forked from lllyasviel/ControlNet-v1-1-nightly
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgradio_tile.py
116 lines (89 loc) · 5.52 KB
/
gradio_tile.py
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
from share import *
import config
import cv2
import einops
import gradio as gr
import numpy as np
import torch
import random
from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
from cldm.model import create_model, load_state_dict
from cldm.ddim_hacked import DDIMSampler
model_name = 'control_v11u_sd15_tile'
model = create_model(f'./models/{model_name}.yaml').cpu()
model.load_state_dict(load_state_dict('./models/v1-5-pruned.ckpt', location='cuda'), strict=False)
model.load_state_dict(load_state_dict(f'./models/{model_name}.pth', location='cuda'), strict=False)
model = model.cuda()
ddim_sampler = DDIMSampler(model)
def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, guess_mode, strength, scale, seed, eta, denoise_strength):
global preprocessor
with torch.no_grad():
if min(input_image.shape[0], input_image.shape[1]) < 64:
print('Input tile is smaller than 64*64. Terminated.')
return []
input_image = HWC3(input_image)
img = resize_image(input_image, image_resolution)
H, W, C = img.shape
detected_map = cv2.resize(input_image, (W // 8, H // 8), interpolation=cv2.INTER_AREA) # using 64 * 64 images
for _ in range(3):
detected_map = cv2.pyrUp(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()
img = torch.from_numpy(img.copy()).float().cuda() / 127.0 - 1.0
img = torch.stack([img for _ in range(num_samples)], dim=0)
img = einops.rearrange(img, 'b h w c -> b c h w').clone()
if seed == -1:
seed = random.randint(0, 65535)
seed_everything(seed)
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
un_cond = {"c_concat": None if guess_mode else [control], "c_crossattn": [model.get_learned_conditioning([n_prompt] * num_samples)]}
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
ddim_sampler.make_schedule(ddim_steps, ddim_eta=eta, verbose=True)
t_enc = min(int(denoise_strength * ddim_steps), ddim_steps - 1)
z = model.get_first_stage_encoding(model.encode_first_stage(img))
z_enc = ddim_sampler.stochastic_encode(z, torch.tensor([t_enc] * num_samples).to(model.device))
if config.save_memory:
model.low_vram_shift(is_diffusing=True)
model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13)
# Magic number. IDK why. Perhaps because 0.825**12<0.01 but 0.826**12>0.01
samples = ddim_sampler.decode(z_enc, cond, t_enc, unconditional_guidance_scale=scale, unconditional_conditioning=un_cond)
if config.save_memory:
model.low_vram_shift(is_diffusing=False)
x_samples = 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 [input_image] + results
block = gr.Blocks().queue()
with block:
with gr.Row():
gr.Markdown("## Control Stable Diffusion with Tile")
with gr.Row():
with gr.Column():
input_image = gr.Image(source='upload', type="numpy")
gr.Markdown("1. Upload image and write prompt.")
gr.Markdown("2. Click the pencil icon on the top-right corner of your uploaded image to select tile.")
prompt = gr.Textbox(label="Prompt")
run_button = gr.Button(label="Run")
num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, value=12345)
det = gr.Radio(choices=["None"], type="value", value="None", label="Preprocessor")
with gr.Accordion("Advanced options", open=False):
denoise_strength = gr.Slider(label="Denoising Strength", minimum=0.1, maximum=1.0, value=1.0, step=0.01)
image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=2048, 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=32, step=1)
scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
eta = gr.Slider(label="DDIM ETA", minimum=0.0, maximum=1.0, value=1.0, step=0.01)
a_prompt = gr.Textbox(label="Added Prompt", value='best quality')
n_prompt = gr.Textbox(label="Negative Prompt", value='blur, lowres, bad anatomy, bad hands, cropped, worst 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, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, guess_mode, strength, scale, seed, eta, denoise_strength]
run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
block.launch(server_name='0.0.0.0')