SAVRN
Search Contact SAVRN

Open-weight model · Image to 3d

TRELLIS-image-large

by Microsoft microsoft/TRELLIS-image-large

The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper Structured 3D Latents for Scalable and Versatile 3D Generation.

Parameters
Context
Weights3.3 GB
Licensemit
AccessOpen weights
Monthly Downloads2.8M

SAVRN's Notes on TRELLIS-image-large

Microsoft released this image-conditioned TRELLIS checkpoint on December 2, 2024, and it now draws 2.76 million downloads a month. It turns one picture into 3D output by the method in arXiv:2412.01506. The weights come to 3.3 GB across 19 files under the trellis library, with no per-precision memory figures or host price on our Index. At 3.3 GB you are not shopping for memory; you are sizing for generations per hour.

MIT asks for the copyright notice and the permission notice, and it allows commercial use, modification and redistribution, so the checkpoint can sit inside a commercial pipeline with those notices as the whole obligation. What the record lacks matters: no parameter count, no artifact formats, no reported evaluations, and the paper is the only relation listed. December 6, 2024 is the last time the weights changed; run your own product images through it before you commit hardware.

Model Card

By Microsoft, published under mit, revision 25e0d31ffbeb.

The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper Structured 3D Latents for Scalable and Versatile 3D Generation.

Read Microsoft's full model card

The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper Structured 3D Latents for Scalable and Versatile 3D Generation.

Project page: https://trellis3d.github.io/

Code: https://github.com/Microsoft/TRELLIS

Identity and Version

Repository
microsoft/TRELLIS-image-large
Publisher
Microsoft
Task
Image to 3d
Modality
Other
Library
trellis
Parameters
Not stated by the source
Languages
en
Revision
25e0d31ffbebe4b5a97464dd851910efc3002d96
First published
2024-12-02
Last updated
2024-12-06

Files and Weights

19 files, 3.3 GB in total. The weights are 8 files totalling 3.3 GB in safetensors.

Weights8 files · 3.3 GB
Configuration9 files · 5.2 KB
Documentation1 file · 464 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.safetensorsWeights171.5 MB 38c84bcef5ce
ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.safetensorsWeights181.9 MB 3e87aba94b57
ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.safetensorsWeights171.5 MB 737da6578d01
ckpts/slat_enc_swin8_B_64l8_fp16.safetensorsWeights173.2 MB 21dceac6bee9
ckpts/slat_flow_img_dit_L_64l8p2_fp16.safetensorsWeights1.2 GB 693fb2a58ad4
ckpts/ss_dec_conv3d_16l8_fp16.safetensorsWeights147.6 MB 1c76d4a40519
ckpts/ss_enc_conv3d_16l8_fp16.safetensorsWeights119.1 MB 107874eeaa0f
ckpts/ss_flow_img_dit_L_16l8_fp16.safetensorsWeights1.1 GB 96dc6bfd4136
ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.jsonConfiguration843 B
ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.jsonConfiguration372 B
ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.jsonConfiguration396 B
ckpts/slat_enc_swin8_B_64l8_fp16.jsonConfiguration321 B
ckpts/slat_flow_img_dit_L_64l8p2_fp16.jsonConfiguration442 B
ckpts/ss_dec_conv3d_16l8_fp16.jsonConfiguration245 B
ckpts/ss_enc_conv3d_16l8_fp16.jsonConfiguration244 B
ckpts/ss_flow_img_dit_L_16l8_fp16.jsonConfiguration385 B
pipeline.jsonConfiguration2.0 KB
README.mdDocumentation464 B
.gitattributesRepository1.5 KB

License and Download

License
mit
Access
Open weights, no gate
Download size
3.3 GB
Download from Microsoft

Released by Microsoft through its official repository on Hugging Face. Read the license.

Built From

  • Described by arXiv:2412.01506

Memory Requirements

PrecisionWeights in memory
As published3.3 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About TRELLIS-image-large

Can I use TRELLIS-image-large commercially?

Yes. TRELLIS-image-large is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Similar Models

Model · Image to 3d

TRELLIS.2-4B

Microsoft

TRELLIS.2 is a state-of-the-art large 3D generative model designed for high-fidelity image-to-3D generation. It leverages a novel "field-free" sparse voxel structure termed O-Voxel and a large-scale flow-matching transformer (4 Billion parameters). Unlike previous methods that rely on iso-surface fields (e.g., SDF, Flexicubes) which struggle with open surfaces or non-manifold geometry, TRELLIS can reconstruct and generate arbitrary 3D assets with complex topologies, sharp features, and full Physical-Based Rendering (PBR) materials—including transparency/translucency. - The CUDA Toolkit is needed to compile certain packages. Recommended version is 12.4. - Conda is recommended for managing…

Open weights mit trellis2

Model · Image to 3d

matchanu-1.5

PYGRASSREAL

Matchanu 1.5 is PyGrassReal's generative 3D asset engine capable of synthesizing production-ready watertight 3D meshes (STL, OBJ, PLY) and real-time 3D Gaussian Splats from text descriptions or single 2D concept images. Designed for Industrial Prototyping (3D Printing), Game & AR/VR Assets, and Architectural Elements, Matchanu 1.5 generates clean topology, UV unwrappings, and volume-accurate meshes without the point cloud artifacts common to open-source prototypes. 1. Prompt & Image-to-3D Mesh: - Converts single-view product photos or text prompts into clean, manifold 3D meshes ready for Blender, Rhino, Maya, or Unreal Engine. 2. 3D Printing Ready (Watertight Topology): - Automatically…

Open weights other