use the folowing command to merge the updates locally
git pull
venv\scripts\activate
cd CogVideoX
- CogVideoX_v1.5_5b Text to Video
python CogVideoX_v1.5_5b_t2v_gradio.py
- CogVideoX_v1.5_5b Image to Video
python CogVideoX_v1.5_5b_i2v_gradio.py
- CogVideoX_v1.5_5b Video to Video
python CogVideoX_v1.5_5b_v2v_gradio.py
- CogVideoX-Fun-V1.1-5b - Pose
python CogVideoX-Fun-V1.1-5b-Pose_gradio.py
Added Width/Height/negative prompt support in the following models
- Sana 2K 1.6B MultiLingual [fp16]
- Sana 2K 1.6B MultiLingual (with PAG) [fp16]
use the folowing command to merge the updates locally
git pull
- HunyuanVideo Text to Video
Activate virtual environment
cd HunyuanVideo
python HunyuanVideo_gradio.py
- LTX-Video: ltx-video-2b-v0.9.1 Image to Video
Activate virtual environment
cd LTX
python LTX091_I2V_gradio.py
- LTX-Video: ltx-video-2b-v0.9.1
Activate virtual environment
cd LTX
python LTX091_gradio.py
Activate virtual environment
cd Sana
- Sana 2K 1.6B MultiLingual [fp16]
python sana_2k_gradio.py
- Sana 2K 1.6B MultiLingual (with PAG) [fp16]
python sana_2k_PAG_gradio.py
Activate virtual environment
cd CogView3
- CogView3 Plus 3B (text to image)
python CogView3-Plus-3B_gradio.py
Activate virtual environment
cd Sana
- Sana 1600M 512px MultiLingual [fp16]
python Sana_gradio_1.6B_512.py
- Sana 1600M 1024px MultiLingual [fp16]
python Sana_gradio_1.6B_1024.py
- LTX-Video: ltx-video-2b-v0.9
Activate virtual environment
cd LTX
python LTX09_gradio.py