over|yonder Espalier-2

over|yonder Espalier-2 runs Microsoft's TRELLIS.2-4B at its highest resolution, the 1536 cascade, on a 16 GB consumer GPU. It uses Microsoft's weights unchanged, so this repository holds no weights of its own. The code, patches and install script are on GitHub.

An espalier is a fruit tree trained flat against a trellis, so a full-size tree grows in a narrow space.

Microsoft's published catapult (top) and Espalier-2's at 1536 on a 16 GB card (bottom)

Microsoft lists a 24 GB GPU as the minimum, and on a 16 GB card its 1536 pipeline runs out of memory in the shape decoder and again in the GLB export. Espalier-2 tiles the decoders' highest-resolution stages, runs the export's remesh in chunks, and frees memory the remesh and simplifier no longer need. On an RTX 5070 Ti, generating the catapult above peaked at 11.9 GiB and its export at 8.3 GiB, measured from the NVIDIA driver.

Dense objects also stay at 1536. Microsoft's cascade lowers the resolution of objects above 49,152 tokens, and Espalier-2's --max-tokens option raises that limit: a water pot of 80,816 tokens generated at 1536 with a 13.0 GiB peak and exported at 11.5 GiB.

Each network's weights are read from its safetensors file to the GPU when its stage runs, so the process holds about 6 GiB of system memory instead of 20 GiB, with bit-identical output.

Espalier-2 also runs Tencent's Pixal3D, which is built on TRELLIS.2, at 1536 on the same card, from one image or from several posed views. With --no-texture, either model skips the texture and exports the untextured geometry, which is identical to a textured run's.

The same patch of both catapults from a 3072-pixel render

The article over|yonder Espalier-2: TRELLIS.2 at 1536 on a 16 GB GPU explains every change and measurement.

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for overyonder/espalier-2

Finetuned
(5)
this model