Image-to-3D

Update model card: description, intended use, limitations

#10
by landam - opened

Turns the install/training README into a proper model card, without changing any of the original content:

  • TL;DR and a Model description section (pixel back-projection conditioning, three-stage cascade, TRELLIS.2 backbone, DINOv2 encoder, GLB + PBR output, multi-view and scene extension)
  • Intended use and Limitations/biases sections (generated-not-measured, unseen-surface invention, ObjaverseXL bias, view-aligned pose, VRAM modes)
  • Quick start pointing to GitHub, with the one-image / low-VRAM / SDPA invocations
  • Keeps the original Branches, Training, Community, Acknowledgements, Citation and License sections

Facts sourced from the paper (arXiv:2605.10922), the GitHub README, and the NOTICE file.

Friendly ping @TencentARC - could this model-card PR be merged when you have a moment? It turns the install/training README into a proper model card (TL;DR, model description, intended use, limitations/biases, quick start) while keeping all original sections. Happy to adjust anything.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment