---
base_model:
- Lightricks/LTX-Video
widget:
  - text: |
      fsdafasdfsda
    output:
      url: assets/ltxv-7-21_00009 (3).mp4
  - text: |
      hsgdhgfd
    output:
      url: assets/ltxv-7-21_00009 (4).mp4
  - text: |
      gsfdgfds
    output:
      url: assets/ltxv-7-21_00009 (2).mp4
tags:
- ltxv
- 13B
- text-to-video
- lora
---

# wan (14b T2V)

<Gallery />

## Description:
Trained only on videos.

- dataset: 135 videos 768x480x41
- steps: 17000
- LR: 2e-4
- optimizer: adamw
- scheduler: contant
- rank: 128
- batch size: 1
- gradient accumulation steps: 1

For training I used the official [LTX-Video Trainer](https://github.com/Lightricks/LTX-Video-Trainer) repo.