Hugging Face's logo

alibaba-pai
/
CogVideoX-Fun-2b-InP

Image-to-Video
Diffusers
Safetensors
English
CogVideoXPipeline
cogvideox-fun
video-generation
alibaba-pai
text-to-video
Model card Files
xet
Community
1
bubbliiiing commited on
Commit
b293ecd
·
1 Parent(s): bfd08f4

update Readme

Browse files
Files changed (2) hide show
  1. README.md +6 -7
  2. README_en.md +5 -5
README.md CHANGED
@@ -4,10 +4,11 @@ license_link: https://modelscope.cn/models/ZhipuAI/CogVideoX-5B/file/view/master
4
  language:
5
  - en
6
  tags:
7
- - cogvideox
8
  - video-generation
9
- - thudm
10
  - text-to-video
 
11
  studios:
12
  - alibaba-pai/CogVideoX-Fun-5b
13
  inference: false
@@ -80,11 +81,9 @@ mkdir models/Diffusion_Transformer
80
  mkdir models/Personalized_Model
81
 
82
  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
83
- 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
84
 
85
  cd models/Diffusion_Transformer/
86
  tar -xvf CogVideoX-Fun-2b-InP.tar.gz
87
- tar -xvf CogVideoX-Fun-5b-InP.tar.gz
88
  cd ../../
89
  ```
90
 
@@ -304,10 +303,10 @@ sh scripts/train.sh
304
  关于一些参数的设置细节，可以查看[Readme Train](scripts/README_TRAIN.md)与[Readme Lora](scripts/README_TRAIN_LORA.md)
305
 
306
  # 模型地址
307
- | 名称 | 存储空间 | 下载地址 | Hugging Face | 描述 |
308
  |--|--|--|--|--|
309
- | CogVideoX-Fun-2b-InP.tar.gz | 解压前 9.7 GB / 解压后 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| 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 |
310
- | CogVideoX-Fun-5b-InP.tar.gz | 解压前 16.0GB / 解压后 20.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| 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 |
311
 
312
  # 未来计划
313
  - 支持中文。
 
4
  language:
5
  - en
6
  tags:
7
+ - cogvideox-fun
8
  - video-generation
9
+ - alibaba-pai
10
  - text-to-video
11
+ - image-to-video
12
  studios:
13
  - alibaba-pai/CogVideoX-Fun-5b
14
  inference: false
 
81
  mkdir models/Personalized_Model
82
 
83
  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
 
84
 
85
  cd models/Diffusion_Transformer/
86
  tar -xvf CogVideoX-Fun-2b-InP.tar.gz
 
87
  cd ../../
88
  ```
89
 
 
303
  关于一些参数的设置细节，可以查看[Readme Train](scripts/README_TRAIN.md)与[Readme Lora](scripts/README_TRAIN_LORA.md)
304
 
305
  # 模型地址
306
+ | 名称 | 存储空间 | Hugging Face | Model Scope | 描述 |
307
  |--|--|--|--|--|
308
+ | CogVideoX-Fun-2b-InP.tar.gz | 解压前 9.7 GB / 解压后 13.0 GB | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP) | [😄Link](https://modelscope.cn/models/PAI/CogVideoX-Fun-2b-InP) | 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 |
309
+ | CogVideoX-Fun-5b-InP.tar.gz | 解压前 16.0GB / 解压后 20.0 GB | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP) | [😄Link](https://modelscope.cn/models/PAI/CogVideoX-Fun-5b-InP) | 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 |
310
 
311
  # 未来计划
312
  - 支持中文。
README_en.md CHANGED
@@ -2,6 +2,8 @@
2
 
3
  😊 Welcome!
4
 
 
 
5
  English | [简体中文](./README.md)
6
 
7
  # Table of Contents
@@ -67,11 +69,9 @@ mkdir models/Diffusion_Transformer
67
  mkdir models/Personalized_Model
68
 
69
  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
70
- 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
71
 
72
  cd models/Diffusion_Transformer/
73
  tar -xvf CogVideoX-Fun-2b-InP.tar.gz
74
- tar -xvf CogVideoX-Fun-5b-InP.tar.gz
75
  cd ../../
76
  ```
77
 
@@ -288,10 +288,10 @@ For details on setting some parameters, please refer to [Readme Train](scripts/R
288
 
289
  # Model zoo
290
 
291
- | Name | Storage Space | Url | Hugging Face | Description |
292
  |--|--|--|--|--|
293
- | CogVideoX-Fun-2b-InP.tar.gz | Before extraction:9.7 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 8 frames per second. |
294
- | CogVideoX-Fun-5b-InP.tar.gz | Before extraction:16.0 GB \/ After extraction: 20.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 8 frames per second. |
295
 
296
  # TODO List
297
  - Support Chinese.
 
2
 
3
  😊 Welcome!
4
 
5
+ [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-yellow)](https://huggingface.co/spaces/alibaba-pai/CogVideoX-Fun-5b)
6
+
7
  English | [简体中文](./README.md)
8
 
9
  # Table of Contents
 
69
  mkdir models/Personalized_Model
70
 
71
  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
 
72
 
73
  cd models/Diffusion_Transformer/
74
  tar -xvf CogVideoX-Fun-2b-InP.tar.gz
 
75
  cd ../../
76
  ```
77
 
 
288
 
289
  # Model zoo
290
 
291
+ | Name | Storage Space | Hugging Face | Model Scope | Description |
292
  |--|--|--|--|--|
293
+ | CogVideoX-Fun-2b-InP.tar.gz | Before extraction:9.7 GB \/ After extraction: 13.0 GB | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP) | [😄Link](https://modelscope.cn/models/PAI/CogVideoX-Fun-2b-InP) | Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 8 frames per second. |
294
+ | CogVideoX-Fun-5b-InP.tar.gz | Before extraction:16.0 GB \/ After extraction: 20.0 GB | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| [😄Link](https://modelscope.cn/models/PAI/CogVideoX-Fun-5b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 8 frames per second. |
295
 
296
  # TODO List
297
  - Support Chinese.