Episodes
Find all the episodes !
EP125 - Kandinsky 3.0 Technical Report
·2 mins
EP124 - Relightable Gaussian Codec Avatars
·2 mins
EP123 - Cache Me if You Can: Accelerating Diffusion Models through Block Caching
·3 mins
EP122 - Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models
·3 mins
EP121 - LooseControl: Lifting ControlNet for Generalized Depth Conditioning
·2 mins
EP120 - MagicStick: Controllable Video Editing via Control Handle Transformations
·2 mins
EP119 - Language-Informed Visual Concept Learning
·2 mins
EP118 - DragVideo: Interactive Drag-style Video Editing
·2 mins
EP117 - Orthogonal Adaptation for Modular Customization of Diffusion Models
·3 mins
EP116 - X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model
·3 mins