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.
Follow TRELLIS (Microsoft) on X (Twitter) for the latest news, updates, and announcements.
Follow @MSFTResearch
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 · 634 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
#19 / 21
Textured ELO
862
Geometry ELO
929
Win rate · all modes
28%
180 wins · 454 losses
Total: 634 votes
Average Generation Cost
$0.42
Typical runtime: 8.0 min
Nearby ranks in Textured
#18 · 918 ELO
TRELLIS.2 is ranked #19 (862 ELO) while Pixal3D currently sits at #18 (918 ELO).
Pixal3D holds a 56 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 36% for Pixal3D.
#20 · 852 ELO
TRELLIS.2 is ranked #19 (862 ELO) while Wonder3D currently sits at #20 (852 ELO).
TRELLIS.2 maintains a 10 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 22% for Wonder3D.
Wonder3D often returns meshes quicker (4.0 min) while TRELLIS.2 focuses on fidelity.
#17 · 990 ELO
TRELLIS.2 is ranked #19 (862 ELO) while N4D-2.5 currently sits at #17 (990 ELO).
N4D-2.5 holds a 128 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 48% for N4D-2.5.
#21 · 733 ELO
TRELLIS.2 is ranked #19 (862 ELO) while SAM 3D currently sits at #21 (733 ELO).
TRELLIS.2 maintains a 129 point lead, which usually translates to steadier community votes.
TRELLIS.2 wins about 28% of its judged matches overall, compared to 12% for SAM 3D.
SAM 3D often returns meshes quicker (55s) while TRELLIS.2 focuses on fidelity.
What is the current Top 3D AI rank for TRELLIS.2?
TRELLIS.2 is sitting at #19 with an arena ELO of 862. It has participated in 634 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 Pixal3D?
TRELLIS.2 is ranked #19 (862 ELO) while Pixal3D currently sits at #18 (918 ELO). Pixal3D holds a 56 point advantage, so TRELLIS.2 fans tend to focus on prompts that highlight its strengths. TRELLIS.2 wins about 28% of its judged matches overall, compared to 36% for Pixal3D.
