Add files using upload-large-folder tool
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ license: apache-2.0
|
|
| 8 |
|
| 9 |
## Overview
|
| 10 |
|
| 11 |
-
<p align="center"><img src="https://huggingface.co/RaphaelLiu/PusaV1/resolve/main/pusa_benchmark_figure_dark.png" width="
|
| 12 |
|
| 13 |
The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchronization of frame evolution imposed by conventional scalar timestep variables. While task-specific adaptations and autoregressive models have sought to address these challenges, they remain constrained by computational inefficiency, catastrophic forgetting, or narrow applicability.
|
| 14 |
|
|
|
|
| 8 |
|
| 9 |
## Overview
|
| 10 |
|
| 11 |
+
<p align="center"><img src="https://huggingface.co/RaphaelLiu/PusaV1/resolve/main/pusa_benchmark_figure_dark.png" width="100%"></p>
|
| 12 |
|
| 13 |
The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchronization of frame evolution imposed by conventional scalar timestep variables. While task-specific adaptations and autoregressive models have sought to address these challenges, they remain constrained by computational inefficiency, catastrophic forgetting, or narrow applicability.
|
| 14 |
|