Hugging Face's logo

lightx2v
/
LightVAE

Other
Wan2.2
MiniMax H3
video-vae
video-generation
distillation
image-to-video
text-to-video
comfyui
wan2.1
Model card Files
xet
 Community
4

Add pipeline tag and paper link

#3
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+12
-11
Files changed (1) hide show
  1. README.md +12 -11
README.md CHANGED
@@ -1,23 +1,24 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
- - diffusion-single-file
5
- - distillation
6
- - video-vae
7
- - video-generation
8
- - image-to-video
9
- - text-to-video
10
- - comfyui
11
- - wan2.1
12
- - wan2.2
13
- - minimax-h3
14
  ---
15
 
16
  # ⚡ LightVAE
17
 
18
  **Towards Compact and Efficient Video Autoencoders**
19
 
20
- [💻 Code](https://github.com/ModelTC/LightVAE) · [🧩 ComfyUI](https://github.com/ModelTC/LightVAE/tree/main/comfyui) · [⚡ LightX2V](https://github.com/ModelTC/LightX2V)
21
 
22
  LightVAE accelerates video autoencoders while preserving their original latent interfaces. We provide compressed components for **Wan2.1, Wan2.2 and MiniMax-H3**, with native ComfyUI integration for H3.
23
 
 
1
  ---
2
  license: apache-2.0
3
+ pipeline_tag: other
4
  tags:
5
+ - diffusion-single-file
6
+ - distillation
7
+ - video-vae
8
+ - video-generation
9
+ - image-to-video
10
+ - text-to-video
11
+ - comfyui
12
+ - wan2.1
13
+ - wan2.2
14
+ - minimax-h3
15
  ---
16
 
17
  # ⚡ LightVAE
18
 
19
  **Towards Compact and Efficient Video Autoencoders**
20
 
21
+ [📄 Paper](https://huggingface.co/papers/2610.14726) · [💻 Code](https://github.com/ModelTC/LightVAE) · [🧩 ComfyUI](https://github.com/ModelTC/LightVAE/tree/main/comfyui) · [⚡ LightX2V](https://github.com/ModelTC/LightX2V)
22
 
23
  LightVAE accelerates video autoencoders while preserving their original latent interfaces. We provide compressed components for **Wan2.1, Wan2.2 and MiniMax-H3**, with native ComfyUI integration for H3.
24