Laboratory
Entity that develops or publishes the model and maintains its technical and safety documentation.
Explore the documented models, published evaluations and primary sources associated with this organisation.
Apple family released on November 20 that estimates per-pixel metric depth from photos and video. It combines attention across frames with a decoder per image to preserve edges and temporal consistency. Each size has its own weights; the focal estimator is a separate component.
21 NOV 2026↗ MONOCULAR METRIC DEPTH · 97MApple family released on November 20 that estimates per-pixel metric depth from photos and video. It combines attention across frames with a decoder per image to preserve edges and temporal consistency. Each size has its own weights; the focal estimator is a separate component.
21 NOV 2026↗ MONOCULAR METRIC DEPTH · 334MApple family released on November 20 that estimates per-pixel metric depth from photos and video. It combines attention across frames with a decoder per image to preserve edges and temporal consistency. Each size has its own weights; the focal estimator is a separate component.
21 NOV 2026↗ MONOCULAR METRIC DEPTH · 872MApple family released on November 20 that estimates per-pixel metric depth from photos and video. It combines attention across frames with a decoder per image to preserve edges and temporal consistency. Each size has its own weights; the focal estimator is a separate component.
21 NOV 2026↗ 23.5M-PARAMETER FOCAL LENGTH ESTIMATORApple component with separate weights released on November 20. It estimates unknown focal length for a photo or video frames. It is shared across the four Depth Pro 2 sizes; by itself it does not generate depth maps.
21 NOV 2026↗ TWO-STEP AUTOREGRESSIVE VIDEO DIFFUSIONA 14B-parameter video model derived from Wan2.1-14B, with a public checkpoint dated November 20. It combines a two-step causal generator, pixel decoder and KV-cache refinement to reduce latency. The recipe generates 480p video from text.
21 NOV 2026↗Figures are shown with the context reported by their source. A provider result is not an independent comparison and does not replace your own evaluation.
| Model | Benchmark | Result | Metric |
|---|---|---|---|
| Depth Pro 2 S | Depth Pro 2 B200 1080p BF16 32-frame throughput | 44.8 | fps · higher is better |
| Depth Pro 2 S | Depth Pro 2 B200 1080p BF16 32-frame peak memory | 8.0 | GiB · lower is better |
| Depth Pro 2 B | Depth Pro 2 B200 1080p BF16 32-frame throughput | 23.6 | fps · higher is better |
| Depth Pro 2 B | Depth Pro 2 B200 1080p BF16 32-frame peak memory | 14.0 | GiB · lower is better |
| Depth Pro 2 L | Depth Pro 2 B200 1080p BF16 32-frame throughput | 9.1 | fps · higher is better |
| Depth Pro 2 L | Depth Pro 2 B200 1080p BF16 32-frame peak memory | 21.7 | GiB · lower is better |
| Depth Pro 2 H+ | Depth Pro 2 B200 1080p BF16 32-frame throughput | 5.3 | fps · higher is better |
| Depth Pro 2 H+ | Depth Pro 2 B200 1080p BF16 32-frame peak memory | 29.5 | GiB · lower is better |
An organization, a product, and a model are not the same unit. Inferama separates them to avoid attributing capabilities or commercial terms to the wrong item.
Entity that develops or publishes the model and maintains its technical and safety documentation.
Identifiable version with limits, modalities, and behavior that may change between releases.
API, application, associated cloud, or commercial plan; each channel may have different pricing, retention, and limits.
Every claim must retain the official page consulted and the verification date.