What is Wan2.2 built with?
Wan2.2 is a Python repo built with Lightning. It uses AI through accelerate, conformer, openai-whisper, pyworld, sentencepiece, and 14 more, makes its content with imageio-ffmpeg, decord, and imageio, deploys with loguru, and uses pyarrow. It has 19,152 written lines.
Read on November 6, 2026, at commit 1ea34ff. Read it as markdown
Frontend
Interface 2
matplotlib1 file
- Rich
Backend
Data 1
AI 19
- torch38 files
diffusers9 files
opencv-python7 files
torchvision6 files
peft2 files
dashscope1 file
librosa1 file
- ModelScope1 file
torchaudio1 file
accelerate
openai-whisper
tokenizers
- flash-attn4 files
- transformers3 files
- onnxruntime1 file
- conformer
- pyworld
- sentencepiece
- wetext
Other repos with a similar stack
Ordered by how much of its stack they share with Wan2.2, then by stars.
- debpalashVoiceStudio100.7k
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
17 of 39 in commonCompare → - jianchang512pyvideotrans19.6k
Translate the video from one language to another and embed dubbing & subtitles.
16 of 39 in commonCompare → - bojieliai-agent-book57.2k
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
13 of 39 in commonCompare → - hpcaitechColossalAI41.4k
Making large AI models cheaper, faster and more accessible
13 of 39 in commonCompare →
Frequently asked questions
What language is Wan2.2 written in?
What framework does Wan2.2 use?
Does Wan2.2 use AI?
What services does Wan2.2 use?
Which repos have a stack like Wan2.2's?
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.
Is it your repo? Add its badge, keep it up to date or take it down →

