Reliquary Depth Anything v2 Large

--- license: cc-by-nc-4.0 library_name: onnx tags: - onnx - reliquary - depth-estimation pipeline_tag: depth-estimation base_model: depth-anything/Depth-Anything-V2-Large --- # reliquary-depth-anything-v2-large Depth Anything V2 Large (ViT-L, ~335M params) ONNX export. Highest-quality tier for Reliquary's Heightmap Generator. ## Source ONNX re-export of the upstream model — original credits to the authors: - **Repo:** [https://github.com/DepthAnything/Depth-Anything-V2](https://github.com/DepthAnything/Depth-Anything-V2) - **Paper:** "Depth Anything V2" — Yang, Kang, Huang, Xu, Feng, Zhao, NeurIPS 2024. - **Pretrained weights origin:** HuggingFace `depth-anything/Depth-Anything-V2-Large` ## License Inherited from upstream — the Large variant is **CC-BY-NC-4.0** (Creative Commons Attribution-NonCommercial). **Non-commercial use only.** Reliquary itself is non-commercial; downstream commercial users must either switch to the Small variant (Apache-2.0) or obtain a commercial license from the upstream authors. ## Usage in Reliquary This model is consumed by [**Reliquary**](https://github.com/MarekBarski/-reliquary), a browser-based PBR texture editor. The ONNX file is loaded via ONNX Runtime Web in the browser — no Python or server-side inference. - **Runtime integration point:** `src/lib/ai/depthAnything.ts (variant picker)` - **Input shape / format:** `[N, 3, H, W]` — RGB normalised, H/W multiples of 14. - **Output shape / format:** `[N, 1, H, W]` — relative depth, larger = closer. ## Files - `depth_anything_v2_large.onnx` — ONNX graph (1.8 MB) - `depth_anything_v2_large.onnx.data` — external weights (1.2 GB, present because the model exceeds the ONNX protobuf size limit) - `README.md` — this file ## Disclaimer This is a re-export from the original PyTorch checkpoint to a browser-deployable ONNX format with dynamic input axes. The model weights, architecture, and training methodology are entirely the work of the original authors cited above. This repo is a hosting convenience for Reliquary's browser-side ML — it does NOT modify the model. For the full conversion pipeline (including version-compat shims for PyTorch 2.6+, opset selection, dynamic-axes details), see Reliquary's [`PYTHON_CONVERSIONS_GUIDE.md`](https://github.com/MarekBarski/-reliquary/blob/main/scripts/PYTHON_CONVERSIONS_GUIDE.md).

Source context: 0 downloads · 1 likes · Pipeline depth-estimation · Library onnx · Repo Wszelkiebro/reliquary-depth-anything-v2-large

Source context: 0 downloads · 0 likes · Pipeline depth-estimation · Library onnx · Repo Wszelkiebro/reliquary-depth-anything-v2-large