---
tags:
- video-generation
- world-model
- lora
---

# Streaming Code World Model

LoRA checkpoints for [Streaming Code World Model](https://github.com/TingtingLiao/streaming-code-world-model): causal,
chunk-by-chunk video generation from a live proxy, on top of the released
[Code World Model](https://github.com/buaacyw/code-world-model) (MiniMax-H3 Ref2VA + CWM LoRA). Both files are LoRAs
for the released MiniMax-H3 model; install the CWM release first (see the GitHub README).

| file | model | sampling | CARLA MSE ↓ | s / chunk (H200) |
|:---|:---|:---|---:|---:|
| `streaming_df.safetensors` | streaming diffusion forcing | `--steps 35` | 2231 | 47.9 |
| `streaming_dmd_4step.safetensors` | 4-step DMD, the streaming model as teacher | `--steps 4 --rule x0 --shift 5 --kv-reuse` | 1660 | 5.1 |

```bash
hf download Luffuly/streaming-code-world-model --local-dir ckpt
EVAL_ARGS="--steps 4 --rule x0 --shift 5 --kv-reuse" \
    sbatch scripts/eval/eval.sbatch ckpt/streaming_dmd_4step.safetensors out/ clip_0048
```

Inference runs on one NVIDIA H200 (141 GB); peak memory 123 GB (bf16), 108 GB (`--fp8`).