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.
32% win rate · 373 votes across modes
Community rating · out of 5
Community rating
6 ratings · 2 written reviews
Rank, ELO and votes are frozen season results. Cost, runtime and sample outputs are version metadata, not season snapshots.
Arena Rank
#15 / 22
Textured ELO
991
Geometry ELO
1024
Win Rate
47%
478 wins · 546 losses
Total: 1,024 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Textured
#14 · 993 ELO
In March 26, TRELLIS.2 ranked #15 (991 ELO), compared with #14 (993 ELO) for Hi3D v2.0.
Hi3D v2.0 holds a 2 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
During this season, TRELLIS.2 won 47% of its judged matches in this arena, compared with 49% for Hi3D v2.0.
Hi3D v2.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
#16 · 964 ELO
In March 26, TRELLIS.2 ranked #15 (991 ELO), compared with #16 (964 ELO) for Rodin Gen 1.5.
TRELLIS.2 maintains a 27 point lead, which usually translates to steadier community votes.
During this season, TRELLIS.2 won 47% of its judged matches in this arena, compared with 45% for Rodin Gen 1.5.
Rodin Gen 1.5 often returns meshes quicker (2.5 min) while TRELLIS.2 focuses on fidelity.
#13 · 995 ELO
In March 26, TRELLIS.2 ranked #15 (991 ELO), compared with #13 (995 ELO) for Meshy 6.
Meshy 6 holds a 4 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
During this season, TRELLIS.2 won 47% of its judged matches in this arena, compared with 51% for Meshy 6.
Meshy 6 often returns meshes quicker (3.0 min) while TRELLIS.2 focuses on fidelity.
#17 · 961 ELO
In March 26, TRELLIS.2 ranked #15 (991 ELO), compared with #17 (961 ELO) for Alpha3D 4.
TRELLIS.2 maintains a 30 point lead, which usually translates to steadier community votes.
During this season, TRELLIS.2 won 47% of its judged matches in this arena, compared with 46% for Alpha3D 4.
Alpha3D 4 often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
What was the Top 3D AI rank for TRELLIS.2 in March 26?
In March 26, TRELLIS.2 finished at #15 with 991 ELO and 1,024 community votes.
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.
How did TRELLIS.2 compare with Hi3D v2.0 in March 26?
In March 26, TRELLIS.2 ranked #15 (991 ELO), compared with #14 (993 ELO) for Hi3D v2.0. Hi3D v2.0 holds a 2 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. During this season, TRELLIS.2 won 47% of its judged matches in this arena, compared with 49% for Hi3D v2.0. Hi3D v2.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.