nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
lb203
2024-07-24 19:14:11 +08:00
committed by GitHub
parent ae5679185c
commit 3a8c34efd0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -49,7 +49,7 @@ This project aims to create a simple and scalable repo, to reproduce [Sora](http
Open-Sora Plan shows excellent performance in video generation.
### 🔥 High performance CausalVideoVAE, but with fewer training cost
- High compression ratio with excellent performance, capable of **compressing videos by 256 times (4×8×8)**. Causal convolution supports simultaneous inference of images and videos.
- High compression ratio with excellent performance, capable of **compressing videos by 256 times (4×8×8)**. Causal convolution supports simultaneous inference of images and videos but only need **1 node to train**.
### 🚀 Video Diffusion Model based on 3D attention, joint learning of spatiotemporal features.
- With a **3D full attention architecture** instead of a 2+1D model, 3D attention can better capture joint spatial and temporal features.