Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation

• URL: http://arxiv.org/abs/2606.18478v2
• Date: Tue, 23 Jun 2026 08:04:55 GMT
• Title: Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
• Abstract summary: We propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change.<n>We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation.
• Score: 25.352409052792122
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its successor DMD2 achieved strong generation quality and fast convergence. However, due to the nature of the reverse Kullback--Leibler (KL) objective, these methods exhibit two persistent failure modes: a substantial drop in sample diversity, and visibly over-saturated outputs that deviate from real-video appearance. In this work, we propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change. At its core is the teacher score discrepancy to guide the student toward the real-data distribution, pulling it to missing modes (mitigating mode collapse) and away from problematic modes absent in real data (avoiding over-saturation). We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation. With only 100--300 steps of finetuning, DFD effectively restores diversity and fidelity on both Wan2.1-1.3B and Cosmos-Predict2.5-2B model, resolving the over-saturation artifacts with significantly better video dynamics and appearance, and even outperforms the teacher model.

Related papers

• Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout [28.90854720290184]
  Recent methods distill pretrained bidirectional video diffusion models into causal AR students through Distribution Matching Distillation (DMD)<n>The generated videos often suffer from over-saturation and over-smoothing issues, resulting in limited visual quality and realism.<n>We propose Mask Forcing, a Dual-Noise Masking Rollout strategy that perturbs the AR student self-rollout to mitigate mode collapse.
  arXiv  Detail & Related papers  (2026-09-08T17:50:05Z)
• Parallel Decoding Distillation for Fast Image and Video Generation [35.18845060233149]
  We introduce Parallel Decoding Distillation (PDD) for fast inference of diffusion and flow matching models.<n>PDD accelerates generation by predicting multiple denoising steps per network evaluation.<n>Our method achieves SOTA performance with 4-8 NFE on LTX-2.3 Text-to-Video/Audio, Wan 14B Text-to-Video, and Qwen-Image Text-to-Image.
  arXiv  Detail & Related papers  (2026-07-28T17:20:00Z)
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models [49.369312232769154]
  We introduce Causal-rCM, a leading, unified, and scalable algorithm-infrastructure open recipe for diffusion distillation and causal training.<n>We achieve state-of-the-art streaming video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training.
  arXiv  Detail & Related papers  (2026-06-24T06:58:02Z)
• Transition Matching Distillation for Fast Video Generation [63.1049790376783]
  We present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators.<n>TMD matches the multi-step denoising trajectory of a diffusion model with a few-step probability transition process.<n>TMD provides a flexible and strong trade-off between generation speed and visual quality.
  arXiv  Detail & Related papers  (2026-01-14T21:30:03Z)
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency [60.74505433956616]
  continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion.<n>We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks.<n>We propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer.
  arXiv  Detail & Related papers  (2025-10-09T16:45:30Z)
• Dual-Expert Consistency Model for Efficient and High-Quality Video Generation [57.33788820909211]
  We propose a parameter-efficient textbfDual-Expert Consistency Model(DCM), where a semantic expert focuses on learning semantic layout and motion, while a detail expert specializes in fine detail refinement.<n>Our approach achieves state-of-the-art visual quality with significantly reduced sampling steps, demonstrating the effectiveness of expert specialization in video diffusion model distillation.
  arXiv  Detail & Related papers  (2025-06-03T17:55:04Z)
• Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework [127.61297651993561]
  A variety of Auto-Regressive Video Diffusion Models (ARVDM) have achieved remarkable successes in generating realistic long-form videos.<n>We develop theoretical underpinnings for these models and use our insights to improve the performance of existing models.
  arXiv  Detail & Related papers  (2025-03-12T15:32:44Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation [60.54811860967658]
  FluxSR is a novel one-step diffusion Real-ISR based on flow matching models.<n>First, we introduce Flow Trajectory Distillation (FTD) to distill a multi-step flow matching model into a one-step Real-ISR.<n>Second, to improve image realism and address high-frequency artifact issues in generated images, we propose TV-LPIPS as a perceptual loss.
  arXiv  Detail & Related papers  (2025-02-04T04:11:29Z)
• Supercharged One-step Text-to-Image Diffusion Models with Negative Prompts [19.609393551644562]
  We introduce textbfNegative-textbfAway textbfSteer textbfAttention (NASA), an efficient method that integrates negative prompts into one-step diffusion models.<n>NASA operates within the intermediate representation space by leveraging cross-attention mechanisms to suppress undesired visual attributes.
  arXiv  Detail & Related papers  (2024-12-03T18:56:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.