Direct3D-S2
Direct3D-S2 is DreamTech's image-to-3D model. It generates a signed distance field on sparse voxels, first at 512^3 and then at 1024^3, and returns the object as a mesh. Upstream needs CUDA-only extensions; LibreYOLO runs the same weights in plain PyTorch through the LibreGen factory.
- Tasks
- 3d generation
- Sizes
- v11 at 518 px
- Install
pip install "libreyolo[gen]"- Support tier
- Sibling tier, since v1.8.0. A separate product surface with its own factory and contract.
- Licenses
- Code MIT and Apache-2.0, weights MIT. Commercial use
Install
pip install "libreyolo[gen]"The extra brings diffusers, transformers (DINOv2 encoder) and
scikit-image (marching cubes).
Predict
Nothing is gated and no login is needed. Weights download on first use at pinned revisions.
from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("direct3d-s2") # weights download on first useresult = model(SAMPLE_IMAGE, seed=0) result.save("object.obj")m = result.meshesprint(m.vertices[0].shape, m.faces[0].shape)# Saves the object as .obj under runs/generate/predict.libreyolo generate source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/guggenheim-bilbao.jpg model=direct3d-s2 seed=0from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("direct3d-s2")result = model(SAMPLE_IMAGE, resolution=512) # stops after the first passresult = model(SAMPLE_IMAGE, steps=(25, 15, 8)) # fewer steps per stageA dense flow transformer finds the occupied 64^3 voxels, a sparse flow transformer with spatial sparse attention denoises a latent on them, and a sparse decoder turns it into a signed distance field at 512^3. A second pass repeats this at 1024^3. The mesh is the field's zero crossing, from marching cubes. Upstream runs on CUDA only (torchsparse, flash-attn, Triton kernels, a CUDA voxeliser); LibreYOLO replaces them with PyTorch operations and keeps the parameter names, so the released checkpoints load unchanged on CUDA, Apple MPS and CPU.
A seed gives the same object; on CUDA the starting noise equals upstream's
for torch.manual_seed(seed). result.meshes holds vertices (V, 3), z-up
in [-0.5, 0.5]^3, and faces (F, 3). Upstream's optional remeshing and
hole filling are not included (they depend on GPL tools), so meshes come as
marching cubes returns them.
It is slow in plain PyTorch: on an RTX A6000 the library measured about 18
minutes and 23 GB of GPU memory for one object at 1024^3, where upstream's
CUDA kernels take 2.5 minutes. resolution=512 stops after the first pass.
Settings
| Setting | Default | Meaning |
|---|---|---|
resolution | 1024 | 1024 (upstream's default) or 512. |
steps | (50, 30, 15) | Steps of the dense, 512 and 1024 stages; one integer sets all three. |
guidance | 7.0 | Classifier-free guidance of all three stages. |
Variants
One checkpoint, v11 (Direct3D-S2 v1.1): 2.0B parameters in eight networks,
about 4.2 GB, plus 1.2 GB for DINOv2 ViT-L/14 and 0.4 GB for BiRefNet.
Export
| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3D generation | 3D generation to ONNX: not supported | 3D generation to TorchScript: not supported | 3D generation to ExecuTorch: not supported | 3D generation to TensorRT: not supported | 3D generation to OpenVINO: not supported | 3D generation to Paddle: not supported | 3D generation to MNN: not supported | 3D generation to RKNN: not supported | 3D generation to Axelera: not supported | 3D generation to ncnn: not supported | 3D generation to TFLite: not supported | 3D generation to CoreML: not supported | 3D generation to Core AI: not supported |
Export is not implemented for LibreGen 3D families. export(), train() and
val() raise NotImplementedError (ADR 0031 in the library).
Licensing
Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.
This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.
- Original work
- Direct3D-S2, DreamTech
- Upstream license
- MIT
- Upstream source
- github.com/DreamTechAI/Direct3D-S2
- LibreYOLO code
- MIT
- Weights
- MIT, republished at huggingface.co/LibreYOLO
- Interpretation
- MIT is a permissive license, so the code and weights can be used in commercial and closed-source products; the only obligation is to keep the copyright and license notice with copies. LibreYOLO's adapter is MIT; the flow transformers, SDF VAE decoders, refiners and spatial sparse attention it adapts from Direct3D-S2 keep MIT, with the attention following native-sparse-attention-triton (Apache-2.0) and the transformer modules TRELLIS's (MIT), noted in libreyolo/models/gen/direct3d_s2/NOTICE. Upstream's hole filling and remeshing, which need GPL-licensed pymeshfix and python-igraph, are not used. The wushuang98/Direct3D-S2 v1.1 weights (MIT) are redistributed unchanged as LibreYOLO/LibreDirect3DS2v11; the BiRefNet weights (MIT) come from LibreYOLO/LibreTRELLISl and the DINOv2 encoder, facebook/dinov2-with-registers-large (Apache-2.0), from Meta. All are pinned and none is gated.
Direct3D-S2 is by DreamTech
(DreamTechAI/Direct3D-S2). Code
and the wushuang98/Direct3D-S2 v1.1 weights are MIT, so commercial use is
fine with the notice kept. LibreYOLO redistributes the weights unchanged as
LibreYOLO/LibreDirect3DS2v11. BiRefNet (MIT) comes from LibreYOLO/LibreTRELLISl
and the DINOv2 encoder, facebook/dinov2-with-registers-large (Apache-2.0),
from Meta. Upstream's GPL pymeshfix and python-igraph are not used.
Citation
@article{wu2025direct3ds2gigascale3dgeneration,
title={Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention},
author={Shuang Wu and Youtian Lin and Feihu Zhang and Yifei Zeng and Yikang Yang and Yajie Bao and Jiachen Qian and Siyu Zhu and Philip Torr and Xun Cao and Yao Yao},
journal={arXiv preprint arXiv:2505.17412},
year={2025}
}Copied from the authors' citation block at github.com/DreamTechAI/Direct3D-S2#-citation.