nodes/aigc-apps-VideoX-Fun
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Rename && Update Readme

Browse Source
This commit is contained in:
bubbliiiing
2024-09-10 11:26:18 +08:00
parent ef55bd3bbe
commit 4ee00bb26b
3 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/README_TRAIN.md
+3 -3
View File
@@ -2,9 +2,9 @@
The default training commands for the different versions are as follows:
We can choose whether to use deep speed in CogVideoX-Arbitrary, which can save a lot of video memory.
We can choose whether to use deep speed in CogVideoX-Fun, which can save a lot of video memory.
CogVideoX-Arbitrary without deepspeed:
CogVideoX-Fun without deepspeed:
```sh
export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
export DATASET_NAME="datasets/internal_datasets/"
@@ -52,7 +52,7 @@ accelerate launch --mixed_precision="bf16" scripts/train.py \
--trainable_modules "."
```
CogVideoX-Arbitrary with deepspeed:
CogVideoX-Fun with deepspeed:
```sh
export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
export DATASET_NAME="datasets/internal_datasets/"
scripts/README_TRAIN_LORA.md
+2 -2
View File
@@ -1,8 +1,8 @@
## Lora Training Code
We can choose whether to use deep speed in CogVideoX-Arbitrary, which can save a lot of video memory.
We can choose whether to use deep speed in CogVideoX-Fun, which can save a lot of video memory.
CogVideoX-Arbitrary without deepspeed:
CogVideoX-Fun without deepspeed:
```sh
export MODEL_NAME="models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"