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.
Upstream
Direct3D-S2 by DreamTech, MIT. Paper, source
Licenses
Code MIT and Apache-2.0, weights MIT. Commercial use

Install

bash
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.

Python
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)
CLI
# 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=0
Settings
from 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 stage

A 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

SettingDefaultMeaning
resolution10241024 (upstream's default) or 512.
steps(50, 30, 15)Steps of the dense, 512 and 1024 stages; one integer sets all three.
guidance7.0Classifier-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

TaskONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
3D generation3D generation to ONNX: not supported3D generation to TorchScript: not supported3D generation to ExecuTorch: not supported3D generation to TensorRT: not supported3D generation to OpenVINO: not supported3D generation to Paddle: not supported3D generation to MNN: not supported3D generation to RKNN: not supported3D generation to Axelera: not supported3D generation to ncnn: not supported3D generation to TFLite: not supported3D generation to CoreML: not supported3D 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
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.

Verified against LibreYOLO v1.8.0. Support tables, checkpoints and benchmark numbers on this page are generated from the released library and the published weights, not written by hand.