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
cogvideox/ui/ui.py
+8 -8
View File
@@ -427,11 +427,11 @@ def ui(low_gpu_memory_mode, weight_dtype):
with gr.Blocks(css=css) as demo:
gr.Markdown(
"""
# CogVideoX-Arbitrary:
# CogVideoX-Fun:
A CogVideoX with more flexible generation conditions, capable of producing videos of different resolutions, around 6 seconds, and fps 8 (frames 1 to 49), as well as image generated videos.
[Github](https://github.com/aigc-apps/CogVideoX-Arbitrary/)
[Github](https://github.com/aigc-apps/CogVideoX-Fun/)
"""
)
with gr.Column(variant="panel"):
@@ -872,11 +872,11 @@ def ui_modelscope(model_name, savedir_sample, low_gpu_memory_mode, weight_dtype)
with gr.Blocks(css=css) as demo:
gr.Markdown(
"""
# CogVideoX-Arbitrary
# CogVideoX-Fun
A CogVideoX with more flexible generation conditions, capable of producing videos of different resolutions, around 6 seconds, and fps 8 (frames 1 to 49), as well as image generated videos.
[Github](https://github.com/aigc-apps/CogVideoX-Arbitrary/)
[Github](https://github.com/aigc-apps/CogVideoX-Fun/)
"""
)
with gr.Column(variant="panel"):
@@ -903,7 +903,7 @@ def ui_modelscope(model_name, savedir_sample, low_gpu_memory_mode, weight_dtype)
with gr.Column(visible=False):
gr.Markdown(
"""
### Minimalism is an example portrait of Lora, triggered by specific prompt words. More details can be found on [Wiki](https://github.com/aigc-apps/CogVideoX-Arbitrary/wiki/Training-Lora).
### Minimalism is an example portrait of Lora, triggered by specific prompt words. More details can be found on [Wiki](https://github.com/aigc-apps/CogVideoX-Fun/wiki/Training-Lora).
"""
)
with gr.Row():
@@ -1206,11 +1206,11 @@ def ui_eas(model_name, savedir_sample):
with gr.Blocks(css=css) as demo:
gr.Markdown(
"""
# CogVideoX-Arbitrary
# CogVideoX-Fun
A CogVideoX with more flexible generation conditions, capable of producing videos of different resolutions, around 6 seconds, and fps 8 (frames 1 to 49), as well as image generated videos.
[Github](https://github.com/aigc-apps/CogVideoX-Arbitrary/)
[Github](https://github.com/aigc-apps/CogVideoX-Fun/)
"""
)
with gr.Column(variant="panel"):
@@ -1237,7 +1237,7 @@ def ui_eas(model_name, savedir_sample):
with gr.Column(visible=False):
gr.Markdown(
"""
### Minimalism is an example portrait of Lora, triggered by specific prompt words. More details can be found on [Wiki](https://github.com/aigc-apps/CogVideoX-Arbitrary/wiki/Training-Lora).
### Minimalism is an example portrait of Lora, triggered by specific prompt words. More details can be found on [Wiki](https://github.com/aigc-apps/CogVideoX-Fun/wiki/Training-Lora).
"""
)
with gr.Row():
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"