showlab
/

show-1-sr2

VideoToVideoSDPipeline

Model card Files Files and versions

Junhao233 commited on Oct 12, 2023

Commit

2d1824a

·

1 Parent(s): f2ca054

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ To marry the strength and alleviate the weakness of pixel-based and latent-based
 ## Model Details
-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.
 - **Developed by:** [Show Lab, National University of Singapore](https://sites.google.com/view/showlab/home?authuser=0)
 - **Model type:** pixel- and latent-based cascaded text-to-video diffusion model

 ## Model Details
+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.
 - **Developed by:** [Show Lab, National University of Singapore](https://sites.google.com/view/showlab/home?authuser=0)
 - **Model type:** pixel- and latent-based cascaded text-to-video diffusion model