update

Author: BrianChen1129

content/blogs/fastvideo_post_training/index.md

@@ -34,7 +34,7 @@ With this blog, we are releasing the following models and their recipes:
 |:-------------------------------------------------------------------------------------------:	|:---------------------------------------------------------------------------------------------------------------:	|:--------------------------------------------------------------------------------------------------------:	|
 | [FastWan2.1-T2V-1.3B](https://huggingface.co/FastVideo/FastWan2.1-T2V-1.3B-Diffusers)       	|    [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P)    	| [FastVideo Synthetic Wan2.1 480P](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x448x832_600k)     	|
 | [FastWan2.1-T2V-14B-Preview](https://huggingface.co/FastVideo/FastWan2.1-T2V-14B-Diffusers) 	|                                                   Coming soon!                                                  	|   [FastVideo Synthetic Wan2.1 720P](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x768x1280_250k)  	|
-| [FastWan2.2-TI2V-5B-FullAttn](https://huggingface.co/FastVideo/FastWan2.2-TI2V-5B-Diffusers)         	| [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.2-TI2V-5B-Diffusers/Data-free) 	| [FastVideo Synthetic Wan2.2 720P](https://huggingface.co/datasets/FastVideo/Wan2.2-Syn-121x704x1280_32k) 	|
+| [FastWan2.2-TI2V-5B-FullAttn](https://huggingface.co/FastVideo/FastWan2.2-TI2V-5B-Diffusers)         	| [Recipe](https://github.com/hao-ai-lab/FastVideo/tree/main/examples/distill/Wan2.2-TI2V-5B-Diffusers-FullAttn/Data-free) 	| [FastVideo Synthetic Wan2.2 720P](https://huggingface.co/datasets/FastVideo/Wan2.2-Syn-121x704x1280_32k) 	|
 
 
 For FastWan2.2-TI2V-5B-FullAttn, since its sequence length is short and doesn't benefit much from VSA, we only apply DMD with full attention. We are actively working on applying sparse distillation to 14B models for both Wan2.1 and Wan2.2 and will be releasing those checkpoints over the following weeks. Follow our progress at our [Github](https://github.com/hao-ai-lab/FastVideo), [Slack](https://join.slack.com/t/fastvideo/shared_invite/zt-38u6p1jqe-yDI1QJOCEnbtkLoaI5bjZQ) and [Discord](https://discord.gg/Dm8F2peD3e)!
@@ -72,7 +72,11 @@ Video diffusion models are incredibly powerful, but they've long been held back
 1. The huge number of denoising steps needed to generate a video. 
 2. The quadratic cost of attention when handling long sequences — which are unavoidable for high-resolution videos. Taking Wan2.1-14B as an example, the models run for 50 diffusion steps, and generating just a 5-second 720P video involves processing over 80K tokens. Even worse, attention operations can eat up more than 85% of total inference time.
 
+<<<<<<< HEAD
 Sparse distillation is our core innovation in FastWan2.1 — the first method to **jointly train sparse attention and denoising step distillation in a unified framework**. At its heart, sparse distillation answers a fundamental question: *Can we retain the speedups from sparse attention while applying extreme diffusion compression (e.g., 3 steps instead of 50)?* Prior work says no — and in the following sections we show why that answer changes with Video Sparse Attention (VSA). 
+=======
+Sparse distillation is our core innovation in FastWan — the first method to **jointly train sparse attention and denoising step distillation in a unified framework**. At its heart, sparse distillation answers a fundamental question: *Can we retain the speedups from sparse attention while applying extreme diffusion compression (e.g., 3 steps instead of 50)?* Prior work says no — and in the following sections we show why that answer changes with Video Sparse Attention (VSA). 
+>>>>>>> 969b5d9136d5021acf3334fc8dbc9d9aae7e4ef4
 
 ### Why Existing Sparse Attention Fails Under Distillation
 Most prior sparse attention methods (e.g., [STA](https://arxiv.org/pdf/2502.04507), [SVG](https://svg-project.github.io/)) rely on redundancy in multi-step denoising to prune attention maps. They often sparsify only late-stage denoising steps and retain full attention in early steps. However, when distillation compresses 50 steps into 1–4 steps, there’s no “later stage” to sparsify — and the redundancy they depend on vanishes. As a result, these sparse patterns no longer hold up. Our preliminary experiments confirm that existing sparse attention schemes degrade sharply under sub-10 step setups. This is a critical limitation. While sparse attention alone can yield up to 3× speedup, distillation offers more than 20× gains. We argue that to make sparse attention truly effective and production-ready, it must be compatible with training and distillation.