Now even Netflix has its own video AI • The Register A new Netflix model promises to rewrite the way we make movies Just imagine this As the director of the multi-million dollar epic Car Crash III: Suddenest Impact, you've just finished filming the finale where your star, Cruz Control, drives straight into an onrushing semi The collision is
Netflix Releases VOID Video Inpainting Model | Lets Data Science Netflix researchers on April 3, 2026 published a preprint and released VOID, a vision-language model that removes objects from video and inpaints physically plausible outcomes The model, authored by Netflix and Sofia University researchers, is available on Hugging Face and was preferred in human tests—64 8 percent versus 18 4 percent for Runway—across synthetic and real-world scenarios
netflix void-model · Hugging Face VOID removes objects from videos along with all interactions they induce on the scene — not just secondary effects like shadows and reflections, but physical interactions like objects falling when a person is removed Project Page | Paper | GitHub | Demo
GitHub - Netflix void-model VOID uses two transformer checkpoints, trained sequentially You can run inference with Pass 1 alone or chain both passes for higher temporal consistency Place checkpoints anywhere and pass the path via --config video_model transformer_path (Pass 1) or --model_checkpoint (Pass 2)
Now even Netflix has its own video AI - Briefly Now even Netflix has its own video AI Netflix's VOID model, which stands for Video Object and Interaction Deletion, enables filmmakers to modify scenes by erasing objects and generating new content
Thomas Claburn • The Register His specialty lies in government IT, software development, and the ethical use of artificial intelligence Thomas has nearly 30 years of experience in technology publishing, including roles ranging from magazine section editor to editor-at-large I see you're trying to kill children Would you like some help with that? Chat at your own risk!