Image · Open Source · Commercial Use · ComfyUI · 4K Texture
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.
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.
28% win rate · 549 votes across modes
Community rating · out of 5
Community rating
6 ratings · 2 written reviews
Live performance in the current season. Closed seasons use recorded snapshots.
Arena Rank
#20 / 21
Textured ELO
846
Geometry ELO
935
Win rate · all modes
28%
151 wins · 398 losses
Total: 549 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Textured
#19 · 858 ELO
TRELLIS.2 is ranked #20 (846 ELO) while Wonder3D currently sits at #19 (858 ELO).
Wonder3D holds a 12 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 21% for Wonder3D.
Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#21 · 752 ELO
TRELLIS.2 is ranked #20 (846 ELO) while SAM 3D currently sits at #21 (752 ELO).
TRELLIS.2 maintains a 94 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 12% for SAM 3D.
SAM 3D often returns meshes quicker (55s) while TRELLIS.2 focuses on fidelity.
#18 · 931 ELO
TRELLIS.2 is ranked #20 (846 ELO) while Pixal3D currently sits at #18 (931 ELO).
Pixal3D holds a 85 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 37% for Pixal3D.
#17 · 997 ELO
TRELLIS.2 is ranked #20 (846 ELO) while Triverse 3.0 currently sits at #17 (997 ELO).
Triverse 3.0 holds a 150 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 43% 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 #20 with an arena ELO of 846. It has participated in 549 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 Wonder3D?
TRELLIS.2 is ranked #20 (846 ELO) while Wonder3D currently sits at #19 (858 ELO). Wonder3D holds a 12 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 28% of its judged matches overall, compared to 21% for Wonder3D. Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
