# TRELLIS-image-large by Microsoft: Open-Weight Model Source: https://savrn.com/models/trellis-image-large Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## 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. SAVRN Research, 2026-09-18 ## 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](https://huggingface.co/papers/2412.01506). 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 | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.safetensors | Weights | 171.5 MB | 38c84bcef5ce | | ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.safetensors | Weights | 181.9 MB | 3e87aba94b57 | | ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.safetensors | Weights | 171.5 MB | 737da6578d01 | | ckpts/slat_enc_swin8_B_64l8_fp16.safetensors | Weights | 173.2 MB | 21dceac6bee9 | | ckpts/slat_flow_img_dit_L_64l8p2_fp16.safetensors | Weights | 1.2 GB | 693fb2a58ad4 | | ckpts/ss_dec_conv3d_16l8_fp16.safetensors | Weights | 147.6 MB | 1c76d4a40519 | | ckpts/ss_enc_conv3d_16l8_fp16.safetensors | Weights | 119.1 MB | 107874eeaa0f | | ckpts/ss_flow_img_dit_L_16l8_fp16.safetensors | Weights | 1.1 GB | 96dc6bfd4136 | | ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.json | Configuration | 843 B | — | | ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.json | Configuration | 372 B | — | | ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.json | Configuration | 396 B | — | | ckpts/slat_enc_swin8_B_64l8_fp16.json | Configuration | 321 B | — | | ckpts/slat_flow_img_dit_L_64l8p2_fp16.json | Configuration | 442 B | — | | ckpts/ss_dec_conv3d_16l8_fp16.json | Configuration | 245 B | — | | ckpts/ss_enc_conv3d_16l8_fp16.json | Configuration | 244 B | — | | ckpts/ss_flow_img_dit_L_16l8_fp16.json | Configuration | 385 B | — | | pipeline.json | Configuration | 2.0 KB | — | | README.md | Documentation | 464 B | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License mit Access Open weights, no gate Download size 3.3 GB [Download from Microsoft](https://huggingface.co/microsoft/TRELLIS-image-large) Released by Microsoft through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Described by arXiv:2412.01506 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 3.3 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](https://savrn.com/models/trellis-2-4b) [Microsoft](https://savrn.com/model-publishers/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 [View model](https://savrn.com/models/trellis-2-4b) Model · Image to 3d ### [QtMeshEditor-models](https://savrn.com/models/qtmesheditor-models) [Fernando Tonon](https://savrn.com/model-publishers/fernandotonon) The models used by QtMeshEditor's AI-assisted authoring features. This repo is what the app downloads from at runtime (each model on first use, then it runs locally/offline). Licenses are per model — see the table and each dedicated repo. The dedicated repos carry the full model cards (I/O contracts, provenance, reproduction scripts) for anyone who wants the converted weights standalone. 1x-PBRifyNormalV3.onnx, 1x-PBRifyRoughnessV2.onnx, 1x-PBRifyHeight.onnx generate tangent-space normal / roughness / height maps from a single albedo texture. ONNX re-exports of the CC0 SPAN models from Kim2091/PBRifyRemix — all RealESRGANx2plus.onnx, RealESRGANx4plus.onnx — 2×/4× super-resolution. ONNX… Open weights other onnx [View model](https://savrn.com/models/qtmesheditor-models) Model · Image to 3d ### [matchanu-1.5](https://savrn.com/models/matchanu-1-5) [PGR](https://savrn.com/model-publishers/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 [View model](https://savrn.com/models/matchanu-1-5) Model · Image to 3d ### [ABot-Recon-Axera](https://savrn.com/models/abot-recon-axera) [AXERA](https://savrn.com/model-publishers/axera-tech) ABot-Recon(流式前馈三维重建:视频 → 相机位姿 + 世界坐标点云 + 置信度)编译到 Axera AX650N NPU 的模型文件。 模型与算法来自原作者:amap-cvlab/ABot-Recon(主页 ),本仓库只做 Axera NPU 的格式转换。 代码与使用说明:https://github.com/AXERA-TECH/ABot-Recon-Axera 三个 axmodel 由 pulsar2 编译,芯片 AX650N,支持 AXCL PCIe 卡和 AX650 片上两种运行方式。 打开 http://:8011。Python 调用: 片上运行需要板子 CMM 预留 ≥ 6 GB。 这些权重转换自 ABot-Recon 发布的权重,后者派生自 Pi3;再分发须保留对 Pi3 与 ABot-Recon 的署名与 CC BY-NC 4.0 条款。商业使用需另行获得书面授权。 - presentvalid 封顶 8(应为 11),长序列有轻微漂移。 Open weights cc-by-nc-4.0 [View model](https://savrn.com/models/abot-recon-axera) Model · Image to 3d ### [MeshAxiom-Base](https://savrn.com/models/meshaxiom-base) [Alaya Lab](https://savrn.com/model-publishers/alayalab) Open weights meshaxiom [View model](https://savrn.com/models/meshaxiom-base) Model · Image to 3d ### [etri_recon](https://savrn.com/models/etri-recon) [Jiwoo Chung](https://savrn.com/model-publishers/wldn0202) Open weights other diffusers [View model](https://savrn.com/models/etri-recon) ## Microsoft [All models and datasets](https://savrn.com/model-publishers/microsoft) ## Versions - [25e0d31ffbeb](https://savrn.com/models/trellis-image-large/versions/25e0d31ffbeb) · current 2026-10-25 ## Explore More - [All image to 3d models](https://savrn.com/models/tasks/image-to-3d) - [All models under mit](https://savrn.com/models/licenses/mit) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Microsoft website](https://github.com/microsoft) - [Hugging Face record](https://huggingface.co/microsoft/TRELLIS-image-large) - [How the hub is built](https://savrn.com/model-hub/methodology)