guess mode

This commit is contained in:
lvmin
2023-02-20 05:17:30 -08:00
parent fccb513fb3
commit 9ec94ff924
13 changed files with 15 additions and 11 deletions

View File

@@ -218,7 +218,7 @@ In this mode, you can just remove all prompts, and then the ControlNet encoder w
This task is the most difficult one among all tasks in this work.
This mode is very suitable for comparing different methods to control stable diffusion because the non-prompted generating task is significantly more difficult than prompted task. In this mode, different methods' performance will be very salient.
This mode is very suitable for comparing different methods to control stable diffusion, because the non-prompted generating task is significantly more difficult than prompted task. In this mode, different methods' performance will be very salient.
Feel free to reproduce the below examples using the parameters in the screenshots.
@@ -244,6 +244,10 @@ Without prompt, the HED seems good at generating images look like paintings when
![p](github_page/uc6.png)
As you can see below, because **Non-prompted** mode is extremely difficult, even the very deep ControlNet may also generate failure cases. (In the example below, the right-bottom one seem ok.) Because of this, the non-prompted mode seems a nice metric to test the capability of different encoder-based methods to control stable diffusion.
![p](github_page/uc7.png)
# Annotate Your Own Data
We provide simple python scripts to process images.

BIN
github_page/uc7.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 810 KiB

View File

@@ -76,7 +76,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
low_threshold = gr.Slider(label="Canny low threshold", minimum=1, maximum=255, value=100, step=1)

View File

@@ -78,7 +78,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="Depth Resolution", minimum=128, maximum=1024, value=384, step=1)

View File

@@ -82,7 +82,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="HED Resolution", minimum=128, maximum=1024, value=512, step=1)

View File

@@ -78,7 +78,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="HED Resolution", minimum=128, maximum=1024, value=512, step=1)

View File

@@ -78,7 +78,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="Hough Resolution", minimum=128, maximum=1024, value=512, step=1)

View File

@@ -78,7 +78,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="Normal Resolution", minimum=128, maximum=1024, value=384, step=1)

View File

@@ -78,7 +78,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="OpenPose Resolution", minimum=128, maximum=1024, value=512, step=1)

View File

@@ -73,7 +73,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)

View File

@@ -83,7 +83,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)

View File

@@ -77,7 +77,7 @@ with block:
run_button = gr.Button(label="Run")
with gr.Accordion("Advanced options", open=False):
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01)
guess_mode = gr.Checkbox(label='Guess Mode', value=False)
detect_resolution = gr.Slider(label="Segmentation Resolution", minimum=128, maximum=1024, value=512, step=1)

BIN
test_imgs/human_hed_bin.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 9.2 KiB