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

Update CausalVideoVAE.md

Browse Source 
Former-commit-id: fcde4d0ff783448c2006d6f4751a0e4f9cc23d0f
This commit is contained in:
lb203
2024-03-28 20:16:49 +08:00
committed by GitHub
parent f48b3da80a
commit 5dc588f47c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/CausalVideoVAE.md
+1 -1
View File
@@ -20,7 +20,7 @@ https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/8aa8f587-d9f1-4e
## Model Structure
![image](https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/6242a88c-01eb-47a2-844b-aab6e45b6558)
![image](https://github.com/PKU-YuanGroup/Open-Sora-Plan/assets/88202804/e3c8b35d-a217-4d96-b2e9-5c248a2859c8)
The Causal Video VAE architecture inherits from the [Stable-Diffusion Image VAE](https://github.com/CompVis/stable-diffusion/tree/main). To ensure that the pretrained weights of the Image VAE can be seamlessly applied to the Video VAE, the model structure has been designed as follows: