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 / 25
Textured ELO
980
Geometry ELO
997
Win Rate
54%
247 wins · 212 losses
Total: 459 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Geometry
#14 · 998 ELO
In Jun 26, TRELLIS.2 ranked #15 (997 ELO), compared with #14 (998 ELO) for Alpha3D 4.
Alpha3D 4 holds a 1 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
During this season, TRELLIS.2 won 54% of its judged matches in this arena, compared with 50% for Alpha3D 4.
Alpha3D 4 often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#16 · 993 ELO
In Jun 26, TRELLIS.2 ranked #15 (997 ELO), compared with #16 (993 ELO) for Triverse 3.0.
TRELLIS.2 maintains a 4 point lead, which usually translates to steadier community votes.
During this season, TRELLIS.2 won 54% of its judged matches in this arena, compared with 44% for Triverse 3.0.
Triverse 3.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
#13 · 1008 ELO
In Jun 26, TRELLIS.2 ranked #15 (997 ELO), compared with #13 (1008 ELO) for Pixal3D.
Pixal3D holds a 11 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
During this season, TRELLIS.2 won 54% of its judged matches in this arena, compared with 54% for Pixal3D.
#17 · 990 ELO
In Jun 26, TRELLIS.2 ranked #15 (997 ELO), compared with #17 (990 ELO) for Hi3D v2.1.
TRELLIS.2 maintains a 7 point lead, which usually translates to steadier community votes.
During this season, TRELLIS.2 won 54% of its judged matches in this arena, compared with 49% for Hi3D v2.1.
Hi3D v2.1 often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
What was the Top 3D AI rank for TRELLIS.2 in Jun 26?
In Jun 26, TRELLIS.2 finished at #15 with 997 ELO and 459 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 Alpha3D 4 in Jun 26?
In Jun 26, TRELLIS.2 ranked #15 (997 ELO), compared with #14 (998 ELO) for Alpha3D 4. Alpha3D 4 holds a 1 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. During this season, TRELLIS.2 won 54% of its judged matches in this arena, compared with 50% for Alpha3D 4. Alpha3D 4 often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.