Completed
- Motivation for Image Pretraining
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Stable Video Diffusion: Model Architecture and Training Pipeline
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - Model Architecture
- 3 - Training Stages
- 4 - Image Pretraining Stage
- 5 - Motivation for Image Pretraining
- 6 - Video Curation Stage
- 7 - Video data curation pipeline
- 8 - LVD Dataset
- 9 - Filtering Mechanisms
- 10 - Optical Flow
- 11 - Synthetic Captions
- 12 - OCR Detection
- 13 - LVD dataset summarised
- 14 - Ablation studies
- 15 - High quality fine-tuning
- 16 - Base Model
- 17 - Tex-to-video example
- 18 - Image-to-video example
- 19 - Conclusion
