This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Alexandre Morgand, PhD
alexmrgd.bsky.social
did:plc:qzv3sbnfuvuzmykdl57zzdiv
Pippo : High-Resolution Multi-View Humans from a Single Image
TL;DR: 1K Multiview Diffusion Transformer pre-trained on 3B Human images without captions; post-trained on 2.5K studio captures with pixel-aligned control via ControlMLP; generates > 5x views at inference
2025-02-18T10:16:55.751Z