diffusion transformer
A diffusion transformer is a type of model that incorporates diffusion processes into its architecture, typically used in generative tasks, providing advantages in capturing complex distributions of data.
- Boosting Generative Image Modeling via Joint Image-Feature Synthesis
- DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
- Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
- FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation
- Frame In-N-Out: Unbounded Controllable Image-to-Video Generation
- Image Editing As Programs with Diffusion Models
- Localizing Knowledge in Diffusion Transformers
- OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers
- OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions
- On Inductive Biases That Enable Generalization in Diffusion Transformers
- ROSE: Remove Objects with Side Effects in Videos
- RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
- StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
- Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
- TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography
- Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling
- Training-Free Efficient Video Generation via Dynamic Token Carving
- U-REPA: Aligning Diffusion U-Nets to ViTs
- Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models