Views
No views yet
config.json + model.safetensors. SLAT + mesh/gaussian decoders come from microsoft/TRELLIS-image-large.| Model | Description | # Params |
|---|---|---|
reconstruction | Multi-view RGBD sparse-structure flow | 164.6 M |
affordance | Text-conditioned affordance heatmap flow | 185.4 M |
1from affostruction import AffostructionPipeline
2
3pipeline = AffostructionPipeline.from_pretrained("chrockey/Affostruction").cuda()
4outputs = pipeline.run(input_dict, queries=["Point to the part you would sit on."])
5
6coords = outputs["coords"] # (N, 4) sparse voxel coords
7probs = outputs["affordance"][0]["probs"] # (N,) per-voxel heatmap in [0, 1], paired with coordsNeed mesh / gaussian? Passformats=["mesh", "gaussian"]— decoding is opt-in.Reconstruction only? Dropqueries.
examples/affostruction.py (full pipeline), examples/reconstruction.py (reconstruction-only), and examples/reconstruction_unposed.py (experimental unposed single-view).