-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathapp.py
208 lines (189 loc) · 7.34 KB
/
app.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
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
import os
import gradio as gr
import os
import random
from PIL import Image
import time
import torch
from torch import autocast
from kandinsky2 import get_kandinsky2
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = get_kandinsky2(
'cuda',
task_type='text2img',
cache_dir='/media/agp/d58e0f56-1cd5-45af-938c-27e43b4fc343/kandinsky/tmp',
model_version='2.1',
use_flash_attention=False
)
"""
num_steps=50,
batch_size=4,
guidance_scale=7,
h=768,
w=768,
sampler='ddim_sampler',
prior_cf_scale=1,
prior_steps='25',
"""
#@title Images Generation
def infer(prompt, negative,h,w,batch_size, num_steps, guidance_scale,prior_cf_scale):
images = model.generate_text2img(prompt,
negative_prior_prompt=negative,
negative_decoder_prompt=negative,
num_steps=int(num_steps),
batch_size=int(batch_size),
guidance_scale=int(guidance_scale),
h=int(h), w=int(w),
sampler='p_sampler',
prior_cf_scale=int(prior_cf_scale),
prior_steps='30',)
return images
css = """
.gradio-container {
font-family: 'IBM Plex Sans', sans-serif;
}
.gr-button {
color: white;
border-color: black;
background: black;
}
input[type='range'] {
accent-color: black;
}
.dark input[type='range'] {
accent-color: #dfdfdf;
}
.container {
max-width: 930px;
margin: auto;
padding-top: 1.5rem;
}
#gallery {
min-height: 22rem;
margin-bottom: 15px;
margin-left: auto;
margin-right: auto;
border-bottom-right-radius: .5rem !important;
border-bottom-left-radius: .5rem !important;
}
#gallery>div>.h-full {
min-height: 20rem;
}
.details:hover {
text-decoration: underline;
}
.gr-button {
white-space: nowrap;
}
.gr-button:focus {
border-color: rgb(147 197 253 / var(--tw-border-opacity));
outline: none;
box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
--tw-border-opacity: 1;
--tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
--tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
--tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
--tw-ring-opacity: .5;
}
#advanced-btn {
font-size: .7rem !important;
line-height: 19px;
margin-top: 12px;
margin-bottom: 12px;
padding: 2px 8px;
border-radius: 14px !important;
}
#advanced-options {
display: none;
margin-bottom: 20px;
}
.footer {
margin-bottom: 45px;
margin-top: 35px;
text-align: center;
border-bottom: 1px solid #e5e5e5;
}
.footer>p {
font-size: .8rem;
display: inline-block;
padding: 0 10px;
transform: translateY(10px);
background: white;
}
.dark .footer {
border-color: #303030;
}
.dark .footer>p {
background: #0b0f19;
}
.acknowledgments h4{
margin: 1.25em 0 .25em 0;
font-weight: bold;
font-size: 115%;
}
#container-advanced-btns{
display: flex;
flex-wrap: wrap;
justify-content: space-between;
align-items: center;
}
.animate-spin {
animation: spin 1s linear infinite;
}
@keyframes spin {
from {
transform: rotate(0deg);
}
to {
transform: rotate(360deg);
}
}
}
.gr-form{
flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
}
#prompt-container{
gap: 0;
}
#generated_id{
min-height: 1860x
}
"""
block = gr.Blocks(css=css)
#SPACE_ID = os.getenv('SPACE_ID')
with block as webui:
gr.Markdown(f"""
"""
)
with gr.Tab("text to image"):
with gr.Group():
with gr.Box():
with gr.Row():
text = gr.Textbox(
label="Enter your prompt", show_label=True, max_lines=2
)
negative = gr.Textbox(
label="Enter your negative prompt", show_label=True, max_lines=2
)
with gr.Row():
with gr.Accordion("Advanced image settings", open=False):
h = gr.Slider(minimum=512, maximum=1280, step=64 ,label="Height. Minimum 512px, maximum 1280px")
w = gr.Slider(minimum=512, maximum=1280, step=64, label="Width. Minimum 512px , Maximum 1280px")
num_steps = gr.Slider(minimum=40, maximum=150, step=5 ,label="Number of Steps: Minimum 30, maximum 150")
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label="Number of images to generate: Minimum 1, maximum 8")
guidance_scale = gr.Slider( minimum=1, maximum=20, step=1, label="Guidance scale. A high guidance scale means that the model should generate images that closely match the specified style or theme, while a low guidance scale allows the model to generate more diverse and original images")
prior_cf_scale = gr.Slider(minimum=1, maximum=20, step=1, label="Prior config scale.Overall, the prior config scale hyperparameter allows users to control the level of adherence to specified conditions in the generated images. A high prior config scale results in images that closely match the specified conditions, while a low prior config scale generates more diverse and creative images.")
#prior_steps = gr.Slider(minimum=1, maximum=50, step=1, label="Prior steps. Increasing the prior steps can result in more detailed and accurate output, but it can also make the model slower and more computationally expensive.")
with gr.Row():
btn = gr.Button("Generate")
gallery = gr.Gallery(label="Generated images", show_label=False, elem_id="generated_id").style(columns=[2], rows=[2], object_fit="contain", height="auto")
# ex = gr.Examples(examples=examples, fn=infer, inputs=[text, negative], outputs=gallery, cache_examples=True)
#ex.dataset.headers = [""]
text.submit(infer, inputs=[text, negative, h, w, batch_size, num_steps, guidance_scale, prior_cf_scale], outputs=gallery)
btn.click(infer, inputs=[text, negative, h, w, batch_size, num_steps, guidance_scale, prior_cf_scale], outputs=gallery)
with gr.Tab("Flip Text"):
gr.Markdown(f"""
text test
"""
)
webui.queue(max_size=15).launch()