Filter by type:
Filter by tags:
depth-anything-3-base
Depth Anything 3 (base) monocular metric depth + camera pose, served via the
native depth-anything.cpp backend (C++/ggml + purego, no Python at inference).
Given an image it returns a dense depth map plus the recovered camera
extrinsics (3x4) and intrinsics (3x3). Use GenerateImage (src -> normalized
depth PNG at dst) or Predict (JSON depth stats + pose). q4_k is the
recommended CPU default.
Repository: localaiLicense: apache-2.0
depth-anything-3-base-q8_0
Depth Anything 3 (base), q8_0 — near-lossless 8-bit quant (~149 MB). Same
depth + camera pose output as the q4_k default at higher fidelity.
Repository: localaiLicense: apache-2.0
depth-anything-3-base-f16
Depth Anything 3 (base), f16 — half precision (~233 MB), no measurable
accuracy loss vs f32. Depth + camera pose.
Repository: localaiLicense: apache-2.0
depth-anything-3-base-f32
Depth Anything 3 (base), f32 — maximum fidelity (~412 MB). Reference-parity
depth + camera pose.
Repository: localaiLicense: apache-2.0
depth-anything-3-giant
Depth Anything 3 (giant / vitg), f32 — the large backbone (~4.9 GB) for
maximum quality depth + camera pose. GPU recommended.
Repository: localaiLicense: apache-2.0
depth-anything-3-small
Depth Anything 3 (small / vits), f32 — the smallest backbone (~131 MB) for
fast CPU depth + camera pose. Same output as base at lower latency.
Repository: localaiLicense: apache-2.0
depth-anything-3-large
Depth Anything 3 (large / vitl), f32 (~1.6 GB) — higher quality depth +
camera pose than base. GPU recommended for interactive use.
Repository: localaiLicense: apache-2.0
depth-anything-3-mono-large
Depth Anything 3 (monocular large / vitl), f32 (~1.3 GB) — single-image
monocular depth + a sky mask (no camera pose). DPT single-head variant; use
GenerateImage (src -> normalized depth PNG) or Predict (JSON depth stats).
Repository: localaiLicense: apache-2.0
depth-anything-3-metric-large
Depth Anything 3 (metric large / vitl), f32 (~1.3 GB) — single-image
metric-scale depth (meters) + a sky mask. DPT single-head metric variant; use
GenerateImage (src -> normalized depth PNG) or Predict (JSON metric depth
stats, is_metric=true).
Repository: localaiLicense: apache-2.0
depth-anything-3-nested
Depth Anything 3 (nested giant+large), f32 — the recommended metric model. A
two-branch pipeline: the anyview GIANT (vitg) branch and a metric ViT-L branch
are run and aligned to recover true metric-scale depth (meters) + scaled camera
pose from a single image. Downloads both branches (~6 GB total); GPU strongly
recommended. Predict returns metric depth stats + pose (is_metric=true).
Repository: localaiLicense: apache-2.0
depth-anything-2-base
Depth Anything V2 (base / ViT-B) monocular depth, served via the native
depth-anything.cpp backend (C++/ggml + purego, no Python at inference).
Given an image it returns a dense monocular depth map only — no camera pose,
no confidence. This is the relative variant (relative inverse depth). Use
GenerateImage (src -> normalized depth PNG at dst) or the Depth endpoint.
q4_k is the recommended CPU default.
Repository: localaiLicense: apache-2.0
depth-anything-2-base-q8_0
Depth Anything V2 (base / ViT-B), q8_0 — near-lossless 8-bit quant. Same
relative monocular depth output as the q4_k default at higher fidelity. Use
GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-base-f16
Depth Anything V2 (base / ViT-B), f16 — half precision, no measurable
accuracy loss vs f32. Relative monocular depth only (no pose). Use
GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-base-f32
Depth Anything V2 (base / ViT-B), f32 — maximum reference fidelity. Relative
monocular depth only (no pose). Use GenerateImage (src -> depth PNG) or the
Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-small
Depth Anything V2 (small / ViT-S), f32 — the smallest, fastest backbone for
relative monocular depth on CPU. Depth only (no pose). Use GenerateImage
(src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-large
Depth Anything V2 (large / ViT-L), f32 — higher-quality relative monocular
depth than base. Depth only (no pose). Use GenerateImage (src -> depth PNG)
or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-metric-hypersim-small
Depth Anything V2 Metric (Hypersim, indoor / ViT-S), q4_k — metric monocular
depth in METRES (indoor, max_depth 20). Depth only (no pose). Use
GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-metric-hypersim-base
Depth Anything V2 Metric (Hypersim, indoor / ViT-B), q4_k — metric monocular
depth in METRES (indoor, max_depth 20). Depth only (no pose). Use
GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-metric-hypersim-large
Depth Anything V2 Metric (Hypersim, indoor / ViT-L), q4_k — highest-quality
metric monocular depth in METRES (indoor, max_depth 20). Depth only (no
pose). Use GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-metric-vkitti-small
Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-S), q4_k — metric
monocular depth in METRES (outdoor, max_depth 80). Depth only (no pose). Use
GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
depth-anything-2-metric-vkitti-base
Depth Anything V2 Metric (Virtual KITTI, outdoor / ViT-B), q4_k — metric
monocular depth in METRES (outdoor, max_depth 80). Depth only (no pose). Use
GenerateImage (src -> depth PNG) or the Depth endpoint.
Repository: localaiLicense: apache-2.0
Page 1