TRELLIS.2: state-of-the-art large 3D generative model (4B)

Summary

Native and Compact Structured Latents for 3D Generation trellis2.mp4 (Compressed version due to GitHub size limits. See the full-quality video on our project page!) TRELLIS.2 is a state-of-the-art large 3D generative model (4B parameters) designed for high-fidelity image-to-3D generation. It leverages a novel "field-free" sparse voxel structure termed O-Voxel to reconstruct and generate arbitrary 3D assets with complex topologies, sharp features, and full PBR materials. ✨ Features 1. High Quality, Resolution & Efficiency Our 4B-parameter model generates high-resolution fully textured assets with exceptional fidelity and efficiency using vanilla DiTs. It utilizes a Sparse 3D VAE with 16× spatial downsampling to encode assets into a compact latent space. Resolution Total Time* Breakdown (Shape + Mat) 512³ ~3s 2s + 1s 1024³ ~17s 10s + 7s 1536³ ~60s 35s + 25s *Tested on NVIDIA H100 GPU. 2. Arbitrary Topology Handling The O-Voxel representation breaks the limits of iso-surface fields. It robustly handles complex structures without lossy conversion: ✅ Open Surfaces (e.g., clothing, leaves) (e.g., clothing, leaves) ✅ Non-manifold Geometry ✅ Internal Enclosed Structures 3. Rich Texture Modeling Beyond basic colors, TRELLIS.2 models arbitrary surface attributes including Base Color, Roughness, Metallic, and Opacity, enabling photorealistic rendering and transparency support. 4. Minimalist Processing Data processing is streamlined for instant conversions that are fully rendering-free and optimization-free. < 10s (Single CPU): Textured Mesh → O-Voxel (Single CPU): Textured Mesh → O-Voxel < 100ms (CUDA): O-Voxel → Textured Mesh 🗺️ Roadmap Paper release Paper release Release image-to-3D inference code Release image-to-3D inference code Release pretrained checkpoints (4B) Release pretrained checkpoints (4B) Hugging Face Spaces demo Hugging Face Spaces demo Release shape-conditioned texture generation inference code (Current schdule: before 12/24/2025) Release shape-conditioned te...