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.
Model source
Source description
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: License: see the source model.
Sources
1 sourceVerified Oct 10
Model artifacts
30 artifactsSource excerpts
3 excerpts--- license: other tags: - gguf - ggml - image-to-3d - trellis --- # TRELLIS.2 — GGUF GGUF weights for **TRELLIS.2 (image-to-3D)**, converted for use with [trellis.cpp](https://github.com/pwilkin/trellis.cpp) — a standalone C++/GGML runtime (CUDA + Vulkan), and with [Lemonade](https://github.com/lemonade-sdk/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).
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).
gguf · 842 MB · SHA-256 10c5dd4dcac9…bbc1 · Hugging Face
Source context: 120416 downloads · 15 likes · Pipeline image-to-3d · Library trellis · Repo ilintar/trellis2-gguf
Source context: 23294 downloads · 8 likes · Pipeline image-to-3d · Library trellis · Repo ilintar/trellis2-gguf