Amaan9136

Amaan9136/wan-qwen-musetalk-video-pipeline

Local text to video pipeline that turns a text prompt into a lip synced talking video. Wan2.1 handles video generation, Qwen3 TTS creates the voice, and MuseTalk 1.5 syncs the lips. Everything runs offline after the models are downloaded.

1 good first / help-wanted issue · Jupyter Notebook · last activity Sep 24, 2026

0 stars 0 forks 0 watchers Jupyter Notebook Other
ai-video-generation-api diffusion-models generative-ai lip-sync local-ai musetalk offline-ai open-source pytorch qwen-tts speech-synthesis talking-avatar text-to-speech text-to-video video-generation-api wan2-1 wan21
View on GitHub
1 Open Issue Need Help Last updated: Sep 24, 2026

Open Issues Need Help

View All on GitHub
[Tracking] Full end-to-end pipeline validation pending hardware/storage upgrade about 1 month ago
documentation enhancement help wanted
Amaan9136/wan-qwen-musetalk-video-pipeline
0

Local text to video pipeline that turns a text prompt into a lip synced talking video. Wan2.1 handles video generation, Qwen3 TTS creates the voice, and MuseTalk 1.5 syncs the lips. Everything runs offline after the models are downloaded.

Jupyter Notebook
#ai-video-generation-api#diffusion-models#generative-ai#lip-sync#local-ai#musetalk#offline-ai#open-source#pytorch#qwen-tts#speech-synthesis#talking-avatar#text-to-speech#text-to-video#video-generation-api#wan2-1#wan21