LiveFrame

Real-time video generation, honestly measured.

LiveFrame is an evidence-first measurement framework for real-time autoregressive diffusion video, spanning NVIDIA CUDA and Apple MLX. It separates four claim layers — numerical trajectory, intrinsic quality, same-seed identity, and complete-wall performance — with pre-registered thresholds and digest-bound provenance.

Paper: LiveFrame: Evidence-First Measurement of Real-Time Autoregressive Diffusion Video Across CUDA and Apple MLX (2026).

This release (0.1.0)

This first release ships the evidence verifier for LiveFrame claim ledgers:

pip install liveframe

# re-hash every unique digest-bound artifact referenced by a ledger (fail-closed)
liveframe verify path/to/liveframe-publication-claims.v1.json --artifacts-root path/to/repo

# independently recompute headline arithmetic from values recorded in the ledger
liveframe recompute path/to/liveframe-publication-claims.v1.json

verify requires the separately distributed evidence artifacts referenced by the ledger; model weights and evidence files are not bundled in this Python package. It rejects missing files, digest mismatches, unsupported schemas, conflicting references, and artifact paths outside the selected root.

The streaming engine APIs (stream, clip, benchmark) are planned for later releases. See the repository for the full evidence bundle, claim protocol, and reports.

License

Apache-2.0