Update app.py
Browse files
app.py
CHANGED
|
@@ -270,6 +270,7 @@ The new pose should be pixel accurate to the pose we are trying to copy.
|
|
| 270 |
The position of the arms and head and legs should be the same as the pose we are trying to copy.
|
| 271 |
Change the field of view and angle to match exactly image 2. Head tilt and eye gaze pose should match the person in image 2.
|
| 272 |
Remove the background of image 2, and replace it with the background of image 1.
|
|
|
|
| 273 |
"""
|
| 274 |
|
| 275 |
def use_output_as_input(output_images):
|
|
@@ -283,7 +284,7 @@ def use_output_as_input(output_images):
|
|
| 283 |
def infer(
|
| 284 |
reference_image,
|
| 285 |
pose_image,
|
| 286 |
-
prompt,
|
| 287 |
seed=42,
|
| 288 |
randomize_seed=False,
|
| 289 |
true_guidance_scale=1.0,
|
|
|
|
| 270 |
The position of the arms and head and legs should be the same as the pose we are trying to copy.
|
| 271 |
Change the field of view and angle to match exactly image 2. Head tilt and eye gaze pose should match the person in image 2.
|
| 272 |
Remove the background of image 2, and replace it with the background of image 1.
|
| 273 |
+
Don't change the identity of the person in image 1, keep their appearance the same, it is undesirable to change their facical features or hair style. don't do it.
|
| 274 |
"""
|
| 275 |
|
| 276 |
def use_output_as_input(output_images):
|
|
|
|
| 284 |
def infer(
|
| 285 |
reference_image,
|
| 286 |
pose_image,
|
| 287 |
+
prompt=DEFAULT_LORA_PROMPT,
|
| 288 |
seed=42,
|
| 289 |
randomize_seed=False,
|
| 290 |
true_guidance_scale=1.0,
|