π€π₯ Contributions welcome. Accepting Pull Requests.
π¬ Large Language Models
πΌοΈ Image Models
ποΈ Video Models
- π Text to video generation
- βοΈ Frame Interpolation (Temporal Interpolation)
- π― Segmentation & Tracking
- π Super Resolution (Spacial Interpolation)
- β²οΈ Spacio Temporal Interpolation
- π Benchmarking
π΅ Audio Models
- ποΈ Compression
- π Multiple Tasks
- π Speech Recognition
- π£οΈ TextToSpeech
- π Voice Conversion
- πΆ Music Generation