File size: 11,933 Bytes
b5d5c28
043f26d
 
b5d5c28
043f26d
 
 
 
 
 
 
d410924
 
043f26d
 
b5d5c28
 
043f26d
d410924
 
 
 
 
 
 
 
043f26d
 
 
 
 
 
 
 
 
 
 
 
d410924
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
043f26d
 
 
 
 
 
270829d
b5d5c28
 
0aa8fba
 
 
b5d5c28
 
043f26d
 
0aa8fba
 
 
 
043f26d
 
 
 
 
0aa8fba
 
043f26d
 
0aa8fba
043f26d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44ccef2
 
 
 
 
043f26d
b5d5c28
270829d
a6f876f
043f26d
 
b5d5c28
270829d
a6f876f
043f26d
 
b5d5c28
a6f876f
 
 
c9cd475
5d86663
c9cd475
 
 
 
 
 
 
 
 
 
 
 
 
043f26d
 
 
 
85457ac
043f26d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
587bddc
d410924
 
 
043f26d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
684a737
270829d
043f26d
 
b5d5c28
 
 
 
 
 
 
043f26d
 
b5d5c28
 
043f26d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d410924
 
 
 
4fe0536
 
 
 
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
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
from contextlib import nullcontext
import gradio as gr
import torch
from torch import autocast
from diffusers import DiffusionPipeline
from transformers import (
    pipeline,
    MBart50TokenizerFast,
    MBartForConditionalGeneration,
)

import utils

device = "cuda" if torch.cuda.is_available() else "cpu"
device_dict = {"cuda": 0, "cpu": -1}
context = autocast if device == "cuda" else nullcontext
dtype = torch.float16 if device == "cuda" else torch.float32

# Detect if code is running in Colab
is_colab = utils.is_google_colab()
colab_instruction = "" if is_colab else """
<p>You can skip the queue using Colab: 
<a href="https://colab.research.google.com/drive/1nhXyddThldnxPfIYO2my_bYinlMUW30R?usp=sharing">
<img data-canonical-src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>"""
device_print = "GPU πŸ”₯" if torch.cuda.is_available() else "CPU πŸ₯Ά"

# Add language detection pipeline
language_detection_model_ckpt = "papluca/xlm-roberta-base-language-detection"
language_detection_pipeline = pipeline("text-classification",
                                       model=language_detection_model_ckpt,
                                       device=device_dict[device])

# Add model for language translation
trans_tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-one-mmt")
trans_model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-one-mmt").to(device)

model_id = "CompVis/stable-diffusion-v1-4"

if is_colab:
    pipe = DiffusionPipeline.from_pretrained(
        model_id,
        custom_pipeline="multilingual_stable_diffusion",
        detection_pipeline=language_detection_pipeline,
        translation_model=trans_model,
        translation_tokenizer=trans_tokenizer,
        revision="fp16",
        torch_dtype=dtype,
    )
else:
    import streamlit as st
    pipe = DiffusionPipeline.from_pretrained(
        model_id,
        custom_pipeline="multilingual_stable_diffusion",
        use_auth_token=st.secrets["USER_TOKEN"],
        detection_pipeline=language_detection_pipeline,
        translation_model=trans_model,
        translation_tokenizer=trans_tokenizer,
        revision="fp16",
        torch_dtype=dtype,
    )

pipe = pipe.to(device)

#torch.backends.cudnn.benchmark = True
num_samples = 2

def infer(prompt, steps, scale):
    
    with context("cuda"):
        images = pipe(num_samples*[prompt],
                      guidance_scale=scale,
                      num_inference_steps=int(steps)).images

