File size: 8,678 Bytes
56ce3ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
import os

import gradio as gr
import torch
from torch import autocast
from kandinsky2 import get_kandinsky2
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')


from kandinsky2 import get_kandinsky2
model = get_kandinsky2('cuda', task_type='text2img', 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',
"""
def infer(prompt, negative='low quality, bad quality'):
    images = model.generate_text2img(prompt, 
                           negative_prior_prompt=negative,
                           negative_decoder_prompt=negative, 
                           num_steps=50,
                           batch_size=1,
                           guidance_scale=4,
                           h=768, w=768,
                           sampler='ddim_sampler',
                           prior_cf_scale=1,
                           prior_steps="25",)
    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: 730px;
            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);
            }
        }
        #share-btn-container {
            display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
        }
        #share-btn {
            all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;
        }
        #share-btn * {
            all: unset;
        }
        .gr-form{
            flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
        }
        #prompt-container{
            gap: 0;
        }
        #generated_id{
            min-height: 700px
        }
"""
block = gr.Blocks(css=css)

examples = [

    [
        'Thinking man in anime style'
    ],

]

SPACE_ID = os.getenv('SPACE_ID')

with block as demo:
    gr.Markdown(f"""


[![Framework: PyTorch](https://img.shields.io/badge/Framework-PyTorch-orange.svg)](https://pytorch.org/) [![Huggingface space](https://img.shields.io/badge/🤗-Huggingface-yello.svg)](https://huggingface.co/sberbank-ai/Kandinsky_2.0)

<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>

[Offical BlogPost](https://habr.com/ru/company/sberbank/blog/725282/)
[Offical Telegram Bot](https://t.me/kandinsky21_bot)
[Offical site](https://fusionbrain.ai/diffusion)

## Model architecture:
Kandinsky 2.1 inherits best practicies from Dall-E 2 and Latent diffusion, while introducing some new ideas.

As text and image encoder it uses CLIP model and diffusion image prior (mapping) between latent spaces of CLIP modalities. This approach increases the visual performance of the model and unveils new horizons in blending images and text-guided image manipulation.

For diffusion mapping of latent spaces we use transformer with num_layers=20, num_heads=32 and hidden_size=2048.

Other architecture parts:

- Text encoder (XLM-Roberta-Large-Vit-L-14) - 560M
- Diffusion Image Prior — 1B
- CLIP image encoder (ViT-L/14) - 427M
- Latent Diffusion U-Net - 1.22B
- MoVQ encoder/decoder - 67M

Kandinsky 2.1 was trained on a large-scale image-text dataset LAION HighRes and fine-tuned on our internal datasets.

**Kandinsky 2.1** architecture overview:

![](https://raw.githubusercontent.com/ai-forever/Kandinsky-2/main/content/einstein.png)


        """
    )
    with gr.Group():
        with gr.Box():
            with gr.Row().style(mobile_collapse=False, equal_height=True):

                text = gr.Textbox(
                    label="Enter your prompt", show_label=True, max_lines=2
                ).style(
                    border=(True, False, True, True),
                    rounded=(True, False, False, True),
                    container=False,
                )
                negative = gr.Textbox(
                    label="Enter your negative prompt", show_label=True, max_lines=2
                ).style(
                    border=(True, False, True, True),
                    rounded=(True, False, False, True),
                    container=False,
                )
                btn = gr.Button("Run").style(
                    margin=False,
                    rounded=(False, True, True, False),
                )

        gallery = gr.Gallery(label="Generated images", show_label=False, elem_id="generated_id").style(
            grid=[2], 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], outputs=gallery)
        btn.click(infer, inputs=[text, negative], outputs=gallery)
gr.Markdown("""


# Authors

+ Arseniy Shakhmatov: [Github](https://github.com/cene555), [Blog](https://t.me/gradientdip)
+ Anton Razzhigaev: [Github](https://github.com/razzant), [Blog](https://t.me/abstractDL)
+ Aleksandr Nikolich: [Github](https://github.com/AlexWortega), [Blog](https://t.me/lovedeathtransformers)
+ Vladimir Arkhipkin: [Github](https://github.com/oriBetelgeuse)
+ Igor Pavlov: [Github](https://github.com/boomb0om)
+ Andrey Kuznetsov: [Github](https://github.com/kuznetsoffandrey)
+ Denis Dimitrov: [Github](https://github.com/denndimitrov)

    """
    )

demo.queue(max_size=15).launch()