Video-Depth-Anything-Base

by bigshanedogg depth-estimation transformers cc-by-nc-4.0

4 downloads 0 likes on Hugging Face updated 2026-10-27

Hugging Face

bigshanedogg/Video-Depth-Anything-Base · model repository official

Revision: 5555f5e3ca90
Files: 18
Downloaded from this source: 4

Provider-specific. This path, revision and file list belong to Hugging Face alone. A different source for the same model may publish different files, or the same names with different contents — which is why nothing here is merged across providers.

Tensor information · safetensors

Parameters: 114.5M
Precision · F32: 114.5M params

Parameter counts and precision come from the provider's safetensors metadata. Per-tensor shapes live in the file header and are not part of our index.

Files 18 · revision `5555f5e3ca90`

Hashes: Git OID identifies the file in the repository; LFS SHA256 is the fingerprint of a large file's contents; Xet is the provider's own content fingerprint. Expand “hashes” on any row for the full values.

.gitattributes 1.5 KiB

hashes

Git OID
a6344aac8c09253b3b630fb776ae94478aa0275b
config.json 681 B

hashes

Git OID
7373c6e68c967343eca80374d36726e6b407eacd
configuration_video_depth_anything.py 1.2 KiB

hashes

Git OID
5bf510b4b29f21873e1da7de475a547a17064e74
image_processing_video_depth_anything.py 4.1 KiB

hashes

Git OID
552d7853c9935171742036ab55886ae95463556c
LICENSE 18.9 KiB

hashes

Git OID
fe463e0f7888bbf8b82e42d55f5743508ddafb7e
LICENSE.code 11.1 KiB

hashes

Git OID
f49a4e16e68b128803cc2dcea614603632b04eac
model.safetensors LFS 436.9 MiB c44413b568de

hashes

Git OID
970615ccd2676dfe5fba48f2e448187309c18a01

LFS SHA256
c44413b568deef4438f6a002d72cebc19f3a7e35854a1b32918a720d80665571

Xet hash
0365380f91388b89b5c1a571d428275f425c35aa66b1b4c4778383568e06c185

Pointer size
134 B
modeling_video_depth_anything.py 5.8 KiB

hashes

Git OID
42870191eed32679cb4f17cf3469744ef19c26d2
NOTICE 1.7 KiB

hashes

Git OID
e391de323beab0a59c7c88edd2edea249dc47846
processing_video_depth_anything.py 694 B

hashes

Git OID
1f4231b4b7c3bbc77bd0db16ccc79ea3ff0fb922
processor_config.json 485 B

hashes

Git OID
e6c4d75b73adc2b123ddd4b40bb76b6bed117a0f
README.md 4.2 KiB

hashes

Git OID
f40186ffd64e16d253fd5821311bb9c59f060771
vda_dinov2.py 36.5 KiB

hashes

Git OID
c3e706de0c93b5e5aa1fd6d4e9e19657f8048400
vda_dpt.py 25 KiB

hashes

Git OID
235bf363f987d112483b830314e816d54b64e290
vda_motion_attention.py 17 KiB

hashes

Git OID
3171089d2505aa48a00a8da1be3395591c3599da
vda_motion_module.py 13.1 KiB

hashes

Git OID
e432a5f3b5ab751adea4ae689fedeab8456aeeef
vda_video_depth.py 7.1 KiB

hashes

Git OID
5119359130346f66a6ebd2c899763f41c3f4bff4
vda_video_depth_stream.py 7.3 KiB

hashes

Git OID
7be98851dd1c10da4c7267098041a00761d1f06b

Get this model

hp get bigshanedogg/Video-Depth-Anything-Base

The huggingpeers CLI is not released yet. Once it ships, the command above will download the model. Until then, download the weights from Hugging Face.

Details

HuggingPeers ID: ID hpm-NvcYF0EQAiA
Provider: Hugging Face
Revision: 5555f5e3ca90
Organization: bigshanedogg
Pipeline: depth-estimation
Library: transformers
License: cc-by-nc-4.0
Parameters: 114.5M
Published: 2026-10-27

Files 18

Total size: 437.1 MiB
LFS files: 1
Parameters: 114.5M
Revision: 5555f5e3ca90

Browse files & hashes →

Papers 1

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos 282 citations · 2025

Open the papers tab →

Code

GitHub · DepthAnything/Video-Depth-Anything ↗

Linked from the model card — we do not mirror source repositories.

Sources

Hugging Face · bigshanedogg/Video-Depth-Anything-Base (this) · checked recently

View on Hugging Face ↗