CrossDistill is a trajectory-level hybrid few-step distillation framework for diffusion models that balances quality and diversity by splitting the sampling trajectory at a crossover point. The high-noise interval uses a trajectory-preserving objective to maintain global mode coverage, while the low-noise interval applies a distribution-matching objective to sharpen local details, with the two stages coupled through the crossover state. This noise-level scheduling policy, demonstrated on text-to-video and image-to-video diffusion models, expands the few-step quality-diversity frontier by preserving seed-level variation while achieving competitive visual fidelity.
arXiv:2608. 09637v1 Announce Type: cross Abstract: Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment.
Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation alleviates this cost, yet exposes a quality--diversity trade-off between its two dominant paradigms: trajectory-level distillation (e.
The paper introduces Uncertainty DMD, a lightweight framework that injects uncertainty into few-step autoregressive video distillation to counteract diversity collapse. By perturbing the first chunk’s timestep and employing a stochastic cache-writing mechanism for subsequent chunks, the method restores stochasticity without altering the model architecture. Experiments demonstrate consistent improvements in video diversity and motion dynamics while preserving visual quality.
arXiv:2601. 09881v2 Announce Type: replace-cross Abstract: Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process.
arXiv:2606. 02453v1 Announce Type: cross Abstract: Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse.
The paper introduces DM-Align, a single-stage optimization framework that jointly performs distribution matching for distillation and aligns video generative models with human preferences. By deriving complementary gradient directions—one minimizing the gap between real and fake models and another guiding the model toward preferred samples—the method eliminates the need for separate reinforcement learning and distillation stages. Experiments on multiple foundational video models show that this sample-guided approach consistently outperforms both standalone variants and traditional two-stage pipelines.
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both...
ViRDM is a new post‑training method for few‑step causal video generation that eliminates the need for a large teacher model and an online critic. By applying representation distribution matching (RDM) with a precomputed target distribution, a lightweight VAE decoder, and staged vector–Jacobian products, ViRDM overcomes memory, optimization, and temporal dynamics challenges. The approach reduces GPU memory usage and training time, achieving state‑of‑the‑art VBench performance with only 20 generator updates and 16 A100 GPU‑hours.
LiveVVT introduces a rolling streaming diffusion framework for video virtual try‑on that maintains high visual fidelity while enabling real‑time performance. By confining bidirectional spatio‑temporal modeling to a fixed‑size window and using bounded temporal and global appearance memories, it emits clean video chunks with low latency. A progressive distillation pipeline further refines the model, achieving superior quality with 26× lower latency and 11× higher throughput compared to prior methods.
arXiv:2506. 13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation.
LiveVVT introduces a rolling streaming diffusion framework for video virtual try‑on that maintains high visual fidelity while enabling real‑time performance. It preserves bounded bidirectional modeling within a fixed‑size window, emits clean video chunks iteratively, and uses two memory modules—a bounded temporal memory and a persistent global appearance memory—to sustain long‑term consistency. A progressive distillation process further aligns teacher‑based bidirectional learning with causal few‑step inference, resulting in superior generation quality with 26× lower latency and 11× higher throughput compared to comparable models.
Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is high-variance and blind to global shape consistency. Prior work addresses this by retraining the diffusion prior on multi-view data; this improves consistency but makes the sampling contribution inseparable from prior quality.