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
979
Geometry ELO
915
Win Rate
39%
Arena Votes
Total: 475 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Curated from neighboring ranks
#15 · 986 ELO
TRELLIS.2 is ranked #16 (979 ELO) while Meshy 6 currently sits at #15 (986 ELO).
Meshy 6 holds a 7 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 44% for Meshy 6.
Meshy 6 often returns meshes quicker (3.0 min) while TRELLIS.2 focuses on fidelity.
#17 · 965 ELO
TRELLIS.2 is ranked #16 (979 ELO) while Pixal3D currently sits at #17 (965 ELO).
TRELLIS.2 maintains a 14 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 · 993 ELO
TRELLIS.2 is ranked #16 (979 ELO) while Hi3D v2.1 currently sits at #14 (993 ELO).
Hi3D v2.1 holds a 14 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 55% for Hi3D v2.1.
Hi3D v2.1 often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#18 · 965 ELO
TRELLIS.2 is ranked #16 (979 ELO) while Triverse 3.0 currently sits at #18 (965 ELO).
TRELLIS.2 maintains a 14 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 39% of its judged matches overall, compared to 40% 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 979. It has participated in 475 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 Meshy 6?
TRELLIS.2 is ranked #16 (979 ELO) while Meshy 6 currently sits at #15 (986 ELO). Meshy 6 holds a 7 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 44% for Meshy 6. Meshy 6 often returns meshes quicker (3.0 min) while TRELLIS.2 focuses on fidelity.
Follow TRELLIS (Microsoft) on X (Twitter) for the latest news, updates, and announcements.
Follow @MSFTResearch