Models / depth-anything / Depth Anything ViT-L/14

Depth Anything ViT-L/14

JSON →
vision

A monocular depth estimation model using a Vision Transformer (ViT-L/14) backbone from the original Depth Anything release.

imagevision
Specs
Context & limits
context window
max output
Lifecycle
Dates
released2024-01-01
Resources