helloworld-S commited on
Commit
ae043fd
·
verified ·
1 Parent(s): 1ad2320

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -4
app.py CHANGED
@@ -322,6 +322,8 @@ if __name__ == "__main__":
322
  - **GitHub**: [ByteDance/XVerse](https://github.com/bytedance/XVerse)
323
  - **Project Page**: [ByteDance/XVerse](https://bytedance.github.io/XVerse/)
324
 
 
 
325
  #### Input Images and Prompts
326
 
327
  * **Prompt**: The textual description guiding the image generation.
@@ -333,9 +335,9 @@ if __name__ == "__main__":
333
 
334
  > **⚠️ Important Usage Notes:**
335
  >
336
- > * **Prompt Construction**: The main text prompt **MUST** include the exact text you entered in the `Image Description` field for each active image. **Generation will fail if this description is missing from the prompt.**
337
- > * *Example*: If you upload two images and set their descriptions as "a man with red hair" (for Image 1) and "a woman with blue eyes" (for Image 2), your main prompt might be: "A `a man with red hair` walking beside `a woman with blue eyes` in a park."
338
- > * You can then write your main prompt simply as: "`ENT1` walking beside `ENT2` in a park." The code will **automatically replace** these placeholders with the full description text before generation.
339
  """)
340
  with gr.Row():
341
  with gr.Column():
@@ -360,7 +362,7 @@ if __name__ == "__main__":
360
  with gr.Row():
361
 
362
  # 将其他设置参数压缩到 Advanced Accordion 内
363
- with gr.Accordion("Advanced Settings Explained", open=False):
364
  gr.Markdown("""The Gradio demo provides several parameters to control your image generation process:
365
  * **Generated Height/Width**: Use the sliders to set the shape of the output image.
366
  * **Weight_id/ip**: Adjust these weight parameters. Higher values generally lead to better subject consistency but might slightly impact the naturalness of the generated image.
 
322
  - **GitHub**: [ByteDance/XVerse](https://github.com/bytedance/XVerse)
323
  - **Project Page**: [ByteDance/XVerse](https://bytedance.github.io/XVerse/)
324
 
325
+ ---
326
+
327
  #### Input Images and Prompts
328
 
329
  * **Prompt**: The textual description guiding the image generation.
 
335
 
336
  > **⚠️ Important Usage Notes:**
337
  >
338
+ > The main text prompt **MUST** include the exact text you entered in the `Image Description` field for each active image. **Generation will fail if this description is missing from the prompt.**
339
+ > * *Example*: If you upload two images and set their descriptions as "a man with red hair" (for Image 1) and "a woman with blue eyes" (for Image 2), your main prompt might be: "A `a man with red hair` walking beside `a woman with blue eyes` in a park."
340
+ > * You can then write your main prompt simply as: "`ENT1` walking beside `ENT2` in a park." The code will **automatically replace** these placeholders with the full description text before generation.
341
  """)
342
  with gr.Row():
343
  with gr.Column():
 
362
  with gr.Row():
363
 
364
  # 将其他设置参数压缩到 Advanced Accordion 内
365
+ with gr.Accordion("Advanced Settings", open=False):
366
  gr.Markdown("""The Gradio demo provides several parameters to control your image generation process:
367
  * **Generated Height/Width**: Use the sliders to set the shape of the output image.
368
  * **Weight_id/ip**: Adjust these weight parameters. Higher values generally lead to better subject consistency but might slightly impact the naturalness of the generated image.