Microsoft's 4B-parameter image-to-3D model producing up to 1536³ resolution PBR textured assets. Uses novel O-Voxel representation that handles arbitrary topology including open surfaces and non-manifold geometry. Generates high-fidelity assets in 3-60 seconds depending on resolution. Fully open source under MIT license.
Arena Rank
#16
Overall ELO
972
Geometry ELO
904
Win Rate
39%
Arena Votes
Total: 738 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Curated from neighboring ranks
#15 · 985 ELO
TRELLIS.2 is ranked #16 (972 ELO) while Hi3D v2.0 currently sits at #15 (985 ELO).
Hi3D v2.0 holds a 13 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 39% of its judged matches overall, compared to 52% for Hi3D v2.0.
Hi3D v2.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
#17 · 956 ELO
TRELLIS.2 is ranked #16 (972 ELO) while Pixal3D currently sits at #17 (956 ELO).
TRELLIS.2 maintains a 17 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 39% of its judged matches overall, compared to 40% for Pixal3D.
#14 · 995 ELO
TRELLIS.2 is ranked #16 (972 ELO) while Hi3D v2.1 currently sits at #14 (995 ELO).
Hi3D v2.1 holds a 23 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 39% of its judged matches overall, compared to 53% for Hi3D v2.1.
Hi3D v2.1 often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#18 · 955 ELO
TRELLIS.2 is ranked #16 (972 ELO) while Triverse 3.0 currently sits at #18 (955 ELO).
TRELLIS.2 maintains a 17 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 39% of its judged matches overall, compared to 41% for Triverse 3.0.
Triverse 3.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #16 with an arena ELO of 972. It has participated in 738 community votes so far.
How much does it cost to generate with TRELLIS.2?
TRELLIS.2 reports an average generation cost of $0.42 per test with a typical runtime of 8.0 min.
When should I choose TRELLIS.2 over Hi3D v2.0?
TRELLIS.2 is ranked #16 (972 ELO) while Hi3D v2.0 currently sits at #15 (985 ELO). Hi3D v2.0 holds a 13 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 39% of its judged matches overall, compared to 52% for Hi3D v2.0. Hi3D v2.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
Follow TRELLIS (Microsoft) on X (Twitter) for the latest news, updates, and announcements.
Follow @MSFTResearch