Models just want to generalize. For the past years, we’ve been pushing the frontier of controllability in video, releasing new models and techniques for inpainting, outpainting, segmentation, stylization, keyframing, motion and camera control. Aleph is a single in-context model that can solve all of those tasks at once, as well as other ones (e.g. novel view synthesis), in many cases with zero task-specific training. The recipe of References continues to work, and scaled to new heights.