Merge pull request #460 from THUDM/CogVideoX_dev

requirements update

inference/gradio_composite_demo/requirements.txt

@@ -3,15 +3,15 @@ safetensors>=0.4.5
 spandrel>=0.4.0
 tqdm>=4.66.5
 scikit-video>=1.1.11
-git+https://github.com/huggingface/diffusers.git@main
+diffusers>=0.31.0
 transformers>=4.44.0
 accelerate>=0.34.2
 opencv-python>=4.10.0.84
 sentencepiece>=0.2.0
 numpy==1.26.0
-torch>=2.4.0
-torchvision>=0.19.0
-gradio>=4.44.0
+torch>=2.5.0
+torchvision>=0.20.0
+gradio>=5.4.0
 imageio>=2.34.2
 imageio-ffmpeg>=0.5.1
 openai>=1.45.0

requirements.txt

@@ -1,15 +1,14 @@
-diffusers>=0.30.3
-accelerate>=0.34.2
-transformers>=4.44.2
+diffusers>=0.31.0
+accelerate>=1.0.1
+transformers>=4.46.1
 numpy==1.26.0
-torch>=2.4.0
-torchvision>=0.19.0
+torch>=2.5.0
+torchvision>=0.20.0
 sentencepiece>=0.2.0
 SwissArmyTransformer>=0.4.12
-gradio>=4.44.0
+gradio>=5.4.0
 imageio>=2.35.1
 imageio-ffmpeg>=0.5.1
-openai>=1.45.0
+openai>=1.53.0
 moviepy>=1.0.3
-pillow==9.5.0
-scikit-video
+scikit-video>=1.1.11