You can deploy this model and start earning money today!

StabilityLabs/
arbor

text-to-3d

3d-generation

checkpoint

geometry-conditioned-generation

2606.23514

other

Views

No views yet

Arbor

Explicit Geometric Conditioning for Controllable 3D Asset Generation

Arbor is a text-to-3D generation model with explicit geometry controls. It accepts a prompt and typed constraint meshes for hull, avoidance, and touch regions.

Please note: For individuals or organizations generating annual revenue of US $1,000,000 (or local currency equivalent) or more, regardless of the source of that revenue, you must obtain an enterprise commercial license directly from Stability AI before commercially using Arbor, derivative works of Arbor, or outputs from Arbor. See https://stability.ai/license and https://stability.ai/enterprise.

Model Description

Developed by: Stability AI
Authors: Jan-Niklas Dihlmann, Andreas Engelhardt, Simon Donne, Hendrik Lensch, Mark Boss
Model type: Text and geometry constrained 3D generation model
Model details: Arbor generates a geometry-conditioned sparse structure that is decoded into a mesh with the TRELLIS SLAT mesh decoder.
Base stack: TRELLIS text-to-3D and TRELLIS.2 constraint encoding components

Model Sources

Repository: https://github.com/Stability-AI/arbor
Project page: https://arbor.jdihlmann.com/
Paper: Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation

For installation, evaluation, Blender notes, and demo assets, please use the GitHub repository.

Usage

Below is a simple example of using the Python API to run Arbor:

python

from pathlib import Path
from arbor import ArborPipeline, ConstraintSet

pipeline = ArborPipeline(model_dir="artifacts/model")
result = pipeline.run(
    prompt="A small red toy piano with a rounded rectangular body.",
    constraints=ConstraintSet(
        hull=(Path("examples/constraints/piano__piano_038__8a941e90/hull_constraint.ply"),),
    ),
    output_dir="outputs/piano_038",
    seed=1,
)
print(result.mesh_path)

Files

arbor_sparse_structure_config.json: public inference config for Arbor sparse-structure generation.
slat_flow_txt_dit_B_64l8p2_geo_router_v1_ft_fp16.json: SLAT mesh generation config used by the release pipeline.
denoiser_ema0.9999_step0053000.pt: public Arbor sparse-structure checkpoint.
Optional parity artifact, if uploaded: denoiser_step0053000.pt.

License

Community License: Free for research, non-commercial, and commercial use by organizations and individuals generating annual revenue of US $1,000,000 (or local currency equivalent) or less, regardless of the source of that revenue.
If your annual revenue exceeds US $1M, any commercial use of this model or derivative works requires an Enterprise License directly from Stability AI.

Please refer to Stability AI's Community License at https://stability.ai/license for more information.

Intended Uses

Intended uses include research and creative workflows involving constrained 3D asset generation, design exploration, and assessment of text plus geometry conditioned generation methods.

Out-of-Scope Uses

Arbor is not intended to generate factual representations of people, events, products, or places. Use must comply with Stability AI's Acceptable Use Policy and license terms.

Citation

bibtex

@misc{dihlmann2026arbor,
  author = {Dihlmann, Jan-Niklas and Engelhardt, Andreas and Donne, Simon and Lensch, Hendrik and Boss, Mark},
  title = {Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation},
  booktitle = {Preprint},
  year = {2026}
}

Safety

Users should evaluate generated outputs for their own application constraints and apply additional mitigations where needed. Report safety issues to safety@stability.ai and security issues to security@stability.ai.

StabilityLabs/arbor