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.
38% win rate · 21 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
#12 / 21
Textured ELO
1000
Geometry ELO
981
Win rate · all modes
38%
8 wins · 13 losses
Total: 21 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Textured
#11 · 1005 ELO
TRELLIS.2 is ranked #12 (1000 ELO) while Rodin Gen 2.5 currently sits at #11 (1005 ELO).
Rodin Gen 2.5 holds a 5 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 38% of its judged matches overall, compared to 50% for Rodin Gen 2.5.
Rodin Gen 2.5 often returns meshes quicker (4.5 min) while TRELLIS.2 focuses on fidelity.
#13 · 992 ELO
TRELLIS.2 is ranked #12 (1000 ELO) while Hi3D v2.0 currently sits at #13 (992 ELO).
TRELLIS.2 maintains a 8 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 38% of its judged matches overall, compared to 45% for Hi3D v2.0.
Hi3D v2.0 often returns meshes quicker (7.0 min) while TRELLIS.2 focuses on fidelity.
#10 · 1005 ELO
TRELLIS.2 is ranked #12 (1000 ELO) while Wonder3D currently sits at #10 (1005 ELO).
Wonder3D holds a 5 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 38% of its judged matches overall, compared to 24% for Wonder3D.
Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#14 · 991 ELO
TRELLIS.2 is ranked #12 (1000 ELO) while YVO3D 2.5 currently sits at #14 (991 ELO).
TRELLIS.2 maintains a 9 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 38% of its judged matches overall, compared to 50% for YVO3D 2.5.
YVO3D 2.5 often returns meshes quicker (5.0 min) while TRELLIS.2 focuses on fidelity.
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #12 with an arena ELO of 1000. It has participated in 21 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 Rodin Gen 2.5?
TRELLIS.2 is ranked #12 (1000 ELO) while Rodin Gen 2.5 currently sits at #11 (1005 ELO). Rodin Gen 2.5 holds a 5 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 38% of its judged matches overall, compared to 50% for Rodin Gen 2.5. Rodin Gen 2.5 often returns meshes quicker (4.5 min) while TRELLIS.2 focuses on fidelity.
