zR commited on
Commit
0d6a353
·
1 Parent(s): 95830a4

update_diffusers

Browse files
Files changed (2) hide show
  1. README.md +13 -14
  2. README_zh.md +2 -3
README.md CHANGED
@@ -88,18 +88,18 @@ inference: false
88
  CogVideoX is an open-source video generation model that shares the same origins as [清影](https://chatglm.cn/video).
89
  The table below provides a list of the video generation models we currently offer, along with their basic information.
90
 
91
- | Model Name | CogVideoX-2B (Current Repos) |
92
- |--------------------------------------------|-----------------------------------------------|
93
- | Supported Prompt Language | English |
94
- | GPU Memory Required for Inference | 36GB (will be optimized before the PR is merged) |
95
- | GPU Memory Required for Fine-tuning (bs=1) | 42GB |
96
- | Prompt Length | 226 Tokens |
97
- | Video Length | 6 seconds |
98
- | Frames Per Second | 8 frames |
99
- | Resolution | 720 * 480 |
100
- | Positional Embeddings | Sinusoidal |
101
- | Quantized Inference | Not Supported |
102
- | Multi-card Inference | Not Supported |
103
 
104
  **Note** Using [SAT](https://github.com/THUDM/SwissArmyTransformer) model cost 18GB for inference. Check our github.
105
 
@@ -113,8 +113,7 @@ optimizations and conversions to get a better experience.**
113
  1. Install the required dependencies
114
 
115
  ```shell
116
- pip install --upgrade opencv-python transformers
117
- pip install git+https://github.com/huggingface/diffusers.git@878f609aa5ce4a78fea0f048726889debde1d7e8#egg=diffusers # Still in PR
118
  ```
119
 
120
  2. Run the code
 
88
  CogVideoX is an open-source video generation model that shares the same origins as [清影](https://chatglm.cn/video).
89
  The table below provides a list of the video generation models we currently offer, along with their basic information.
90
 
91
+ | Model Name | CogVideoX-2B (Current Repos) |
92
+ |--------------------------------------------|------------------------------|
93
+ | Supported Prompt Language | English |
94
+ | GPU Memory Required for Inference | 36GB |
95
+ | GPU Memory Required for Fine-tuning (bs=1) | 42GB |
96
+ | Prompt Length | 226 Tokens |
97
+ | Video Length | 6 seconds |
98
+ | Frames Per Second | 8 frames |
99
+ | Resolution | 720 * 480 |
100
+ | Positional Embeddings | Sinusoidal |
101
+ | Quantized Inference | Not Supported |
102
+ | Multi-card Inference | Not Supported |
103
 
104
  **Note** Using [SAT](https://github.com/THUDM/SwissArmyTransformer) model cost 18GB for inference. Check our github.
105
 
 
113
  1. Install the required dependencies
114
 
115
  ```shell
116
+ pip install --upgrade opencv-python transformers diffusers # Must using diffusers>=0.30.0
 
117
  ```
118
 
119
  2. Run the code
README_zh.md CHANGED
@@ -76,7 +76,7 @@ CogVideoX是 [清影](https://chatglm.cn/video) 同源的开源版本视频生
76
  | Model Name | CogVideoX-2B (当前仓库) |
77
  |---------------|---------------------|
78
  | 提示词语言 | English |
79
- | 推理显存消耗 | 36GB(会在PR合并之前优化) |
80
  | 微调显存消耗 (bs=1) | 42GB |
81
  | 提示词长度上限 | 226 Tokens |
82
  | 视频生成长度 | 6 seconds |
@@ -97,8 +97,7 @@ CogVideoX是 [清影](https://chatglm.cn/video) 同源的开源版本视频生
97
  1. 安装对应的依赖
98
 
99
  ```shell
100
- pip install --upgrade opencv-python transformers acc
101
- pip install git+https://github.com/huggingface/diffusers.git@878f609aa5ce4a78fea0f048726889debde1d7e8#egg=diffusers # Still in PR
102
  ```
103
 
104
  2. 运行代码
 
76
  | Model Name | CogVideoX-2B (当前仓库) |
77
  |---------------|---------------------|
78
  | 提示词语言 | English |
79
+ | 推理显存消耗 | 36GB |
80
  | 微调显存消耗 (bs=1) | 42GB |
81
  | 提示词长度上限 | 226 Tokens |
82
  | 视频生成长度 | 6 seconds |
 
97
  1. 安装对应的依赖
98
 
99
  ```shell
100
+ pip install --upgrade opencv-python transformers accelerate diffusers # Must using diffusers>=0.30.0
 
101
  ```
102
 
103
  2. 运行代码