File size: 11,720 Bytes
87cceff d59438d 87cceff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
import cv2
import einops
import gradio as gr
import numpy as np
import torch
from pytorch_lightning import seed_everything
from util import resize_image, HWC3, apply_canny
from ldm.models.diffusion.ddim import DDIMSampler
from annotator.openpose import apply_openpose
from cldm.model import create_model, load_state_dict
from huggingface_hub import hf_hub_url, cached_download
REPO_ID = "Thaweewat/ControlNet-Architecture"
canny_checkpoint = "models/control_sd15_canny.pth"
scribble_checkpoint = "models/control_sd15_scribble.pth"
pose_checkpoint = "models/control_sd15_openpose.pth"
canny_model = create_model('./models/cldm_v15.yaml').cpu()
canny_model.load_state_dict(load_state_dict(cached_download(
hf_hub_url(REPO_ID, canny_checkpoint)
), location='cpu'))
canny_model = canny_model.cuda()
ddim_sampler = DDIMSampler(canny_model)
pose_model = create_model('./models/cldm_v15.yaml').cpu()
pose_model.load_state_dict(load_state_dict(cached_download(
hf_hub_url(REPO_ID, pose_checkpoint)
), location='cpu'))
pose_model = pose_model.cuda()
ddim_sampler_pose = DDIMSampler(pose_model)
scribble_model = create_model('./models/cldm_v15.yaml').cpu()
scribble_model.load_state_dict(load_state_dict(cached_download(
hf_hub_url(REPO_ID, scribble_checkpoint)
), location='cpu'))
scribble_model = scribble_model.cuda()
ddim_sampler_scribble = DDIMSampler(scribble_model)
save_memory = False
def process(input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
# TODO: Add other control tasks
if input_control == "Scribble":
return process_scribble(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta)
elif input_control == "Pose":
return process_pose(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, image_resolution, ddim_steps, scale, seed, eta)
return process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold)
def process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
with torch.no_grad():
img = resize_image(HWC3(input_image), image_resolution)
H, W, C = img.shape
detected_map = apply_canny(img, low_threshold, high_threshold)
detected_map = HWC3(detected_map)
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
seed_everything(seed)
if save_memory:
canny_model.low_vram_shift(is_diffusing=False)
cond = {"c_concat": [control], "c_crossattn": [canny_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
un_cond = {"c_concat": [control], "c_crossattn": [canny_model.get_learned_conditioning([n_prompt] * num_samples)]}
shape = (4, H // 8, W // 8)
if save_memory:
canny_model.low_vram_shift(is_diffusing=False)
samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,
shape, cond, verbose=False, eta=eta,
unconditional_guidance_scale=scale,
unconditional_conditioning=un_cond)
if save_memory:
canny_model.low_vram_shift(is_diffusing=False)
x_samples = canny_model.decode_first_stage(samples)
x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
results = [x_samples[i] for i in range(num_samples)]
return [255 - detected_map] + results
def process_scribble(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta):
with torch.no_grad():
img = resize_image(HWC3(input_image), image_resolution)
H, W, C = img.shape
detected_map = np.zeros_like(img, dtype=np.uint8)
detected_map[np.min(img, axis=2) < 127] = 255
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
seed_everything(seed)
if save_memory:
scribble_model.low_vram_shift(is_diffusing=False)
cond = {"c_concat": [control], "c_crossattn": [scribble_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
un_cond = {"c_concat": [control], "c_crossattn": [scribble_model.get_learned_conditioning([n_prompt] * num_samples)]}
shape = (4, H // 8, W // 8)
if save_memory:
scribble_model.low_vram_shift(is_diffusing=False)
samples, intermediates = ddim_sampler_scribble.sample(ddim_steps, num_samples,
shape, cond, verbose=False, eta=eta,
unconditional_guidance_scale=scale,
unconditional_conditioning=un_cond)
if save_memory:
scribble_model.low_vram_shift(is_diffusing=False)
x_samples = scribble_model.decode_first_stage(samples)
x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
results = [x_samples[i] for i in range(num_samples)]
return [255 - detected_map] + results
def process_pose(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, scale, seed, eta):
with torch.no_grad():
input_image = HWC3(input_image)
detected_map, _ = apply_openpose(resize_image(input_image, detect_resolution))
detected_map = HWC3(detected_map)
img = resize_image(input_image, image_resolution)
H, W, C = img.shape
detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_NEAREST)
control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
control = torch.stack([control for _ in range(num_samples)], dim=0)
control = einops.rearrange(control, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 65535)
seed_everything(seed)
if save_memory:
pose_model.low_vram_shift(is_diffusing=False)
cond = {"c_concat": [control], "c_crossattn": [pose_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
un_cond = {"c_concat": [control], "c_crossattn": [pose_model.get_learned_conditioning([n_prompt] * num_samples)]}
shape = (4, H // 8, W // 8)
if save_memory:
pose_model.low_vram_shift(is_diffusing=False)
samples, intermediates = ddim_sampler_pose.sample(ddim_steps, num_samples,
shape, cond, verbose=False, eta=eta,
unconditional_guidance_scale=scale,
unconditional_conditioning=un_cond)
if save_memory:
pose_model.low_vram_shift(is_diffusing=False)
x_samples = pose_model.decode_first_stage(samples)
x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
results = [x_samples[i] for i in range(num_samples)]
return [detected_map] + results
def create_canvas(w, h):
new_control_options = ["Interactive Scribble"]
return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255
block = gr.Blocks().queue()
control_task_list = [
"Canny Edge Map",
"Scribble",
"Pose"
]
with block:
gr.Markdown("## Adding Conditional Control to Text-to-Image Diffusion Models")
gr.HTML('''
<p style="margin-bottom: 10px; font-size: 94%">
This is an unofficial demo for ControlNet, which is a neural network structure to control diffusion models by adding extra conditions such as canny edge detection. The demo is based on the <a href="https://github.com/lllyasviel/ControlNet" style="text-decoration: underline;" target="_blank"> Github </a> implementation.
</p>
''')
gr.HTML("<p>You can duplicate this Space to run it privately without a queue and load additional checkpoints. : <a style='display:inline-block' href='https://huggingface.co/spaces/RamAnanth1/ControlNet?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14' alt='Duplicate Space'></a> <a style='display:inline-block' href='https://colab.research.google.com/github/camenduru/controlnet-colab/blob/main/controlnet-colab.ipynb'><img src = 'https://colab.research.google.com/assets/colab-badge.svg' alt='Open in Colab'></a></p>")
with gr.Row():
with gr.Column():
input_image = gr.Image(source='upload', type="numpy")
input_control = gr.Dropdown(control_task_list, value="Scribble", label="Control Task")
prompt = gr.Textbox(label="Prompt")
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)
low_threshold = gr.Slider(label="Canny low threshold", minimum=1, maximum=255, value=100, step=1)
high_threshold = gr.Slider(label="Canny high threshold", minimum=1, maximum=255, value=200, step=1)
ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
eta = gr.Slider(label="eta (DDIM)", minimum=0.0,maximum =1.0, value=0.0, step=0.1)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
n_prompt = gr.Textbox(label="Negative Prompt",
value='longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality')
with gr.Column():
result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid=2, height='auto')
ips = [input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold]
run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
block.launch(debug = True) |