Fine-tuning
Consistent Generative Video: Building Video Models That Remember
Our short summary of JioHotstar’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on blog.hotstar.com (opens in a new tab)Problem
Users wanted realistic talking‑head videos of IP characters without reshooting, but existing models drifted in identity and lip sync.
Solution
They trained tiny LoRA adapters on two video diffusion models, keeping the base frozen and adding only ~0.1% new parameters per layer, enabling fast, scalable character‑specific generation.
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on blog.hotstar.com (opens in a new tab)