Views
No views yet
# pull image
docker pull mybigpai-public-registry.cn-beijing.cr.aliyuncs.com/easycv/torch_cuda:cogvideox_fun
# enter image
docker run -it -p 7860:7860 --network host --gpus all --security-opt seccomp:unconfined --shm-size 200g mybigpai-public-registry.cn-beijing.cr.aliyuncs.com/easycv/torch_cuda:cogvideox_fun
# clone code
git clone https://github.com/aigc-apps/CogVideoX-Fun.git
# enter CogVideoX-Fun's dir
cd CogVideoX-Fun
# download weights
mkdir models/Diffusion_Transformer
mkdir models/Personalized_Model
wget https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz -O models/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz
wget https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz -O models/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz
cd models/Diffusion_Transformer/
tar -xvf CogVideoX-Fun-2b-InP.tar.gz
tar -xvf CogVideoX-Fun-5b-InP.tar.gz
cd ../../📦 models/
├── 📂 Diffusion_Transformer/
│ ├── 📂 CogVideoX-Fun-2b-InP/
│ └── 📂 CogVideoX-Fun-5b-InP/
├── 📂 Personalized_Model/
│ └── your trained trainformer model / your trained lora model (for UI load)📦 project/
├── 📂 datasets/
│ ├── 📂 internal_datasets/
│ ├── 📂 train/
│ │ ├── 📄 00000001.mp4
│ │ ├── 📄 00000002.jpg
│ │ └── 📄 .....
│ └── 📄 json_of_internal_datasets.json1[
2 {
3 "file_path": "train/00000001.mp4",
4 "text": "A group of young men in suits and sunglasses are walking down a city street.",
5 "type": "video"
6 },
7 {
8 "file_path": "train/00000002.jpg",
9 "text": "A group of young men in suits and sunglasses are walking down a city street.",
10 "type": "image"
11 },
12 .....
13]1[
2 {
3 "file_path": "/mnt/data/videos/00000001.mp4",
4 "text": "A group of young men in suits and sunglasses are walking down a city street.",
5 "type": "video"
6 },
7 {
8 "file_path": "/mnt/data/train/00000001.jpg",
9 "text": "A group of young men in suits and sunglasses are walking down a city street.",
10 "type": "image"
11 },
12 .....
13]export DATASET_NAME="datasets/internal_datasets/"
export DATASET_META_NAME="datasets/internal_datasets/json_of_internal_datasets.json"
...
train_data_format="normal"export DATASET_NAME=""
export DATASET_META_NAME="/mnt/data/json_of_internal_datasets.json"sh scripts/train.sh| 名称 | 存储空间 | 下载地址 | Hugging Face | 描述 |
|---|---|---|---|---|
| CogVideoX-Fun-2b-InP.tar.gz | 解压前 9.7 GB / 解压后 13.0 GB | Download | 🤗Link | 官方的图生视频权重。支持多分辨率（512，768，1024，1280）的视频预测，以49帧、每秒8帧进行训练 |
| CogVideoX-Fun-5b-InP.tar.gz | 解压前 16.0GB / 解压后 20.0 GB | Download | 🤗Link | 官方的图生视频权重。支持多分辨率（512，768，1024，1280）的视频预测，以49帧、每秒8帧进行训练 |