README.md 1.01 KB
Newer Older
Dongz's avatar
Dongz committed
1
# LightX2V: Light Video Generation Inference Framework
helloyongyang's avatar
helloyongyang committed
2

helloyongyang's avatar
helloyongyang committed
3
4
5
6
7
<div align="center">
  <picture>
    <img alt="LightLLM" src="assets/img_lightx2v.jpg" width=75%>
  </picture>
</div>
helloyongyang's avatar
helloyongyang committed
8

helloyongyang's avatar
helloyongyang committed
9
--------------------------------------------------------------------------------
helloyongyang's avatar
helloyongyang committed
10

Dongz's avatar
Dongz committed
11
## Prepare Environment
helloyongyang's avatar
helloyongyang committed
12

Dongz's avatar
Dongz committed
13
```shell
helloyongyang's avatar
helloyongyang committed
14
docker pull registry.cn-sh-01.sensecore.cn/devsft-ccr-2/video-gen:25033101
helloyongyang's avatar
helloyongyang committed
15
16
17
docker run --gpus all -itd --ipc=host --name [name] -v /mnt:/mnt --entrypoint /bin/bash [image id]
```

Dongz's avatar
Dongz committed
18
## Fast Start
helloyongyang's avatar
helloyongyang committed
19

Dongz's avatar
Dongz committed
20
21
22
```shell
git clone https://github.com/ModelTC/lightx2v.git
cd lightx2v
helloyongyang's avatar
helloyongyang committed
23

helloyongyang's avatar
helloyongyang committed
24
# Modify the parameters of the running script
helloyongyang's avatar
helloyongyang committed
25
26
bash run_hunyuan_t2v.sh
```
Dongz's avatar
Dongz committed
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44

## Contribute

We have prepared a `pre-commit` hook to enforce consistent code formatting across the project. You can clean up your code following the steps below:

1. Install the required dependencies:

```shell
    pip install ruff pre-commit
```

2. Then, run the following command:

```shell
    pre-commit run --all-files
```

If your code complies with the standards, you should not see any errors.