Hugging Face's logo

Efficient-Large-Model
/
SANA-WM_bidirectional

Image-to-Video
Diffusers
Safetensors
text-to-video
camera-control
world-model
diffusion
Model card Files
xet
 Community
4
victor HF Staff commited on
Commit
4e129fa
·
verified ·
1 Parent(s): 90e0ff3

add a gif preview?

Browse files

stands out more imo but feel free to close/merge @HaoyiZhu

Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -10,6 +10,8 @@ tags:
10
 
11
  # SANA-WM (Bidirectional)
12
 
 
 
13
  **SANA-WM** is an efficient open-source world model trained natively for
14
  one-minute generation. The bidirectional checkpoint released here is a
15
  2.6B-parameter image-to-video diffusion transformer that synthesises
 
10
 
11
  # SANA-WM (Bidirectional)
12
 
13
+ ![mosaic_2x2_5s_600](https://cdn-uploads.huggingface.co/production/uploads/5f17f0a0925b9863e28ad517/W6I8j-VQA4CulZWROldru.gif)
14
+
15
  **SANA-WM** is an efficient open-source world model trained natively for
16
  one-minute generation. The bidirectional checkpoint released here is a
17
  2.6B-parameter image-to-video diffusion transformer that synthesises