✨Flow Map Distillation Without Data

📝 Summary:
This paper introduces a data-free framework for flow map distillation, eliminating the need for external datasets. By sampling only from the prior distribution, it avoids data mismatch risks and achieves state-of-the-art fidelity with minimal sampling steps, surpassing all data-based alternatives.

🔹 Publication Date: Published on Nov 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.19428
• PDF: https://arxiv.org/pdf/2511.19428

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#FlowMapDistillation #DataFreeLearning #MachineLearning #DeepLearning #AIResearch

🔥 AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

💡 The paper introduces AnyFlow, a novel framework for any-step video diffusion distillation that improves upon existing consistency distillation methods. The problem with consistency distillation is that its performance degrades as more sampling steps are used at test time, limiting its effectiveness for any-step video diffusion. This is because consistency distillation replaces the original probability-flow ODE trajectory with a consistency-sampling trajectory, which weakens the desirable test-time scaling behavior of ODE sampling.

To address this limitation, AnyFlow optimizes the full ODE sampling trajectory instead of distilling a model for only a few fixed sampling steps. The method involves shifting the distillation target from endpoint consistency mapping to flow-map transition learning over arbitrary time intervals. Additionally, the authors propose Flow Map Backward Simulation, which decomposes a full Euler rollout into shortcut flow-map transitions, enabling efficient on-policy distillation that reduces test-time errors.

The results of the paper show that AnyFlow achieves performance that matches or surpasses consistency-based counterparts in the few-step regime, while also scaling with sampling step budgets. The experiments were conducted across both bidirectional and causal architectures, at scales ranging from 1.3B to 14B parameters. Overall, the paper contributes a new framework for any-step video diffusion distillation that improves upon existing methods and achieves state-of-the-art results.

📅 Published on May 13

🔗 Links:
• arXiv: https://arxiv.org/abs/2605.13724
• PDF: https://arxiv.org/pdf/2605.13724
• Project Page: https://nvlabs.github.io/AnyFlow/
• GitHub: https://github.com/NVlabs/AnyFlow ⭐ 197

🤖 Models citing this paper:
• https://huggingface.co/nvidia/AnyFlow-Wan2.1-T2V-14B-Diffusers
• https://huggingface.co/nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers
• https://huggingface.co/nvidia/AnyFlow-FAR-Wan2.1-14B-Diffusers

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VideoDiffusionModels #OnPolicyLearning #FlowMapDistillation #AnyStepSampling #DiffusionBasedGenerativeModels