blanchon / inspatio-world-v1.5

InSpatio-World 1.5 — all weights in one repository

Everything InSpatio-World 1.5 ( paper ) needs at inference, repackaged for the minimal re-implementation inspatio-world : one folder per component, each a config.json + model.safetensors pair loaded with from_pretrained . No other repository is downloaded.

The conversion only renames keys (fusing the DiT's q/k/v and cross-attention k/v projections), drops unused branches (DA3's ray / Gaussian-splatting heads) and casts to the dtype each module runs in; upstream runs the DiT, VAE and text encoder in bf16, so outputs are unchanged. It was produced by scripts/convert_checkpoints.py .

Usage

pip install "inspatio-world @ git+https://github.com/julien-blanchon/inspatio-world-v1.5"
inspatio-world generate --source.paths photo.jpg --moves forward:36 turn-right+forward:36 --output out.mp4

from inspatio_world import CameraAction, CameraRig, WorldConfig, WorldModel
from inspatio_world.data import load_scene

world = WorldModel.from_pretrained(WorldConfig(decoder="taehv", dit_precision="fp8", compile=True))
scene = load_scene(examples_dir / "image_example_00")
session, rig = world.start(scene), CameraRig(scene)
while True:
    block = session.step(rig.advance(CameraAction(forward=1.0, yaw=0.3), session.frames_needed))
    ...  # block.frames: (12, 480, 832, 3) uint8

Interactive demo: spaces/blanchon/inspatio-world-v1.5 .

Licenses

Each component keeps its original license:

• dit/ : InSpatio-World 1.5 weights, released by the InSpatio team with the Apache-2.0 code of inspatio/inspatio-world-v1.5 .
• vae/ , text_encoder/ , tokenizer/ : Wan2.1, Apache-2.0.
• taehv/ : TAEHV, MIT.
• depth/ : Depth-Anything-3 DA3NESTED-GIANT-LARGE, CC BY-NC 4.0 (non-commercial) .
• examples/ : from the upstream repository.

Citation

@misc{inspatio-world,
  title={INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling},
  author={InSpatio Team},
  journal={arXiv preprint arXiv:2604.07209},
  year={2026}
}