jeasinema commited on
Commit
b7fac32
1 Parent(s): e73c979

update gradio

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -103,7 +103,7 @@ article_html = """
103
  <b>UltraEdit</b> is a dataset designed for fine-grained, instruction-based image editing. It contains over 4 million free-form image editing samples and more than 100,000 region-based image editing samples, automatically generated with real images as anchors.
104
  </p>
105
  <p>
106
- This demo allows you to perform image editing using the Stable Diffusion 3 model trained with this extensive dataset. It supports both free-form (without mask) and region-based (with mask) image editing. Use the sliders to adjust the inference steps and guidance scales, and provide a seed for reproducibility. The image guidance scale of 1.5 and text guidance scale of 7.5 / 12.5 is a good start for free-from/region-based image editing.
107
  </p>
108
  </div>
109
  </div>
 
103
  <b>UltraEdit</b> is a dataset designed for fine-grained, instruction-based image editing. It contains over 4 million free-form image editing samples and more than 100,000 region-based image editing samples, automatically generated with real images as anchors.
104
  </p>
105
  <p>
106
+ This demo allows you to perform image editing using the <a href="https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers" style="color: blue; text-decoration: none;">Stable Diffusion 3</a> model as backbone trained with this extensive dataset. It supports both free-form (without mask) and region-based (with mask) image editing. Use the sliders to adjust the inference steps and guidance scales, and provide a seed for reproducibility. The image guidance scale of 1.5 and text guidance scale of 7.5 / 12.5 is a good start for free-from/region-based image editing.
107
  </p>
108
  </div>
109
  </div>