From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models

arXiv:2609.34371 · cs.CV, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Distillation — 31× in this paper · explained in 2 episodes
• Alignment — 30× in this paper · explained in 1 episode
• Diffusion Model — 18× in this paper · explained in 8 episodes
• Diffusion Models — 18× in this paper · explained in 6 episodes
• Latent Space — 10× in this paper · explained in 7 episodes
• On-Policy Distillation — 10× in this paper · explained in 3 episodes
• Consistency — 9× in this paper · explained in 3 episodes
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Fidelity — 7× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Temporal consistency — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Rectified Flow — 4× in this paper · explained in 3 episodes
• AUROC — 3× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Homogeneity — 3× in this paper · explained in 2 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Distribution Matching — 2× in this paper · explained in 2 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Optical Flow — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Prompt Adherence — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Flow-OPD: On-Policy Distillation for Flow Matching Models
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• LTX-Video: Realtime Video Latent Diffusion
• AesRM: Improving Video Aesthetics with Expert-Level Feedback
• LoRA: Low-Rank Adaptation of Large Language Models
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
• Decoupled Weight Decay Regularization
• Video Diffusion Alignment via Reward Gradients
• Make-A-Video: Text-to-Video Generation without Text-Video Data
• Wan: Open and Advanced Large-Scale Video Generative Models
• MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
• Mismatch Matters: On-Policy Distillation Beyond Token Agreement
• VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
• Accelerating Video Diffusion Models via Distribution Matching

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models