FADE: Fractional Anomalous Dynamics Extrapolation for Training-Free Diffusion Transformers Acceleration
cs.LG, cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/black-forest-labs/flux
Project page: https://youngkinlon.github.io/fade-project-page
Terminology
Sources
- HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- Structural Pruning for Diffusion Models
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Variational Autoencoders with Riemannian Brownian Motion Priors
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Hessian Geometry of Latent Space in Generative Models
- Token Caching for Diffusion Transformer Acceleration
- ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
- Progressive Distillation for Fast Sampling of Diffusion Models
- Denoising Diffusion Implicit Models
- Consistency Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis