Depth Anything V2 Giant
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Tik Tok,Hong Kong University
- Organisation type
- Industry,Academia
- Country
- China, Hong Kong
- Published
- 20 October 2024
- Authors
- Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- 3D modeling
- Task
- 3D reconstruction
- Base model
- DINOv2
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 1.3B
- Training data
- tokens
giant model -1.3B parameters
"Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled image" "All images are trained at the resolution of 518×518 by resizing the shorter size to 518 followed by a random crop. When training the teacher model on synthetic images, we use a batch size of 64 for 160K iterations. In the third stage of training on pseudo-labeled real images, the model is trained with a batch size of 192 for 480K iterations. "
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
the model was supposed to be released on hugging face, but, 1 year after the publication, it is still not there
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Depth Anything V2
- Last updated
- 28 November 2025
What the numbers mean
About this model
Depth Anything V2 Giant was published by Tik Tok,Hong Kong University, in China, in October 2024. It comes out of industry,Academia.
It works in 3D modeling, and is recorded as doing 3D reconstruction.
Its starting point was DINOv2 — most models at this scale are adapted from an existing base rather than built from nothing.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
Depth Anything V2 Giant — common questions
How many parameters does Depth Anything V2 Giant have?
Depth Anything V2 Giant has 1.3B parameters. giant model -1.3B parameters. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created Depth Anything V2 Giant?
Depth Anything V2 Giant was published by Tik Tok,Hong Kong University, based in China, categorised as industry,Academia.
When was Depth Anything V2 Giant released?
Depth Anything V2 Giant was published in October 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Depth Anything V2 Giant used for?
Depth Anything V2 Giant works in 3D modeling, and is recorded as handling 3D reconstruction. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
What GPU do I need to run Depth Anything V2 Giant?
None. Depth Anything V2 Giant is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is Depth Anything V2 Giant open source?
No. Depth Anything V2 Giant has not had its weights published, so it exists only as a service controlled by its owner.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.