Efficient-Large-Model
/

Sana_Sprint_1.6B_1024px

sana, sana-sprint

1024px_based_image_size

One-step diffusion

Model card Files Files and versions Community

Lawrence-cj commited on 16 days ago

Commit

f38e349

·

verified ·

1 Parent(s): 23e6773

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -44,13 +44,13 @@ pipeline_tag: text-to-image
 ## Training Pipeline
 <p align="center" border-raduis="10px">
-  <img src="https://nvlabs.github.io/Sana/Sprint/asset/content/paradigm.png" width="85%" alt="teaser_page1"/>
 </p>
 ## Model Efficiency
 <p align="center" border-raduis="10px">
-  <img src="https://nvlabs.github.io/Sana/Sprint/asset/content/teaser.png" width="85%" alt="teaser_page1"/>
 </p>
 SANA-Sprint is an ultra-efficient diffusion model for text-to-image (T2I) generation, reducing inference steps from 20 to 1-4 while achieving state-of-the-art performance.

 ## Training Pipeline
 <p align="center" border-raduis="10px">
+  <img src="https://nvlabs.github.io/Sana/Sprint/asset/content/paradigm.png" width="90%" alt="teaser_page1"/>
 </p>
 ## Model Efficiency
 <p align="center" border-raduis="10px">
+  <img src="https://nvlabs.github.io/Sana/Sprint/asset/content/teaser.png" width="95%" alt="teaser_page1"/>
 </p>
 SANA-Sprint is an ultra-efficient diffusion model for text-to-image (T2I) generation, reducing inference steps from 20 to 1-4 while achieving state-of-the-art performance.