Image-to-Video
video-generation
world-model
distillation
lora
alayaworld
ChuanhaoLi's picture
Upload README.md with huggingface_hub
74541fe verified
|
Raw
History Blame Contribute Delete
1.21 kB
---
license: other
license_name: ltx-2-community-license-agreement
license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
pipeline_tag: image-to-video
tags: [video-generation, world-model, distillation, lora, alayaworld]
---
# AlayaWorld v1.1 — Stage3 Few-Step Student (DMD LoRA)
4-step DMD-distilled student of **AlayaWorld** (real-time inference). LoRA on top of the
[stage2b AR teacher](https://huggingface.co/AlayaLab/AlayaWorld-v1.1-stage2b); LTX-2 Community License.
| File | Size | Content |
|---|---|---|
| `lora.safetensors` | 2.5 GB | generator LoRA (rank 256) |
| `history_encoder.pt` | 33 MB | compressed frame-history encoder |
**Usage** — with [AlayaLab/AlayaWorld](https://github.com/AlayaLab/AlayaWorld):
```yaml
paths:
resume_checkpoint: <stage2b download dir> # teacher base
dmd_resume: <this repo download dir> # lora.safetensors
history_encoder: <this repo download dir>/history_encoder.pt
```
Run: `VALIDATE_ONLY=1 CONFIG_PATH=configs/infer_i2v_camera.yaml bash scripts/finetune/train.sh`
Reports: [intro](https://arxiv.org/abs/2607.06291) · [full](https://arxiv.org/abs/2607.18367) · [v1.1](https://arxiv.org/abs/2608.13492)