๐
All in one framework
Inference and fine-tune state-of-the-art video generation models
๐
Pre-training
Build your own foundational text-to-video model
๐
Continuous training
Keep improving your model with new data
๐
Domain-specific
Adapt models to your specific scenario
๐
Concept-specific
Teach your models with unique concepts
๐
Language understanding
Improve model's comprehension through training
๐
Post-processing
Enhance videos with enhancement model
๐
Human alignment
Post-training with RLHF for better results
