类库
› daVinci-MagiHuman
GAIR-NLP/daVinci-MagiHuman
daVinci-MagiHuman是一个用于生成音频-视频内容的单流Transformer基础模型。它能根据文本快速生成高质量、富有表现力的人像视频，包含同步的语音和动作，支持多种语言。特点包括推理速度快、生成质量高，并完全开源模型和代码。
技术栈
查看全部依赖 (31)
依赖
Pandas
unknown
Pydantic
unknown
accelerate
unknown
av
unknown
beautifulsoup4
unknown
boto3
unknown
debugpy
unknown
depyf
unknown
diffusers
unknown
ffmpeg-python
unknown
ftfy
unknown
graphviz
unknown
imageio
unknown
loguru
unknown
mosaicml_streaming
unknown
numba
unknown
packaging
unknown
psycopg2-binary
unknown
pydantic-settings
unknown
redis
unknown
redislite
unknown
rich
unknown
scipy
unknown
sentencepiece
unknown
setuptools
unknown
soundfile
unknown
timm
unknown
torchao
unknown
transformers
unknown
unfoldNd
unknown
versioningit
unknown
截图
