arXiv Computer Vision
SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 25
Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
arXiv:2604.24136v3 Announce Type: replace Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohi...
arXiv Computer Vision
Aug 26
On-Policy Self-Distillation in Diffusion Models
The paper introduces DiffusionOPSD, an on‑policy self‑distillation framework that transforms image‑level reinforcement learning rewards into explicit targets for intermediate denoising predictions in diffusion models. By generating trajectories with a frozen behavior policy and constructing bounded positive and negative targets around query states, the method trains a policy to fit these targets before updating the behavior policy via an exponential moving average. Experiments on SD 3.5‑M and Z‑Image‑Turbo show that DiffusionOPSD achieves the best held‑out scores in 19 of 20 reward‑matched settings, outperforms the strongest competitor by up to 44 % and cuts GPU‑hour usage by 40–63 % compared to DiffusionNFT.
arXiv AI
Jul 9
Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation
arXiv:2607. 06631v1 Announce Type: cross Abstract: Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs.
Hugging Face Trending Papers
Jul 9
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low latency, but still suffer from error accumulation and weakened motion dynamics during long autoregressive rollout.
arXiv Machine Learning
Jun 9
Optimizing Few-Step Generation with Adaptive Matching Distillation
arXiv:2602. 07345v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force.
arXiv Computer Vision
3d ago
Improving Image-to-Image Translation via a Rectified Flow Reformulation
arXiv:2603.20186v2 Announce Type: replace Abstract: In this work, we propose Image-to-Image Rectified Flow Reformulation (I2I-RFR), a practical plug-in reformulation that recasts standard I2I regress...