TRELLIS

TRELLIS is Microsoft's open image-to-3D model. It builds the object as a sparse voxel structure first, then 32 Gaussians per occupied voxel. Upstream needs CUDA-only extensions; LibreYOLO runs the same weights in plain PyTorch through the LibreGen factory.

작업
3d generation
크기
l at 518 px
설치
pip install "libreyolo[gen]"
지원 티어
별도 티어, v1.8.0부터 지원. 자체 팩토리와 계약을 갖춘 별도의 제품 영역입니다.
업스트림
Microsoft Research의 TRELLIS, MIT. 논문, 소스
라이선스
코드 MIT, 가중치 MIT. 상업적 사용

Install

bash
pip install "libreyolo[gen]"

The extra brings transformers, which loads the DINOv2 image encoder.

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("trellis")         # weights download on first useresult = model(SAMPLE_IMAGE, seed=0) result.save("object.ply")           # standard 3DGS layoutresult.save("object.splat")         # compact web formatprint(len(result.gaussians))        # follows the object, not a knob
CLI
# Saves the object as .ply under runs/generate/predict.libreyolo generate source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/guggenheim-bilbao.jpg model=trellis seed=0
Settings
from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("trellis")result = model(SAMPLE_IMAGE, steps=12)          # faster samplingresult = model(SAMPLE_IMAGE, guidance=3.0, margin=1.3)

A dense flow transformer denoises the object's occupancy at 16^3, a 3D CNN decodes it to the active voxels of a 64^3 grid, a sparse flow transformer denoises a structured latent on those voxels, and a sparse transformer turns each voxel into 32 Gaussians. Both flow stages read DINOv2 tokens of the 518 px input. The number of Gaussians therefore follows the object (often 200,000 to 600,000).

Upstream's sparse convolutions (spconv) and attention (xformers or flash-attn) run on CUDA only. LibreYOLO replaces them with PyTorch operations and keeps the parameter names, so the released weights load unchanged on NVIDIA GPUs, Apple silicon and CPU. Noise is drawn on the CPU as upstream does, so a seed gives the same object on every device.

The output is result.gaussians, the same payload as Speridlabs Idol: xyz, scales, rotations, opacities, sh, colors, seed and params, z-up in [-0.5, 0.5]^3. Background removal runs on LibreYOLO's BiRefNet port.

Settings

SettingDefaultMeaning
steps25Sampling steps, for both flow stages.
guidance5.0Classifier-free guidance, for both flow stages.
shift3.0Flow time shift.
margin1.2Crop side over object size, as upstream.

Variants

One size, l (TRELLIS-image-large): 1.3B parameters in four networks, about 2.7 GB, plus 1.2 GB for the DINOv2 ViT-L/14 encoder.

Export

작업ONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
3D generation3D generation to ONNX: 지원하지 않음3D generation to TorchScript: 지원하지 않음3D generation to ExecuTorch: 지원하지 않음3D generation to TensorRT: 지원하지 않음3D generation to OpenVINO: 지원하지 않음3D generation to Paddle: 지원하지 않음3D generation to MNN: 지원하지 않음3D generation to RKNN: 지원하지 않음3D generation to Axelera: 지원하지 않음3D generation to ncnn: 지원하지 않음3D generation to TFLite: 지원하지 않음3D generation to CoreML: 지원하지 않음3D generation to Core AI: 지원하지 않음

Export is not implemented for LibreGen 3D families. export(), train() and val() raise NotImplementedError (ADR 0031 in the library).

Licensing

내려받는 특정 가중치의 Hugging Face 저장소에서 라이선스를 확인하십시오. LibreYOLO 조직의 모든 체크포인트에는 라이선스가 있으며 한 계열 안에서도 항상 같지는 않습니다. 해당 저장소가 신뢰할 수 있는 기준입니다. 아래 요약은 이 페이지를 마지막으로 검증했을 때 적용된 내용을 설명합니다.

관련 라이선스에 관한 설명이며 법률 자문이 아닙니다. 상업적으로 중요한 사안이라면 라이선스를 직접 읽고 별도의 법률 자문을 받으십시오.

원작
TRELLIS, Microsoft Research
업스트림 라이선스
MIT
업스트림 소스
github.com/microsoft/TRELLIS
LibreYOLO 코드
MIT
가중치
MIT, huggingface.co/LibreYOLO에 다시 게시됨
해석
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, and the flow models, decoders, sparse modules and sampler it adapts from TRELLIS keep MIT, noted in libreyolo/models/gen/trellis/NOTICE. LibreYOLO replaces upstream's CUDA-only spconv, xformers and flash-attn calls with PyTorch, and does not use TRELLIS's Gaussian holder, which carries Inria's non-commercial Gaussian Splatting license. The microsoft/TRELLIS-image-large weights (MIT) are redistributed unchanged as LibreYOLO/LibreTRELLISl together with the BiRefNet weights (MIT); the DINOv2 image encoder, facebook/dinov2-with-registers-large (Apache-2.0), downloads from Meta. All are pinned and none is gated.

TRELLIS is by Microsoft Research (microsoft/TRELLIS). Code and the microsoft/TRELLIS-image-large weights are MIT, so commercial use is fine with the notice kept. LibreYOLO redistributes the weights unchanged, with the BiRefNet weights (MIT), as LibreYOLO/LibreTRELLISl. The DINOv2 encoder, facebook/dinov2-with-registers-large, is Apache-2.0 and downloads from Meta. Upstream's Gaussian holder, under Inria's non-commercial Gaussian Splatting license, is not used.

Citation

@article{xiang2024structured,
    title   = {Structured 3D Latents for Scalable and Versatile 3D Generation},
    author  = {Xiang, Jianfeng and Lv, Zelong and Xu, Sicheng and Deng, Yu and Wang, Ruicheng and Zhang, Bowen and Chen, Dong and Tong, Xin and Yang, Jiaolong},
    journal = {arXiv preprint arXiv:2412.01506},
    year    = {2024}
}

github.com/microsoft/TRELLIS#-citation에 있는 저자의 인용 블록에서 복사했습니다.

LibreYOLO v1.8.0에서 검증되었습니다. 이 페이지의 지원 표, 체크포인트, 벤치마크 수치는 출시된 라이브러리와 공개된 가중치에서 생성되며 수동으로 작성되지 않습니다.