---
title: Temporal Context Routing
emoji: 🎬
colorFrom: gray
colorTo: indigo
sdk: gradio
sdk_version: 6.8.0
python_version: "3.12"
app_file: app.py
short_description: Script-timed multi-shot video with synced audio
startup_duration_timeout: 1h
pinned: false
license: other
---

# The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation

Demo of **TCR** ([paper](https://huggingface.co/papers/2609.02367) ·
[model](https://huggingface.co/starry0929/Temporal-Context-Routing) ·
[code](https://github.com/DAGroup-PKU/Temporal-Context-Routing)).

You write a *script*: a JSON object whose `shots` and `events` carry explicit
`time_range` fields in seconds. TCR turns those intervals into an additive bias on the
text cross-attention logits, so each text token only routes to the video/audio tokens
that fall inside its own time window. The result is a multi-shot clip that cuts where
the script says it cuts, with dialogue/SFX/music landing on the beat.

## What runs here

| Component | Weights |
| --- | --- |
| Base video+audio DiT | [`Lightricks/LTX-2.3`](https://huggingface.co/Lightricks/LTX-2.3) `ltx-2.3-22b-dev.safetensors` (fp8-cast) |
| TCR adapter | [`starry0929/Temporal-Context-Routing`](https://huggingface.co/starry0929/Temporal-Context-Routing) rank-128 LoRA, fused at strength 1.0 |
| Text encoder | [`google/gemma-3-12b-it`](https://huggingface.co/google/gemma-3-12b-it) |

Sampling matches the authors' `scripts/infer.sh`: 30 steps, CFG 4.0, STG 1.0 on block 29
(`stg_av`), `temporal_mode=tcr`, `tcr_beta=5.0`, 24 fps. The clip length is derived from
the script's own latest `time_range` end time (capped at 10 s / 241 frames), because the
TCR bias is expressed in absolute seconds.

Everything is resident on GPU at once (ZeroGPU `xlarge`, 96 GB), so the reference
pipeline's single-card CPU-offload shuffling is disabled.

## Examples

The three bundled scripts come from the authors' own release: `clip_32845.json` is the
example shipped in the GitHub repo (and used by `infer.sh`), and `clip_22172.json` /
`clip_24584.json` are taken from `test_prompts_200.json` in the model repo.

## License

The LTX-2.3 weights and the TCR adapter are released under the
[LTX-2 Community License](https://huggingface.co/Lightricks/LTX-2.3/blob/main/LICENSE);
Gemma is under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).