modelbeast/server/operators/trellis_mac
m3ultra b1d37b1629 feat(trellis_mac): close the fal quality gap — RAM-sized bake cap + forced-opaque alpha
Local GLBs were crushed to exactly 94,535 faces (fal ships ~495k) by the
200k laptop mtlbvh guard + o_voxel cleanup, and noisy baked alpha flipped
materials to BLEND (speckle-veil hair, 'broken face'). Neither was the
diffusion — local decode was already 2.2M tris.

- run.py: default TRELLIS2_MAX_BAKE_FACES by node RAM (>=96GB -> 500k,
  else 200k laptop-safe); pass max_bake_faces/alpha_mode/steps/baker
  params through (server forwards only client-sent params — manifest
  defaults are UI-only)
- manifest: new params, quality defaults
- BENCHMARKS.md: 2026-07-22 entry — 500k cap verified crash-free on M3
  Ultra, 351,898-face GLB, bake 7s->14s, farm-path e2e verified

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 19:04:23 +10:00
..
manifest.json feat(trellis_mac): close the fal quality gap — RAM-sized bake cap + forced-opaque alpha 2026-07-22 19:04:23 +10:00
run.py feat(trellis_mac): close the fal quality gap — RAM-sized bake cap + forced-opaque alpha 2026-07-22 19:04:23 +10:00