Spaces:
Configuration error
Configuration error
UI Tweaks
Browse files
app.py
CHANGED
|
@@ -153,7 +153,7 @@ with gr.Blocks(css="styles.css") as demo:
|
|
| 153 |
|
| 154 |
with gr.Column(scale=1):
|
| 155 |
gr.Markdown(value="""## ✍️ Prompt Editing
|
| 156 |
-
See readme for a prompting guide. Use the '|' symbol to separate prompts. Use the "Add mask" section to make local edits. Negative prompts are highly recommended""", show_label=False)
|
| 157 |
positive_prompts = gr.Textbox(label="Positive prompts",
|
| 158 |
value="a picture of a woman with a very big nose | a picture of a woman with a large wide nose | a woman with an extremely prominent nose")
|
| 159 |
negative_prompts = gr.Textbox(label="Negative prompts",
|
|
@@ -173,11 +173,11 @@ with gr.Blocks(css="styles.css") as demo:
|
|
| 173 |
- I recommend starting prompts with 'a picture of a'
|
| 174 |
- To avoid shifts in gender, you can use 'a person' instead of 'a man' or 'a woman', especially in the negative prompts.
|
| 175 |
- The more 'out-of-domain' the prompts are, the more you need to increase the learning rate and decrease the perceptual loss weight. For example, trying to make a black person have platinum blond hair is more out-of-domain than the same transformation on a caucasian person.
|
| 176 |
-
-
|
| 177 |
""")
|
| 178 |
with gr.Row():
|
| 179 |
# with gr.Column():
|
| 180 |
-
presets = gr.Dropdown(
|
| 181 |
iterations = gr.Slider(minimum=10,
|
| 182 |
maximum=60,
|
| 183 |
step=1,
|
|
|
|
| 153 |
|
| 154 |
with gr.Column(scale=1):
|
| 155 |
gr.Markdown(value="""## ✍️ Prompt Editing
|
| 156 |
+
See readme for a prompting guide. Use the '|' symbol to separate prompts. Use the "Add mask" section to make local edits (Remember to click Set Mask!). Negative prompts are highly recommended""", show_label=False)
|
| 157 |
positive_prompts = gr.Textbox(label="Positive prompts",
|
| 158 |
value="a picture of a woman with a very big nose | a picture of a woman with a large wide nose | a woman with an extremely prominent nose")
|
| 159 |
negative_prompts = gr.Textbox(label="Negative prompts",
|
|
|
|
| 173 |
- I recommend starting prompts with 'a picture of a'
|
| 174 |
- To avoid shifts in gender, you can use 'a person' instead of 'a man' or 'a woman', especially in the negative prompts.
|
| 175 |
- The more 'out-of-domain' the prompts are, the more you need to increase the learning rate and decrease the perceptual loss weight. For example, trying to make a black person have platinum blond hair is more out-of-domain than the same transformation on a caucasian person.
|
| 176 |
+
- Example: Higher config values, like learning rate: 0.7, perceptual loss weight: 35 can be used to make major out-of-domain changes.
|
| 177 |
""")
|
| 178 |
with gr.Row():
|
| 179 |
# with gr.Column():
|
| 180 |
+
presets = gr.Dropdown(value="Select a preset", label="Preset Configs", choices=["Small Masked Changes (e.g. add lipstick)", "Major Masked Changes (e.g. change hair color or nose size)", "Major Global Changes (e.g. change race / gender"])
|
| 181 |
iterations = gr.Slider(minimum=10,
|
| 182 |
maximum=60,
|
| 183 |
step=1,
|