- render_utils_rl.to_glb: fill_holes_num_views 1000 -> 200
- render_utils_rl.to_glb: render_multiview nviews 100 -> 50
- postprocessing_utils.bake_texture: Adam steps 2500 -> 500
- app.py: default simplify 0.95 -> 0.90 (smaller mesh = faster everything)
These should cut GLB bake time from ~60-80s to ~20-30s,
keeping the total @GPU callback well under the 120s limit.
fix(zerogpu): lazy-import nvdiffrast in postprocessing_utils
`import nvdiffrast.torch as dr` at module top level triggered CUDA init
in the main process via the import chain:
app.py
→ trellis.pipelines.NeARImageToRelightable3DPipeline
→ trellis.utils.render_utils_rl
→ trellis.utils.postprocessing_utils
→ import nvdiffrast.torch as dr ← CUDA init here
This caused ZeroGPU's stateless-GPU enforcement to fire even before any
@spaces.GPU callback ran, blocking every GPU callback silently.
Fix: remove top-level import; add `import nvdiffrast.torch as dr` lazily
inside the `mode == 'opt'` branch where it is actually used.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
fix(dino): drop default HF near-assets; use torch.hub facebookresearch/dinov2
- No snapshot_download unless NEAR_AUX_REPO or NEAR_DINO_LOCAL_REPO is set
- Optional NEAR_DINO_TORCH_HUB_REPO overrides github repo id
- Tests: github default path; resolve() without mirror raises
Made-with: Cursor
fix(space): split ZeroGPU cold-start paths and add timing diagnostics
Keep page load and HDRI preview off the heavy model path, separate Hunyuan, NeAR, and gsplat initialization, and add targeted timing logs plus docs/tests so first-request bottlenecks are easier to isolate on Hugging Face Spaces.
Made-with: Cursor
restore: full Space tree + assets (recover from minimal force-push); keep ZeroGPU app.py
- Sync from hf-near mirror for trellis, hy3dshape, assets (LFS), etc.
- README: python_version + quoted short_description for Hub YAML
- requirements: spaces, gradio[oauth,mcp], kaolin find-links; drop --no-build-isolation line for Gradio builder
Made-with: Cursor
