Diffusers
Safetensors
WanPipeline
BrianChen1129 commited on
Commit
629816d
·
verified ·
1 Parent(s): 74b3b88

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ license: apache-2.0
20
  ## Model Overview
21
  - This model is finetuned with [VSA](https://arxiv.org/pdf/2505.13389), based on [Wan-AI/Wan2.1-T2V-14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers).
22
  - It achieves up to 2.1x speed up on a single **H100** GPU.
23
- - Our model is trained on **77×768×1280** resolution, but it supports generating videos with any resolution.(quality may degrade).
24
  - We set **VSA attention sparsity** to 0.9, and training runs for **1500 steps (~14 hours)**. You can tune this value from 0 to 0.9 to balance speed and performance for inference.
25
  - Finetuning and inference scripts are available in the [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository:
26
  - [1 Node/GPU debugging finetuning script](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/finetune/finetune_v1_VSA.sh)
 
20
  ## Model Overview
21
  - This model is finetuned with [VSA](https://arxiv.org/pdf/2505.13389), based on [Wan-AI/Wan2.1-T2V-14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers).
22
  - It achieves up to 2.1x speed up on a single **H100** GPU.
23
+ - Our model is trained on **77×768×1280** resolution, but it supports generating videos with **any resolution**.(quality may degrade).
24
  - We set **VSA attention sparsity** to 0.9, and training runs for **1500 steps (~14 hours)**. You can tune this value from 0 to 0.9 to balance speed and performance for inference.
25
  - Finetuning and inference scripts are available in the [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository:
26
  - [1 Node/GPU debugging finetuning script](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/finetune/finetune_v1_VSA.sh)