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
#14
Overall ELO
945
Geometry ELO
940
Win Rate
44%
Arena Votes
Total: 1,086 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Curated from neighboring ranks
#13 · 977 ELO
TRELLIS.2 is ranked #14 (945 ELO) while Triverse 3.0 currently sits at #13 (977 ELO).
Triverse 3.0 holds a 32 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 44% of its judged matches overall, compared to 48% for Triverse 3.0.
Triverse 3.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
#15 · 937 ELO
TRELLIS.2 is ranked #14 (945 ELO) while Pixal3D currently sits at #15 (937 ELO).
TRELLIS.2 maintains a 8 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 44% of its judged matches overall, compared to 44% for Pixal3D.
#12 · 1003 ELO
TRELLIS.2 is ranked #14 (945 ELO) while N4D-2.5 currently sits at #12 (1003 ELO).
N4D-2.5 holds a 58 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 44% of its judged matches overall, compared to 49% for N4D-2.5.
#16 · 894 ELO
TRELLIS.2 is ranked #14 (945 ELO) while Wonder3D currently sits at #16 (894 ELO).
TRELLIS.2 maintains a 51 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 44% of its judged matches overall, compared to 29% for Wonder3D.
Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #14 with an arena ELO of 945. It has participated in 1,086 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 Triverse 3.0?
TRELLIS.2 is ranked #14 (945 ELO) while Triverse 3.0 currently sits at #13 (977 ELO). Triverse 3.0 holds a 32 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 44% of its judged matches overall, compared to 48% for Triverse 3.0. Triverse 3.0 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