elismasilva commited on
Commit
5764403
·
1 Parent(s): 6997095

update README.md

Browse files
Files changed (1) hide show
  1. app.py +7 -22
app.py CHANGED
@@ -183,28 +183,14 @@ css = """
183
  max-width: unset !important;
184
  }
185
  """
186
- title = """
187
- <div style="text-align: center; font-size: 32px; font-weight: bold; margin-bottom: 20px;">
188
- Mixture-of-Diffusers for SDXL Tiling Pipeline🤗
189
- </div>
190
- <div style="text-align: center;">
191
  <span>This project implements an SDXL pipeline based on the original project, <a href='https://github.com/albarji/mixture-of-diffusers'>Mixture-of-Diffusers</a>. For more information, see the:
192
  <a href="https://arxiv.org/pdf/2408.06072">📜 paper </a>
193
- </div>
194
- <div style="text-align: center;display: flex;justify-content: center;align-items: center;margin-top: 1em;margin-bottom: .5em;">
195
- <span>If the Space is too busy, duplicate it to use privately</span>
196
- <a href="https://huggingface.co/spaces/elismasilva/mixture-of-diffusers-sdxl-tiling?duplicate=true"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-lg.svg" width="160" style="
197
- margin-left: .75em;"></a>
198
- <a href="https://ko-fi.com/S6S71ACXMR" target="_blank"><img height="36" style="border:0px;height:36px;" src="https://storage.ko-fi.com/cdn/kofi6.png?v=6" border="0" alt="Buy Me a Coffee at ko-fi.com"/></a>
199
- </div>
200
-
201
  """
202
- # title = r"""<h1 align="center"></h1>
203
- # <div style="display: flex; flex-direction: column; justify-content: center; align-items: center; text-align: center; overflow:hidden;">
204
- # <p>This project implements an SDXL pipeline based on the original project, <a href='https://github.com/albarji/mixture-of-diffusers'>Mixture-of-Diffusers</a>. For more information, see the <a href='https://arxiv.org/abs/2302.02412'>Paper</a>.</p>
205
- # </div>
206
- # """
207
- tips=r"""
208
  ### Method
209
  The method proposed here strives to provide a better tool for image composition by using several diffusion processes in parallel, each configured with a specific prompt and settings, and focused on a particular region of the image. The mixture of diffusion processes is done in a way that harmonizes the generation process, preventing "seam" effects in the generated image.
210
  Using several diffusion processes in parallel has also practical advantages when generating very large images, as the GPU memory requirements are similar to that of generating an image of the size of a single tile.
@@ -219,15 +205,14 @@ For practical demonstration purposes, this demo only covers image generation usi
219
  6. Enjoy!
220
  """
221
 
222
- about = r"""
223
  📧 **Contact**
224
  <br>
225
  If you have any questions or suggestions, feel free to send your question to <b>[email protected]</b>.
226
  """
227
 
228
  with gr.Blocks(css=css) as app:
229
- gr.Markdown(title)
230
-
231
  with gr.Row():
232
  with gr.Column(scale=7):
233
  generate_button = gr.Button("Generate")
 
183
  max-width: unset !important;
184
  }
185
  """
186
+ title = """<h1 align="center">Mixture-of-Diffusers for SDXL Tiling Pipeline🤗</h1>
187
+ <div style="display: flex; flex-direction: column; justify-content: center; align-items: center; text-align: center; overflow:hidden;">
 
 
 
188
  <span>This project implements an SDXL pipeline based on the original project, <a href='https://github.com/albarji/mixture-of-diffusers'>Mixture-of-Diffusers</a>. For more information, see the:
189
  <a href="https://arxiv.org/pdf/2408.06072">📜 paper </a>
190
+ </div>
 
 
 
 
 
 
 
191
  """
192
+
193
+ tips = """
 
 
 
 
194
  ### Method
195
  The method proposed here strives to provide a better tool for image composition by using several diffusion processes in parallel, each configured with a specific prompt and settings, and focused on a particular region of the image. The mixture of diffusion processes is done in a way that harmonizes the generation process, preventing "seam" effects in the generated image.
196
  Using several diffusion processes in parallel has also practical advantages when generating very large images, as the GPU memory requirements are similar to that of generating an image of the size of a single tile.
 
205
  6. Enjoy!
206
  """
207
 
208
+ about = """
209
  📧 **Contact**
210
  <br>
211
  If you have any questions or suggestions, feel free to send your question to <b>[email protected]</b>.
212
  """
213
 
214
  with gr.Blocks(css=css) as app:
215
+ gr.Markdown(title)
 
216
  with gr.Row():
217
  with gr.Column(scale=7):
218
  generate_button = gr.Button("Generate")