Add model-card YAML metadata (license/pipeline_tag/base_model) + fix links

README.md

@@ -1,3 +1,17 @@
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- coreai
+- core-ml
+- apple-silicon
+- gaussian-splatting
+- image-to-3d
+- 3d-generation
+base_model:
+- VAST-AI/TripoSplat
+---
+
 # TripoSplat → Core AI (zoo's first 3D)
 
 [VAST-AI/TripoSplat](https://github.com/VAST-AI-Research/TripoSplat) — **single image → 3D Gaussian
@@ -7,24 +21,27 @@ viewer (e.g. Apple RealityKit on visionOS, or MetalSplatter on iOS/macOS).
 Pure-PyTorch pipeline (no diffusers/CUDA kernels): bg-removal → DINOv3 ViT-H encode + Flux2-VAE encode
 → 20-step flow-matching DiT denoiser → octree probability sampler → Gaussian decoder → splats.
 
+**This repo holds the Core AI `.aimodel` bundles** (each is a directory). Conversion + runner scripts
+live in the [coreai-models-community](https://huggingface.co/mlboydaisuke) zoo (`conversion/triposplat/`).
+
 ## What runs on Core AI
 
-5 neural nets converted (each gated converted-vs-eager **cos = 1.000000**, fp16):
+5 neural nets converted (each gated converted-vs-eager **cos = 1.000000**):
 
-| net | shape | bundle |
-|---|---|---|
-| DINOv3 ViT-H encoder | (1,3,1024,1024)→(1,4101,1280) | `dinov3` |
-| Flux2-VAE encoder | (1,3,1024,1024)→(1,4096,128) | `vae` |
-| DiT denoiser (one step) | latent(1,8192,16)+cam(1,1,5)+t+feat1(1,4101,1280)+feat2(1,4101,128)→latent,cam | `dit` |
-| Octree probability decoder | x(1,8192,3)+l(1,)+cond(1,8192,16)→logits(1,8192,8) | `octree` |
-| Decode (gs + build_gaussians + .ply activations, baked) | points(1,8192,3)+cond(1,8192,16)→(262144,14) | `decode` |
+| net | shape | bundle | dtype |
+|---|---|---|---|
+| DINOv3 ViT-H encoder | (1,3,1024,1024)→(1,4101,1280) | `dinov3_fp16.aimodel` | fp16 |
+| Flux2-VAE encoder | (1,3,1024,1024)→(1,4096,128) | `vae_fp16.aimodel` | fp16 |
+| DiT denoiser (one step) | latent(1,8192,16)+cam(1,1,5)+t+feat1(1,4101,1280)+feat2(1,4101,128)→latent,cam | `dit_fp16.aimodel` | fp16 |
+| Octree probability decoder | x(1,8192,3)+l(1,)+cond(1,8192,16)→logits(1,8192,8) | `octree_fp32.aimodel` | fp32 |
+| Decode (gs + build_gaussians + .ply activations, baked) | points(1,8192,3)+cond(1,8192,16)→(262144,14) | `decode_fp32.aimodel` | fp32 |
 
 The flow-matching sampler (`FlowEulerCfgSampler`) and the octree `sample_probs` systematic resampling
 stay **host-side** (data-dependent control flow). Scripts: `_conv_*.py` convert+gate each net;
 `_conv_fp16.py` makes the half-size fp16 bundles; `_conv_decode.py` bakes build_gaussians + the
 Gaussian `.ply`-activation math into one net so the runner just writes raw floats.
 
-## model.py patches (the reusable contribution — see ../../knowledge/conversion-guide.md)
+## model.py patches (the reusable contribution — see the zoo's conversion guide)
 
 coreai-torch 0.4.0 needed six edits to VAST's `model.py`; all are general gotchas:
 
@@ -46,9 +63,9 @@ artifact). Octree decoder: int64 `l` (resolution) input → CoreAIError 3 at run
 ## Running it
 
 - **Mac**: `_run_coreai.py` (or `app_backend.py --input <img>`) loads the bundles via coreai.runtime
-  (`SpecializationOptions.default()` = GPU; ~1 min/gen at 20 steps, full quality). End-to-end latent
-  gate vs torch-DiT: **cos 0.999999**.
-- **Mac app / iPhone client**: `apps/` — `TripoSplatMac` (standalone) and `TripoSplatPhone`
+  (`SpecializationOptions.default()` = GPU; ~2 min/gen at 20 steps on Apple silicon, full quality).
+  End-to-end latent gate vs torch-DiT: **cos 0.999999**.
+- **Mac app / iPhone client**: `TripoSplatMac` (standalone) and `TripoSplatPhone`
   (capture on iPhone → Mac server `server.py` → view splats in MetalSplatter / RealityKit).
 
 ## On-device note