Text-to-video generation.
Status: work in progress. Built on a permissive, commercially-licensed foundation (no non-commercial or restricted-weight dependencies). The Zen model is not yet trained/integrated here — this provides the licensing, attribution, and integration scaffold.
Built on Wan2.2 (Alibaba, Apache-2.0) — chosen for permissive, commercial-friendly licensing.
Apache License, Version 2.0 — see LICENSE and NOTICE. Copyright 2025-2026 Zen Authors (https://zenlm.org).
- Wire the permissive foundation as the generation backbone
- Train / fine-tune the Zen variant
- Inference, evaluation, and release