SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

arXiv:2609.37969 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Project page: https://nvlabs.github.io/Sana/Sol-Engine/H3-Super-Acceleration

Terminology

• Distillation — 27× in this paper · explained in 2 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Fidelity — 8× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Distribution Matching — 4× in this paper · explained in 2 episodes
• Flow Matching — 4× in this paper · explained in 8 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Imagen Video: High Definition Video Generation with Diffusion Models
• Seedance 1.0: Exploring the Boundaries of Video Generation Models
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Wan: Open and Advanced Large-Scale Video Generative Models
• MobileWan: Closing the Quality Gap for Mobile Video Diffusion
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• MarDini: Masked Autoregressive Diffusion for Video Generation at Scale
• SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
• Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
• Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
• VEnhancer: Generative Space-Time Enhancement for Video Generation
• Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution
• SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
• DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
• UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space
• SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
• FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
• Improved Distribution Matching Distillation for Fast Image Synthesis
• SF-V: Single Forward Video Generation Model

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