Netflix open-sources ID-V2V, a video restyling model that preserves identity and lip-sync

Netflix's Eyeline Labs has open-sourced ID-V2V under Apache 2.0, a video-to-video restyling model that swaps scenes, lighting and visual style while preserving facial identity, performance and lip-sync, following a "shoot first, restyle later" philosophy.

2026-09-08 ~ 2026-09-08 · 4 related posts

• Netflix releases ID-V2V, an AI that restyles video while keeping faces and lip sync — minchoi · 2026-09-08
• ID-V2V's core idea: shoot first, restyle later without losing the performance — minchoi · 2026-09-08
• ID-V2V goes open source under Apache 2.0: identity-preserving video restyle with relighting at 720p — minchoi · 2026-09-08
• ID-V2V weights land on Hugging Face: Wan 2.1 + VACE, two checkpoints including normal/depth control — minchoi · 2026-09-08