Downloads · 30 days
1.7K
43% of all-time downloads
LocalAI-io/TRELLIS-image-large-GGUF
TRELLIS-image-large-GGUF is a image-to-3d model from LocalAI-io. Use it for the image-to-3d task on the model card, and read the license before you ship it in a product. It is set up for trellis. The card lists the license as mit.
GGUF (f16) conversion of the sparse-structure decoder from microsoft/TRELLIS-image-large for the trellis2cpp / ggml runtime.
Downloads · 30 days
1.7K
43% of all-time downloads
All-time downloads
3.9K
Public
Repo size
147 MB
Likes
2
Public
Click a slice to open those files.
.gguf147 MB · 100%
From the Hugging Face model README
GGUF (f16) conversion of the sparse-structure decoder from
microsoft/TRELLIS-image-large for
the trellis2cpp /
ggml runtime.
The TRELLIS.2 geometry pipeline reuses this TRELLIS-1 sparse-structure decoder to turn the sparse-structure flow output into a 64³ voxel scaffold.
| File | Pipeline stage | Source safetensors |
|---|---|---|
ss_dec_f16.gguf | Sparse-structure decoder → 64³ voxel scaffold | ss_dec_conv3d_16l8_fp16 |
The rest of the TRELLIS.2 pipeline is published at TRELLIS.2-4B-GGUF and dinov3-vitl16-pretrain-lvd1689m-GGUF.
Converted from the upstream fp16 safetensors to GGUF f16 (ggml ftype 1) with
convert_ss_dec_to_gguf.py in the trellis2cpp project. Format conversion only.
MIT, inherited from
microsoft/TRELLIS-image-large.
See LICENSE. Copyright (c) Microsoft Corporation.