DiT
DiT is a model in our research taxonomy.
Related papers
- Beyond Pixel Histories: World Models with Persistent 3D State
- DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
- DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
- A Random Matrix Theory Perspective on the Consistency of Diffusion Models
- CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video
- Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory