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 · 618 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
#14 / 24
Textured ELO
990
Geometry ELO
1009
Win Rate
51%
967 wins · 931 losses
Total: 1,898 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Textured
#13 · 998 ELO
In January 26, TRELLIS.2 ranked #14 (990 ELO), compared with #13 (998 ELO) for VARCO 3D 1.0.
VARCO 3D 1.0 holds a 8 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
During this season, TRELLIS.2 won 51% of its judged matches in this arena, compared with 52% for VARCO 3D 1.0.
VARCO 3D 1.0 often returns meshes quicker (2.0 min) while TRELLIS.2 focuses on fidelity.
#15 · 981 ELO
In January 26, TRELLIS.2 ranked #14 (990 ELO), compared with #15 (981 ELO) for Rodin Gen 1.5.
TRELLIS.2 maintains a 9 point lead, which usually translates to steadier community votes.
During this season, TRELLIS.2 won 51% 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.
#12 · 1018 ELO
In January 26, TRELLIS.2 ranked #14 (990 ELO), compared with #12 (1018 ELO) for Hunyuan 3D v2.5.
Hunyuan 3D v2.5 holds a 28 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
During this season, TRELLIS.2 won 51% of its judged matches in this arena, compared with 55% for Hunyuan 3D v2.5.
Hunyuan 3D v2.5 often returns meshes quicker (3.0 min) while TRELLIS.2 focuses on fidelity.
#16 · 975 ELO
In January 26, TRELLIS.2 ranked #14 (990 ELO), compared with #16 (975 ELO) for Tripo AI v2.5.
TRELLIS.2 maintains a 15 point lead, which usually translates to steadier community votes.
During this season, TRELLIS.2 won 51% of its judged matches in this arena, compared with 50% for Tripo AI v2.5.
Tripo AI v2.5 often returns meshes quicker (2.0 min) while TRELLIS.2 focuses on fidelity.
What was the Top 3D AI rank for TRELLIS.2 in January 26?
In January 26, TRELLIS.2 finished at #14 with 990 ELO and 1,898 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 VARCO 3D 1.0 in January 26?
In January 26, TRELLIS.2 ranked #14 (990 ELO), compared with #13 (998 ELO) for VARCO 3D 1.0. VARCO 3D 1.0 holds a 8 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. During this season, TRELLIS.2 won 51% of its judged matches in this arena, compared with 52% for VARCO 3D 1.0. VARCO 3D 1.0 often returns meshes quicker (2.0 min) while TRELLIS.2 focuses on fidelity.
