Hugging Face's logo

showlab
/
show-1-sr2

Text-to-Video
Diffusers
VideoToVideoSDPipeline
Model card Files Community
Junhao233 commited on
Commit
2d1824a
•
1 Parent(s): f2ca054

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ To marry the strength and alleviate the weakness of pixel-based and latent-based
14
 
15
  ## Model Details
16
 
17
- This is the super-resolution model of Show-1 that upscales videos from a 256x160 resolution to 576x320. The model is finetuned from [cerspense/zeroscope_v2_576w](https://huggingface.co/cerspense/zeroscope_v2_576w) on the [WebVid-10M](https://maxbain.com/webvid-dataset/) dataset.
18
 
19
  - **Developed by:** [Show Lab, National University of Singapore](https://sites.google.com/view/showlab/home?authuser=0)
20
  - **Model type:** pixel- and latent-based cascaded text-to-video diffusion model
 
14
 
15
  ## Model Details
16
 
17
+ This is the super-resolution model of Show-1 that upscales videos from a 256x160 resolution to 576x320. The model is finetuned using diffusion timesteps 0-900 on the [WebVid-10M](https://maxbain.com/webvid-dataset/) dataset.
18
 
19
  - **Developed by:** [Show Lab, National University of Singapore](https://sites.google.com/view/showlab/home?authuser=0)
20
  - **Model type:** pixel- and latent-based cascaded text-to-video diffusion model