Today in Generative Media

The future of AI is video; genAI is inefficient; extract video clips using Munch

• The future of AI is video, and it’s coming at us fast (TechCrunch)

• We still haven’t cracked the code on making generative AI any more efficient (FastCompany)

• Extract the most engaging and impactful clips from your long-form videos using Munch, the #1 AI video repurposing platform (getmunch.com)

• 3D humans from a photo: the data needed to train Volograms AI (Medium)

• AudioCraft is a single-stop code base for all your generative audio needs: music, sound effects, and compression after training on raw audio signals. (Meta) Code on GitHub.

• GeNVS: Generative Novel View Synthesis with 3D-Aware Diffusion Models (ICCV 2023, project page)

• ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation (arXiv)

• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects (arXiv)

• today’s work on post-photography (gen.ericai on X)