Spaces:
Runtime error
Runtime error
|
Download notes.md from Stable-Human/Lip_Wise: direct link, hf CLI and curl.
- Browser
- Download file 1.32 kB
-
https://huggingface.co/spaces/Stable-Human/Lip_Wise/resolve/main/notes.md
- Command line
-
hf download hf://spaces/Stable-Human/Lip_Wise/notes.md
-
curl -L -o notes.md https://huggingface.co/spaces/Stable-Human/Lip_Wise/resolve/main/notes.md
1.32 kB
| # :memo: **TO-DO** List: | |
| ### PREPROCESS | |
| - [x] Add directory check in inference in the beginning. | |
| - [x] Make preprocessing optimal. | |
| - [x] Clear ram after no_face_filter. | |
| - [x] Make face coordinates reusable: | |
| - [x] Saving facial coordinates as .npy file. | |
| - [x] Alter code to also include eye coordinates. | |
| ### IMPROVING GAN UPSCALING | |
| - [x] Merge Data Pipeline with preprocessor: | |
| - [x] Remove need to recrop, realign and rewarp the image. | |
| ### IMPROVING WAV2LIP | |
| - [x] Merge all data Pipeline: | |
| - [x] Remove the need to recrop, realign, renormalizing etc. | |
| - [x] Devise a way to keep frames without face in the video. | |
| - [x] Understand Mels and working of wav2lip model. | |
| ### OPTIONAL | |
| - [ ] Gradio UI | |
| - [ ] A tab for configuration variables. | |
| - [x] A tab for Video, Audio and Output. | |
| - [x] A tab for Image, Audio and output. | |
| ### URGENT REQUIREMENTS | |
| - [ ] setup.py | |
| - [ ] create venv | |
| - [ ] install requirements inside venv | |
| - [ ] codeformer arch initialization | |
| - [ ] Documentation | |
| ### FURTHER IMPROVEMENTS | |
| - [ ] Inference without restorer | |
| - [ ] Model Improvement | |
| - [ ] Implement no_face_filter too | |
| ### FUTURE PLANS | |
| - [ ] Face and Audio wise Lipsync using face recognition. | |
| - [ ] A separate tab for TTS. | |
| ### COLAB NOTEBOOK | |
| - [ ] Optimize Inference. | |
| - [ ] Implement Checks. |