base output as distances in meters
Use DA3METRIC-LARGE and metric_depth = focal * net_output / 300 for meters

The main models give relative depth; the formula is for the Metric model.

Asking DA3-BASE for gs_ply or gs_video export
Use glb, npz, ply or depth_vis with Base; Gaussian exports need infer_gs=True with a Giant model (non-commercial)

Gaussian output is only available on the Giant models.

Starting da3 backend with --host 0.0.0.0 on a shared or public machine
Keep the default 127.0.0.1 binding unless the network is trusted

The backend server has no login, so anyone who can reach it can use it.

License

Apache 2.0 (DA3-SMALL, DA3-BASE, metric and mono models); CC BY-NC 4.0 (DA3 Large and Giant) license. The Base model is under Apache 2.0: free for paid products, keep the license and notice files with copies. The Giant, Large and Nested models are for non-commercial use only.

Commercial use
With conditions

“| [DA3-LARGE-1.1](https://huggingface.co/depth-anything/DA3-LARGE-1.1) | 0.35B | ✅ | ✅ | ✅ | | | | CC BY-NC 4.0 |” README on GitHub

Credit
Not needed

“License Apache 2.0” huggingface.co/depth-anything/DA3-BASE

Inside your app or game
With conditions

“| [DA3-BASE](https://huggingface.co/depth-anything/DA3-BASE) | 0.12B | ✅ | ✅ | ✅ | | | | Apache 2.0 |” README on GitHub

Pass the files on to your users
With conditions

Passing on the code or Base weights is allowed with the Apache 2.0 license; changed files must say they were changed.

“You must cause any modified files to carry prominent notices stating that You changed the files” LICENSE on GitHub

AI training
Not stated
Bots and bulk downloads
Not stated

AllowedWith conditionsNot allowedNot stated or not checked yet

Is Depth Anything 3 (DA3-BASE) free for commercial use? The full answer Not legal advice. Check the license page before you ship.

For your agent

License rules tell your agent what it may do with Depth Anything 3 (DA3-BASE). Paste them into your prompt or AGENTS.md.

License rules
- Depth Anything 3 (DA3-BASE) (AI 3D model generators). Open-weights vision transformer that predicts depth maps, camera poses and 3D geometry from one or more images. Price: free; commercial use with conditions; no credit needed; ship inside your app with conditions.
  Connect: download from https://huggingface.co/depth-anything/DA3-BASE (no API).
  Rule: Keep the Apache 2.0 license and notice files with any distributed copy of the model.
  Rule: Install and run the model locally from the GitHub repository; no hosted API is provided.
  Rule: Cite the Depth Anything 3 paper when used in research.
  Rule: The model may be weaker on domain-specific images; check results.
  Rule: DA3 Large and Giant checkpoints are CC BY-NC 4.0 (non-commercial); Small, Base, metric and mono models are Apache 2.0.
  License: https://huggingface.co/depth-anything/DA3-BASE (checked 2026-11-10; details: https://agentgid.com/assets/depth-anything/)
Can an agent use it by itself?
No.
API, key or account
Not needed. Everything runs on your side.
MCP server
None found
Credit line, if you want one
Depth by Depth Anything 3 (DA3-BASE, ByteDance Seed, Apache 2.0)
This card for machines

Alternatives

Depth Anything 3 (DA3-BASE) This page

Free With conditions Download

TRELLIS

Pick TRELLIS when you want a finished 3D object (mesh, 3D Gaussians or radiance field) from one picture rather than depth and camera data for a scene.

Free With conditions Download

TripoSR

Pick TripoSR when you want a single object as a mesh file from one picture, under MIT.

Free Commercial OK Download

Hunyuan3D 2.0

Pick Hunyuan3D 2.0 when you want a textured 3D object built from one picture.

Free With conditions Download

Shap-E

OpenAI's text-to-3D and image-to-3D model that outputs textured meshes or neural radiance fields.

Free With conditions Download

Point-E

Official code and models for generating 3D point clouds from text or images, plus a model that turns point clouds into meshes.

Free With conditions Download

All ai 3d model generators

Questions

Can I use it in a paid app?

Yes with DA3-BASE, which is Apache 2.0. The Giant and Nested models are non-commercial only.

Which files can it export?

GLB scenes, NPZ and PLY data, depth pictures and more; formats can be combined with a hyphen, such as mini_npz-glb.

Does it work with one photo?

Yes. It predicts a depth map from a single photo, and gives more consistent results from several photos of the same place.

Is there an online demo?

Yes, the model page links a demo on Hugging Face; the model itself runs on your own machine.

Which Python versions work?

Python 3.9 to 3.13 for the package; the optional web app part needs Python 3.10 or newer.