Metadata-Version: 2.1
Name: videox-fun
Version: 1.0.1
Summary: VideoX-Fun is a video generation pipeline that can be used to generate AI images and videos, as well as to train baseline and Lora models for Diffusion Transformer. We support direct prediction from pre-trained baseline models to generate videos with different resolutions, durations, and FPS. Additionally, we also support users in training their own baseline and Lora models to perform specific style transformations.
Home-page: https://github.com/aigc-apps/VideoX-Fun
Requires-Python: >=3.10
Requires-Dist: Pillow
Requires-Dist: einops
Requires-Dist: safetensors
Requires-Dist: timm
Requires-Dist: tomesd
Requires-Dist: torchdiffeq
Requires-Dist: decord
Requires-Dist: datasets
Requires-Dist: numpy
Requires-Dist: scikit-image
Requires-Dist: opencv-python-headless
Requires-Dist: omegaconf
Requires-Dist: SentencePiece
Requires-Dist: albumentations
Requires-Dist: imageio[ffmpeg]
Requires-Dist: imageio[pyav]
Requires-Dist: tensorboard
Requires-Dist: beautifulsoup4
Requires-Dist: ftfy
Requires-Dist: func_timeout
Requires-Dist: accelerate>=0.25.0
Requires-Dist: gradio>=3.41.2
Requires-Dist: diffusers>=0.30.1
Requires-Dist: transformers>=4.46.2
