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
Live performance in the current season. Closed seasons use recorded snapshots.
Arena Rank
#16 / 21
Textured ELO
906
Geometry ELO
949
Win rate · all modes
32%
119 wins · 254 losses
Total: 373 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Geometry
#15 · 982 ELO
TRELLIS.2 is ranked #16 (949 ELO) while N4D-2.5 currently sits at #15 (982 ELO).
N4D-2.5 holds a 33 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 32% of its judged matches overall, compared to 49% for N4D-2.5.
#17 · 945 ELO
TRELLIS.2 is ranked #16 (949 ELO) while Pixal3D currently sits at #17 (945 ELO).
TRELLIS.2 maintains a 4 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 32% of its judged matches overall, compared to 33% for Pixal3D.
#14 · 991 ELO
TRELLIS.2 is ranked #16 (949 ELO) while Meshy 6 currently sits at #14 (991 ELO).
Meshy 6 holds a 42 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 32% of its judged matches overall, compared to 47% for Meshy 6.
Meshy 6 often returns meshes quicker (3.0 min) while TRELLIS.2 focuses on fidelity.
#18 · 942 ELO
TRELLIS.2 is ranked #16 (949 ELO) while VARCO 3D 2.0 currently sits at #18 (942 ELO).
TRELLIS.2 maintains a 8 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 32% of its judged matches overall, compared to 45% for VARCO 3D 2.0.
VARCO 3D 2.0 often returns meshes quicker (2.5 min) while TRELLIS.2 focuses on fidelity.
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #16 with an arena ELO of 949. It has participated in 373 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 N4D-2.5?
TRELLIS.2 is ranked #16 (949 ELO) while N4D-2.5 currently sits at #15 (982 ELO). N4D-2.5 holds a 33 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 32% of its judged matches overall, compared to 49% for N4D-2.5.