Tools Bilawal Sidhu has publicly discussed or demonstrated using. Curated by Magpie's editorial team from podcasts, posts, and public stacks.
About
Bilawal Sidhu is a generative video and 3D creator and host of the TED AI podcast. Previously at Google on AR products, he now posts daily on X about generative video, neural rendering, and 3D capture tools.
Sidhu is one of the most-watched commentators on Runway's video model releases. He posts breakdowns of new Runway features as they ship and pairs Runway output with 3D Gaussian Splatting and photogrammetry workflows in his hybrid pipelines. He frames Runway as the go-to for AI video synthesis when paired with traditional 3D capture for fidelity.
turning a collection of 2d photos into a 3d model never gets old. it's damn near magic. in terms of technique: i love photogrammetry. i love radiance fields. therefore i love 3d gaussian splatting.
Sidhu posts Midjourney workflows including video-conditioned and 3D-feed pipelines on X. He treats Midjourney as the high-quality stills primitive that feeds into his hybrid creative pipelines (often paired with Runway for video and 3D capture tools for spatial work).
Mixing 3d models with real world scans (made w/ 3d gaussian splatting) is a powerful combination. And when you do it all inside an unbiased, physically accurate 3d rendered like Octane - the fidelity is truly next level.
Sidhu uses ElevenLabs for voice generation in his AI-video pipeline and on the TED AI podcast. He treats ElevenLabs as the production-grade voice layer in any AI creative output that needs broadcast-quality audio.
Sidhu reviews and demonstrates Pika alongside Runway as the two-horse race in AI video synthesis. He posts side-by-side comparisons and treats both as serious creative-pipeline options for short-form generated video.
These tools have been mentioned by the people featured in podcasts, interviews, posts, and other public media. Source links and citations are included wherever possible. Magpie AI has no direct relationship with the people on these pages. Spot a missing tool or a wrong attribution? Suggest a correction →