mapo-t2i
/

mapo-pick-style-cartoon

StableDiffusionXLPipeline

diffusers-training

stable-diffusion-xl

stable-diffusion-xl-diffusers

Inference Endpoints

Model card Files Files and versions Community

JW17 commited on 27 days ago

Commit

139195f

•

1 Parent(s): 61382fd

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ base_model: stabilityai/stable-diffusion-xl-base-1.0
 # Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
 <div align="center">
-<img src="assets/mapo_overview.png" width=750/>
 </div><br>
 We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignment technique for text-to-image diffusion models. For more details on the technique, please refer to our paper [here] (TODO).

 # Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
 <div align="center">
+<img src="assets/mapo_overview.jpg" width=750/>
 </div><br>
 We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignment technique for text-to-image diffusion models. For more details on the technique, please refer to our paper [here] (TODO).