# SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer arXiv: https://arxiv.org/abs/2605.30409 ยท HTML: https://mlsanity.com/paper/2605.30409/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Placed in Video generation, one of 14 directions in Diffusion models. - Builds on 40 of its 42 references that are in the map. - First posted on arXiv 28 May 2026. ## Placed in - Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/) ## Builds on (most cited first, 30 of 40) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021) - [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016) - [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023) - [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023) - [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019) - [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024) - [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023) - [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024) - [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024) - [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025) - [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023) - [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024) - [Gated Linear Attention Transformers with Hardware-Efficient Training](https://mlsanity.com/paper/2312.06635/) (2023) - [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021) - [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025) - [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024) - [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025) - [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025) - [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026) - [Kimi Linear: An Expressive, Efficient Attention Architecture](https://mlsanity.com/paper/2510.26692/) (2025) - [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026) - [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://mlsanity.com/paper/2501.18427/) (2025) - [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://mlsanity.com/paper/2509.24695/) (2025) - [SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://mlsanity.com/paper/2503.09641/) (2025) - [Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset](https://mlsanity.com/paper/2510.15742/) (2025) ## Built on by (most cited first, 11 of 11) - [LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing](https://mlsanity.com/paper/2606.26740/) (2026) - [JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion](https://mlsanity.com/paper/2608.03974/) (2026) - [Instruction-Based Video Editing by Repurposing an Image Editing Model](https://mlsanity.com/paper/2608.14790/) (2026) - [SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation](https://mlsanity.com/paper/2607.21553/) (2026) - [EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing](https://mlsanity.com/paper/2608.21424/) (2026) - [ReGenVC: End-to-End Real-Time Generative Video Coding at Ultra-Low Bitrate](https://mlsanity.com/paper/2607.28144/) (2026) - [DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation](https://mlsanity.com/paper/2610.03543/) (2026) - [Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU](https://mlsanity.com/paper/2606.05981/) (2026) - [InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter](https://mlsanity.com/paper/2608.20910/) (2026) - [EditaLive! Unified Character Video Editing for Live Streaming](https://mlsanity.com/paper/2608.27123/) (2026) - [No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation](https://mlsanity.com/paper/2609.38691/) (2026) ## Abstract (arXiv) Real-time streaming video-to-video editing (V2V) is critical for interactive applications such as live broadcasting and gaming, yet it remains a formidable challenge due to the stringent requirements for temporal consistency and inference throughput. In this paper, we present SANA-Streaming, a system-algorithm co-designed framework for high-resolution, real-time streaming video editing on consumer GPUs, with the following three core designs: (1) Hybrid Diffusion Transformer architecture introduces softmax attention in part of the blocks to improve local modeling capabilities while preserving the efficiency of linear layers. (2) Cycle-Reverse Regularization is a novel training strategy that enforces semantic consistency by predicting source frames from generated content via flow matching, improving temporal consistency without requiring paired long edited videos. (3) Efficient System Co-design combines fused GDN kernels and Mixed-Precision Quantization (MPQ) optimized for the NVIDIA Blackwell (RTX 5090) architecture. By profiling real-world throughput, our MPQ maximizes Tensor Core utilization while maintaining generation quality. The resulting system achieves real-time 1280 x 704 resolution editing at 24 end-to-end FPS on a single RTX 5090 GPU, with the DiT core running at 58 FPS. Experimental results demonstrate that our co-design approach significantly outperforms existing SOTA methods in both temporal coherence and system throughput.