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.
26% win rate · 378 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
852
Geometry ELO
951
Win rate · all modes
26%
98 wins · 280 losses
Total: 378 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Textured
#19 · 873 ELO
TRELLIS.2 is ranked #20 (852 ELO) while Wonder3D currently sits at #19 (873 ELO).
Wonder3D holds a 21 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 26% of its judged matches overall, compared to 22% for Wonder3D.
Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#21 · 785 ELO
TRELLIS.2 is ranked #20 (852 ELO) while SAM 3D currently sits at #21 (785 ELO).
TRELLIS.2 maintains a 67 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 26% of its judged matches overall, compared to 10% for SAM 3D.
SAM 3D often returns meshes quicker (55s) while TRELLIS.2 focuses on fidelity.
#18 · 926 ELO
TRELLIS.2 is ranked #20 (852 ELO) while Pixal3D currently sits at #18 (926 ELO).
Pixal3D holds a 74 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 26% of its judged matches overall, compared to 36% for Pixal3D.
#17 · 981 ELO
TRELLIS.2 is ranked #20 (852 ELO) while N4D-2.5 currently sits at #17 (981 ELO).
N4D-2.5 holds a 129 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 26% of its judged matches overall, compared to 47% for N4D-2.5.
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #20 with an arena ELO of 852. It has participated in 378 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 (852 ELO) while Wonder3D currently sits at #19 (873 ELO). Wonder3D holds a 21 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 26% of its judged matches overall, compared to 22% for Wonder3D. Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
