TRELLIS.2 — GGUF

GGUF weights for TRELLIS.2 (image-to-3D), converted for use with trellis.cpp — a standalone C++/GGML runtime (CUDA + Vulkan), and with Lemonade as a GGML media backend.

Source model: https://huggingface.co/microsoft/TRELLIS-image-large License: see the source model.

Files

The full pipeline: dinov3, ss_flow/ss_dec (sparse structure), shape_flow_512/shape_flow_1024/shape_dec, tex_flow_512/tex_flow_1024/tex_dec, and birefnet (optional background removal, CUDA only).

Downloads last month: 999

GGUF

Model size

0.2B params

Architecture

birefnet-swinl

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

Image-to-3D

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support