    return images

css = """
        a {
            color: inherit;
            text-decoration: underline;
        }
        .gradio-container {
            font-family: 'IBM Plex Sans', sans-serif;
        }
        .gr-button {
            color: white;
            border-color: #0000FF;
            background: #0000FF;
        }
        input[type='range'] {
            accent-color: #0000FF;
        }
        .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 {
            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 = [
    [
        'נמר ΧœΧ‘ΧŸ Χ”Χ•ΧœΧš גל Χ—Χ•Χ£ הים, Χ©Χ§Χ™Χ’Χ”, צבגים חזקים, Χ¦ΧœΧœΧ™Χ•Χͺ, Χ¨Χ–ΧœΧ•Χ¦Χ™Χ” Χ’Χ‘Χ•Χ”Χ”, ΧžΧΧ•Χ“ ΧžΧ€Χ•Χ¨Χ˜ Χ•ΧžΧ“Χ•Χ™Χ™Χ§, Χ¨Χ™ΧΧœΧ™Χ‘Χ˜Χ™',
        50,
        7.5,
    ],
    [
        'Una casa en la playa en un atardecer lluvioso',
        45,
        7.5,
    ],
    [
        'Ein Hund, der Orange isst',
        45,
        7.5,
    ],
    [
        "Photo d'un restaurant parisien",
        45,
        7.5,
    ],
    [
        "Franču restorāna fotogrāfija",
        45,
        7.5,
    ],
    [
        "ΰ°ͺారిసియన్ ΰ°°ΰ±†ΰ°Έΰ±ΰ°Ÿΰ°Ύΰ°°ΰ±†ΰ°‚ΰ°Ÿΰ± ΰ°―ΰ±Šΰ°•ΰ±ΰ°• ΰ°«ΰ±‹ΰ°Ÿΰ±‹",
        45,
        7.5,
    ],
    [
        "ءورة Ω„Ω…Ψ·ΨΉΩ… باريسي",
        45,
        7.5,
    ],
]

with block as demo:
    gr.HTML(
        f"""
            <div style="text-align: center; max-width: 650px; margin: 0 auto;">
              <div
                style="
                  display: inline-flex;
                  align-items: center;
                  gap: 0.8rem;
                  font-size: 1.75rem;
                "
              >
                <h1 style="font-weight: 900; margin-bottom: 7px;">
                  Multilingual Stable Diffusion
                </h1>
              </div>
              <p style="margin-bottom: 10px; font-size: 94%">
                Stable Diffusion Pipeline that supports prompts in 50 different languages.
              </p>
              <p style="margin-bottom: 10px; font-size: 94%">
                {colab_instruction}
                Running on <b>{device_print}</b>{(" in a <b>Google Colab</b>." if is_colab else "")}
              </p>
            </div>
        """
    )
    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=False, max_lines=1
                ).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="gallery").style(
            grid=[2], height="auto"
        )
        
        with gr.Row(elem_id="advanced-options"):
            steps = gr.Slider(label="Steps", minimum=5, maximum=50, value=45, step=5)
            scale = gr.Slider(
                label="Guidance Scale", minimum=0, maximum=50, value=7.5, step=0.1
            )
        
        ex = gr.Examples(examples=examples, fn=infer, inputs=[text, steps, scale], outputs=gallery, cache_examples=False)
        ex.dataset.headers = [""]
        
        text.submit(infer, inputs=[text, steps, scale], outputs=gallery)
        btn.click(infer, inputs=[text, steps, scale], outputs=gallery)

    gr.HTML(
            """
                <div class="footer">
                    <p>Stable Diffusion model that supports multiple languages by <a href="https://huggingface.co/juancopi81" style="text-decoration: underline;" target="_blank">juancopi81</a>
                    </p>
                </div>
                <div class="acknowledgments">
                    <p><h4>LICENSE</h4>
The model is licensed with a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
                    <p><h4>Biases and content acknowledgment</h4>
Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
               </div>
           """
        )
    gr.Markdown('''
      [![Twitter Follow](https://img.shields.io/twitter/follow/juancopi81?style=social)](https://twitter.com/juancopi81)
      ![visitors](https://visitor-badge.glitch.me/badge?page_id=Juancopi81.MultilingualStableDiffusion)
    ''')

if not is_colab:
    demo.queue(concurrency_count=1)
demo.launch(debug=is_colab, share=is_colab)