Upload folder using huggingface_hub

.gitattributes

@@ -42,9 +42,3 @@ assets/undistilled/1.gif filter=lfs diff=lfs merge=lfs -text
 assets/undistilled/2.gif filter=lfs diff=lfs merge=lfs -text
 assets/undistilled/3.gif filter=lfs diff=lfs merge=lfs -text
 assets/undistilled/4.gif filter=lfs diff=lfs merge=lfs -text
-assets/undistilled/A[[:space:]]majestic[[:space:]]lion[[:space:]]strides[[:space:]]across[[:space:]]the[[:space:]]golden[[:space:]]savanna,[[:space:]]its[[:space:]]powerful[[:space:]]frame[[:space:]]glistening[[:space:]]under[[:space:]]the[[:space:]]warm[[:space:]]afte.gif filter=lfs diff=lfs merge=lfs -text
-assets/undistilled/A[[:space:]]superintelligent[[:space:]]humanoid[[:space:]]robot[[:space:]]waking[[:space:]]up.[[:space:]]The[[:space:]]robot[[:space:]]has[[:space:]]a[[:space:]]sleek[[:space:]]metallic[[:space:]]body[[:space:]]with[[:space:]]futuristic[[:space:]]des.gif filter=lfs diff=lfs merge=lfs -text
-assets/undistilled/Man[[:space:]]walking[[:space:]]his[[:space:]]dog[[:space:]]in[[:space:]]the[[:space:]]woods[[:space:]]on[[:space:]]a[[:space:]]hot[[:space:]]sunny[[:space:]]day
-.gif filter=lfs diff=lfs merge=lfs -text
-assets/undistilled/fox[[:space:]]in[[:space:]]the[[:space:]]forest[[:space:]]close-up[[:space:]]quickly[[:space:]]turned[[:space:]]its[[:space:]]head[[:space:]]to[[:space:]]the[[:space:]]left
-.gif filter=lfs diff=lfs merge=lfs -text

README.md

@@ -20,12 +20,11 @@ FastHunyuan is an accelerated [HunyuanVideo](https://huggingface.co/tencent/Huny
 - **Distilled from**: [HunyuanVideo](https://huggingface.co/tencent/HunyuanVideo)
 - **Github Repository**: https://github.com/hao-ai-lab/FastVideo
 
-
 ## Usage
 
 - Clone [Fastvideo](https://github.com/hao-ai-lab/FastVideo) repository and follow the inference instructions in the README.
-- Alternatively, you can inference FastHunyuan using the official [Hunyuan Video repository](https://github.com/Tencent/HunyuanVideo) by  **setting the shift to 17, steps to 6, resolution to 720X1280X125, and cfg bigger than 6**.
-We find that a large CFG scale generally leads to faster videos.
+- Alternatively, you can inference FastHunyuan using the official [Hunyuan Video repository](https://github.com/Tencent/HunyuanVideo) by  **setting the shift to 17 and steps to 6**.
+
 ## Training details
 
 FastHunyuan is consistency distillated on the [MixKit](https://huggingface.co/datasets/LanguageBind/Open-Sora-Plan-v1.1.0/tree/main) dataset with the following hyperparamters: