|
import gradio as gr |
|
import cv2 |
|
import numpy as np |
|
|
|
from annotator.util import resize_image, HWC3 |
|
|
|
DESCRIPTION = "# " |
|
DESCRIPTION += "# ControlNet v1.1 Preprocessors Standalone" |
|
DESCRIPTION += "\n<p>Generate Control Images for Stable Diffusion and other apps that uses ControlNet.</p>" |
|
|
|
|
|
model_canny = None |
|
|
|
|
|
def canny(img, res, l, h): |
|
img = resize_image(HWC3(img), res) |
|
global model_canny |
|
if model_canny is None: |
|
from annotator.canny import CannyDetector |
|
|
|
model_canny = CannyDetector() |
|
result = model_canny(img, l, h) |
|
return [result] |
|
|
|
|
|
model_hed = None |
|
|
|
|
|
def hed(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_hed |
|
if model_hed is None: |
|
from annotator.hed import HEDdetector |
|
|
|
model_hed = HEDdetector() |
|
result = model_hed(img) |
|
return [result] |
|
|
|
|
|
model_pidi = None |
|
|
|
|
|
def pidi(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_pidi |
|
if model_pidi is None: |
|
from annotator.pidinet import PidiNetDetector |
|
|
|
model_pidi = PidiNetDetector() |
|
result = model_pidi(img) |
|
return [result] |
|
|
|
|
|
model_mlsd = None |
|
|
|
|
|
def mlsd(img, res, thr_v, thr_d): |
|
img = resize_image(HWC3(img), res) |
|
global model_mlsd |
|
if model_mlsd is None: |
|
from annotator.mlsd import MLSDdetector |
|
|
|
model_mlsd = MLSDdetector() |
|
result = model_mlsd(img, thr_v, thr_d) |
|
return [result] |
|
|
|
|
|
model_midas = None |
|
|
|
|
|
def midas(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_midas |
|
if model_midas is None: |
|
from annotator.midas import MidasDetector |
|
|
|
model_midas = MidasDetector() |
|
result = model_midas(img) |
|
return [result] |
|
|
|
|
|
model_zoe = None |
|
|
|
|
|
def zoe(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_zoe |
|
if model_zoe is None: |
|
from annotator.zoe import ZoeDetector |
|
|
|
model_zoe = ZoeDetector() |
|
result = model_zoe(img) |
|
return [result] |
|
|
|
|
|
model_normalbae = None |
|
|
|
|
|
def normalbae(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_normalbae |
|
if model_normalbae is None: |
|
from annotator.normalbae import NormalBaeDetector |
|
|
|
model_normalbae = NormalBaeDetector() |
|
result = model_normalbae(img) |
|
return [result] |
|
|
|
|
|
model_dwpose = None |
|
|
|
|
|
def dwpose(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_dwpose |
|
if model_dwpose is None: |
|
from annotator.dwpose import DWposeDetector |
|
|
|
model_dwpose = DWposeDetector() |
|
result = model_dwpose(img) |
|
return [result] |
|
|
|
|
|
model_openpose = None |
|
|
|
|
|
def openpose(img, res, hand_and_face): |
|
img = resize_image(HWC3(img), res) |
|
global model_openpose |
|
if model_openpose is None: |
|
from annotator.openpose import OpenposeDetector |
|
|
|
model_openpose = OpenposeDetector() |
|
result = model_openpose(img, hand_and_face) |
|
return [result] |
|
|
|
|
|
model_uniformer = None |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model_lineart_anime = None |
|
model_lineart = None |
|
|
|
|
|
def lineart(img, res, preprocessor_name="Lineart", invert=True): |
|
img = resize_image(HWC3(img), res) |
|
["Lineart", "Lineart Coarse", "Lineart Anime"] |
|
if preprocessor_name in ["Lineart", "Lineart Coarse"]: |
|
coarse = "Coarse" in preprocessor_name |
|
global model_lineart |
|
if model_lineart is None: |
|
from annotator.lineart import LineartDetector |
|
|
|
model_lineart = LineartDetector() |
|
|
|
if invert: |
|
result = cv2.bitwise_not(model_lineart(img, coarse)) |
|
else: |
|
result = model_lineart(img, coarse) |
|
return [result] |
|
elif preprocessor_name == "Lineart Anime": |
|
global model_lineart_anime |
|
if model_lineart_anime is None: |
|
from annotator.lineart_anime import LineartAnimeDetector |
|
|
|
model_lineart_anime = LineartAnimeDetector() |
|
|
|
if invert: |
|
result = cv2.bitwise_not(model_lineart_anime(img)) |
|
else: |
|
result = model_lineart_anime(img) |
|
return [result] |
|
|
|
|
|
model_oneformer_coco = None |
|
|
|
|
|
def oneformer_coco(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_oneformer_coco |
|
if model_oneformer_coco is None: |
|
from annotator.oneformer import OneformerCOCODetector |
|
|
|
model_oneformer_coco = OneformerCOCODetector() |
|
result = model_oneformer_coco(img) |
|
return [result] |
|
|
|
|
|
model_oneformer_ade20k = None |
|
|
|
|
|
def oneformer_ade20k(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_oneformer_ade20k |
|
if model_oneformer_ade20k is None: |
|
from annotator.oneformer import OneformerADE20kDetector |
|
|
|
model_oneformer_ade20k = OneformerADE20kDetector() |
|
result = model_oneformer_ade20k(img) |
|
return [result] |
|
|
|
|
|
model_content_shuffler = None |
|
|
|
|
|
def content_shuffler(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_content_shuffler |
|
if model_content_shuffler is None: |
|
from annotator.shuffle import ContentShuffleDetector |
|
|
|
model_content_shuffler = ContentShuffleDetector() |
|
result = model_content_shuffler(img) |
|
return [result] |
|
|
|
|
|
model_color_shuffler = None |
|
|
|
|
|
def color_shuffler(img, res): |
|
img = resize_image(HWC3(img), res) |
|
global model_color_shuffler |
|
if model_color_shuffler is None: |
|
from annotator.shuffle import ColorShuffleDetector |
|
|
|
model_color_shuffler = ColorShuffleDetector() |
|
result = model_color_shuffler(img) |
|
return [result] |
|
|
|
|
|
model_inpaint = None |
|
|
|
|
|
def inpaint(image, invert): |
|
|
|
color = HWC3(image["background"]) |
|
if invert: |
|
|
|
alpha = image["layers"][0][:, :, 3:] |
|
else: |
|
|
|
alpha = 255 - image["layers"][0][:, :, 3:] |
|
result = np.concatenate([color, alpha], axis=2) |
|
return [result] |
|
|
|
|
|
theme = gr.themes.Soft( |
|
primary_hue="emerald", |
|
|
|
radius_size="sm", |
|
) |
|
|
|
css = """ |
|
body > gradio-app { |
|
background: var(--primary-950); |
|
background: linear-gradient(180deg, color-mix(in srgb, var(--primary-950), transparent 50%) 0%, color-mix(in srgb, var(--primary-950), transparent 50%) 28%, var(--neutral-950) 28%, var(--neutral-950) 100%) !important; |
|
padding-top: 120px; |
|
} |
|
|
|
div.tabs > div.tab-nav > button.selected { |
|
border-width: 0 !important; |
|
background: var(--primary-600) !important; |
|
color: var(--neutral-950); |
|
font-weight: 600; |
|
} |
|
|
|
div.tabs > div.tab-nav { |
|
border-bottom: none; !important; |
|
padding: 0 0.25rem 0 0.25rem !important; |
|
} |
|
|
|
div.tabs div.tabitem { |
|
background-color: var(--neutral-900) !important; |
|
border-top: 8px solid var(--primary-600) !important; |
|
border-radius: var(--container-radius) !important; |
|
} |
|
|
|
.top-description h1 { |
|
color: var(--neutral-400); |
|
font-size: 2rem; |
|
} |
|
""" |
|
|
|
with gr.Blocks(theme=theme, css=css) as demo: |
|
gr.Markdown(DESCRIPTION, elem_classes="top-description") |
|
with gr.Tab("Canny Edge"): |
|
with gr.Row(): |
|
gr.Markdown("## Canny Edge") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
low_threshold = gr.Slider(label="low_threshold", minimum=1, maximum=255, value=100, step=1) |
|
high_threshold = gr.Slider(label="high_threshold", minimum=1, maximum=255, value=200, step=1) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=canny, inputs=[input_image, resolution, low_threshold, high_threshold], outputs=[gallery]) |
|
|
|
with gr.Tab("HED Edge"): |
|
with gr.Row(): |
|
gr.Markdown("## HED Edge "SoftEdge"") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=hed, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("Pidi Edge"): |
|
with gr.Row(): |
|
gr.Markdown("## Pidi Edge "SoftEdge"") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=pidi, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("MLSD Edge"): |
|
with gr.Row(): |
|
gr.Markdown("## MLSD Edge") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
value_threshold = gr.Slider(label="value_threshold", minimum=0.01, maximum=2.0, value=0.1, step=0.01) |
|
distance_threshold = gr.Slider(label="distance_threshold", minimum=0.01, maximum=20.0, value=0.1, step=0.01) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=384, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=mlsd, inputs=[input_image, resolution, value_threshold, distance_threshold], outputs=[gallery]) |
|
|
|
with gr.Tab("MIDAS Depth"): |
|
with gr.Row(): |
|
gr.Markdown("## MIDAS Depth") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=384, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=midas, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("ZOE Depth"): |
|
with gr.Row(): |
|
gr.Markdown("## Zoe Depth") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=zoe, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("Normal Bae"): |
|
with gr.Row(): |
|
gr.Markdown("## Normal Bae") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=normalbae, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("DWPose"): |
|
with gr.Row(): |
|
gr.Markdown("## DWPose") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=dwpose, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("Openpose"): |
|
with gr.Row(): |
|
gr.Markdown("## Openpose") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
hand_and_face = gr.Checkbox(label="Hand and Face", value=False) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=openpose, inputs=[input_image, resolution, hand_and_face], outputs=[gallery]) |
|
|
|
|
|
with gr.Tab("Lineart"): |
|
with gr.Row(): |
|
gr.Markdown("## Lineart \n<p>Check Invert to use with Mochi Diffusion. Inverted image can also be created here for use with ControlNet Scribble.") |
|
with gr.Row(): |
|
with gr.Column(): |
|
preprocessor_name = gr.Radio(label="Preprocessor", choices=["Lineart", "Lineart Coarse", "Lineart Anime"], type="value", value="Lineart") |
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
invert = gr.Checkbox(label="Invert", value=True) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Lineart") |
|
with gr.Column(): |
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
|
|
def update_button_label(preprocessor_name): |
|
if preprocessor_name == "Lineart": |
|
return "Lineart" |
|
elif preprocessor_name == "Lineart Coarse": |
|
return "Lineart Coarse" |
|
elif preprocessor_name == "Lineart Anime": |
|
return "Lineart Anime" |
|
|
|
preprocessor_name.change(fn=update_button_label, inputs=[preprocessor_name], outputs=[run_button]) |
|
run_button.click(fn=lineart, inputs=[input_image, resolution, preprocessor_name, invert], outputs=[gallery]) |
|
|
|
with gr.Tab("InPaint"): |
|
with gr.Row(): |
|
gr.Markdown("## InPaint") |
|
with gr.Row(): |
|
with gr.Column(): |
|
input_image = gr.ImageMask(sources="upload", type="numpy", height="auto") |
|
invert = gr.Checkbox(label="Invert Mask", value=False) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=inpaint, inputs=[input_image, invert], outputs=[gallery]) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
with gr.Tab("Content Shuffle"): |
|
with gr.Row(): |
|
gr.Markdown("## Content Shuffle") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
run_button.click(fn=content_shuffler, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
with gr.Tab("Color Shuffle"): |
|
with gr.Row(): |
|
gr.Markdown("## Color Shuffle") |
|
with gr.Row(): |
|
with gr.Column(): |
|
|
|
input_image = gr.Image(label="Input Image", type="numpy", height=512) |
|
resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64) |
|
run_button = gr.Button("Run") |
|
|
|
with gr.Column(): |
|
|
|
gallery = gr.Gallery(label="Generated images", show_label=False, height="auto") |
|
|
|
run_button.click(fn=color_shuffler, inputs=[input_image, resolution], outputs=[gallery]) |
|
|
|
|
|
demo.launch() |
|
|
