This repository stores the original modality-scoped PyTorch latent shards used by WSM v1 training. PT shards are uploaded directly rather than wrapped in tar archives, so one modality can be replaced without republishing the full cache. Each modality update is committed with its changed PT shards and SHA-256 manifest. This is the continuously maintained raw-PT repository. When the WSG standard advances, this repository is renamed to the next standard version (for example, v1.8 to v1.9) so its commit history remains continuous. Historical tar-packaged repositories remain separate snapshots.
Organization
World Snapshot
World-Snapshot
Unify Computer Vision, Expand Computer Vision, Transcend Computer Vision.
Models in Library0
Datasets in Library2
Models on Hugging Face—
Followers4
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image to image.
Reported licenses: mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Datasets
Raw (pre-VAE) samples for the WSM v1 IC-Light relighting pilot (iclightrelightingv3). Each sample is a self-describing named-key.npz: a source appearance, an IBL light-probe condition, and the relit target. The matching FLUX.2 latents live in the companion latent repo World-Snapshot/WSMv1LatentPTWSGv1.8forFlux2 (custompilots/iclightrelightingv3/cachenamedv2/). Derived from the public GenLit dataset (gbmpi/genlitdataset): Objaverse objects rendered under Poly Haven HDRI environments with a single moving point light. Within a GenLit scene the point-light direction is fixed while its intensity ramps 0 → 30 → 60 → 90 → 100 → 120 and then plateaus at 120 (as the point light rises the environment…