---
title: testtest_2
canonical_url: "https://www.modelscope.cn/models/peteromallet/testtest_2"
md_url: "https://www.modelscope.cn/models/peteromallet/testtest_2.md"
repository: peteromallet/testtest_2
last_updated: 2025-09-01
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
base_model:
  - Lightricks/LTX-Video
base_model_relation: adapter
parameters: 359.1M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 44
stars: 0
tags:
  - ltxv
  - 13B
  - text-to-video
  - lora
---

# testtest_2

> testtest_2 - peteromallet 在 ModelScope 开源的模型。Description: Trained only on videos.

peteromallet/testtest_2 是 ModelScope 魔搭社区上的 359.1M 参数text-to-video-synthesis模型，基于 Lightricks/LTX-Video 构建。

- **Repository**: peteromallet/testtest_2
- **Tasks**: text-to-video-synthesis
- **Parameters**: 359.1M
- **Base model**: Lightricks/LTX-Video
- **Tags**: ltxv, 13B, text-to-video, lora
- **Downloads**: 44
- **Stars**: 0
- **Last updated**: 2025-09-01

Source: https://www.modelscope.cn/models/peteromallet/testtest_2

---

# 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.