fix: correct facial alignment issues and add API server

feat: update download_weights.bat (#372)

fix: convert all audio to WAV 16kHz PCM before processing (#379)

fix: ensure upper bond does not go below zero in landmark extraction (#329)

fix: preprocess import bug (#345)

fix: use torch.no_grad() in inference to prevent excessive memory usage (~30GB) with inference (#349)

fix: download_weights.sh (#318)

feat: windows infer & gradio (#312)

Update audio_processor.py

docs: update readme

feat: data preprocessing and training (#294)

fix: floor (#293)

fix: bug in infer script (#290)

feat: real-time infer (#286)

Update README.md

Merge pull request #282 from zzzweakman/fix/infer

fix: unet config

Merge pull request #281 from zzzweakman/fix/infer

fix: infer bug

Merge pull request #275 from TMElyralab/v15

update readme

v1.5

Update README.md

Merge pull request #206 from WangShaoyu1/patch-1

Create __init__.py

Update README.md

Add import copy to blending.py

Merge pull request #131 from lipku/main

Release technical report

Update README.md

Update app.py

Update README.md

Update README.md

improve blending speed

Update README.md

Release MusePose

<BUGFIX>: fix app.py (#47)

<enhance>: support using float16 in inference to speed up

Update README and LICENSE

<enhance>(inference): support using an image as video input(#17 #34)

Fix fps calculation bug in realtime_inference.py (#35)

Add codes for real time inference

Merge pull request #31 from tobycroft/main

Update requirements.txt

Update app.py

Update README.md

Add gradio

Merge pull request #5 from hotea/main

Update README.md

fix some cuda related issue when run on M-Series Mac