Sapiens2 Segmentation Checkpoint Mirror
Results and visual examples
Sapiens2 segmentation checkpoint mirror. These predict semantic human-part classes; they are not the SAM3-distilled clothing-instance models. No checkpoint-matched saved gallery was recovered in this audit.
No checkpoint-matched photo gallery was located in the existing evidence reviewed for this update. The files and runtime records below are the available evidence; no visual quality claim is inferred from their presence.
Evidence provenance
This documentation update reuses saved results; it does not rerun inference or change weights. The starting repository revision is e012b81953ad. Captions distinguish model predictions, training diagnostics, and aggregate metrics. Qualitative examples are not a representative accuracy estimate.
Gallery sources and SHA-256 checksums.
Mirrored reusable checkpoints for Fury Sapiens2 segmentation work.
Published files:
seg/sapiens2_0.4b_seg.safetensorsseg/sapiens2_0.8b_seg.safetensors
Not published:
0.1bsegmentation, because upstream shipsfacebook/sapiens2-pretrain-0.1bbut not a matching segmentation checkpoint/config.