Trajectory-Regularized Distribution Distillation for One-Step Generation
cs.CV, cs.AI
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/happyw1nd/TRD
Terminology
Sources
- Classifier-Free Diffusion Guidance
- Distribution Matching Distillation without Fake Score Network
- Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs