Spaces:
jbilcke-hf
/
Running on A10G

File size: 10,102 Bytes
65fd06d
 
 
 
 
 
 
 
 
 
 
99c8f9a
65fd06d
7f11b82
65fd06d
 
 
 
 
 
 
7f11b82
65fd06d
 
 
99c8f9a
65fd06d
 
99c8f9a
65fd06d
 
 
 
 
99c8f9a
65fd06d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f11b82
65fd06d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88cc598
 
 
0810225
 
88cc598
65fd06d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
452770a
65fd06d
7f11b82
 
 
 
 
65fd06d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b44efcb
65fd06d
 
 
 
 
 
 
 
 
 
 
 
b44efcb
65fd06d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f11b82
65fd06d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec9409f
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
#!/usr/bin/env python

from __future__ import annotations

import os
import random

import gradio as gr
import numpy as np
import PIL.Image
import torch
from diffusers import AutoencoderKL, DiffusionPipeline

DESCRIPTION = 'This space is an API service meant to be used by VideoChain and VideoQuest.\nWant to use this space for yourself? Please use the original code: [https://huggingface.co/spaces/hysts/SD-XL](https://huggingface.co/spaces/hysts/SD-XL)'
if not torch.cuda.is_available():
    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = int(os.getenv('MAX_IMAGE_SIZE', '1024'))
USE_TORCH_COMPILE = os.getenv('USE_TORCH_COMPILE') == '1'
ENABLE_CPU_OFFLOAD = os.getenv('ENABLE_CPU_OFFLOAD') == '1'
SECRET_TOKEN = os.getenv('SECRET_TOKEN', 'default_secret')

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
if torch.cuda.is_available():
    vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
    pipe = DiffusionPipeline.from_pretrained(
        'stabilityai/stable-diffusion-xl-base-1.0',
        vae=vae,
        torch_dtype=torch.float16,
        use_safetensors=True,
        variant='fp16')
    refiner = DiffusionPipeline.from_pretrained(
        'stabilityai/stable-diffusion-xl-refiner-1.0',
        vae=vae,
        torch_dtype=torch.float16,
        use_safetensors=True,
        variant='fp16')

    if ENABLE_CPU_OFFLOAD:
        pipe.enable_model_cpu_offload()
        refiner.enable_model_cpu_offload()
    else:
        pipe.to(device)
        refiner.to(device)

    if USE_TORCH_COMPILE:
        pipe.unet = torch.compile(pipe.unet,
                                  mode='reduce-overhead',
                                  fullgraph=True)
else:
    pipe = None
    refiner = None
    
def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed


def generate(prompt: str,
             negative_prompt: str = '',
             prompt_2: str = '',
             negative_prompt_2: str = '',
             use_negative_prompt: bool = False,
             use_prompt_2: bool = False,
             use_negative_prompt_2: bool = False,
             seed: int = 0,
             width: int = 1024,
             height: int = 1024,
             guidance_scale_base: float = 5.0,
             guidance_scale_refiner: float = 5.0,
             num_inference_steps_base: int = 50,
             num_inference_steps_refiner: int = 50,
             apply_refiner: bool = False,
             secret_token: str = '') -> PIL.Image.Image:
    if secret_token != SECRET_TOKEN:
        raise gr.Error(
            f'Invalid secret token. Please fork the original space if you want to use it for yourself.')
        
    generator = torch.Generator().manual_seed(seed)

    if not use_negative_prompt:
        negative_prompt = None  # type: ignore
    if not use_prompt_2:
        prompt_2 = None  # type: ignore
    if not use_negative_prompt_2:
        negative_prompt_2 = None  # type: ignore

    if not apply_refiner:
        return pipe(prompt=prompt,
                    negative_prompt=negative_prompt,
                    prompt_2=prompt_2,
                    negative_prompt_2=negative_prompt_2,
                    width=width,
                    height=height,
                    guidance_scale=guidance_scale_base,
                    num_inference_steps=num_inference_steps_base,
                    generator=generator,
                    output_type='pil').images[0]
    else:
        latents = pipe(prompt=prompt,
                       negative_prompt=negative_prompt,
                       prompt_2=prompt_2,
                       negative_prompt_2=negative_prompt_2,
                       width=width,
                       height=height,
                       guidance_scale=guidance_scale_base,
                       num_inference_steps=num_inference_steps_base,
                       generator=generator,
                       output_type='latent').images
        image = refiner(prompt=prompt,
                        negative_prompt=negative_prompt,
                        prompt_2=prompt_2,
                        negative_prompt_2=negative_prompt_2,
                        guidance_scale=guidance_scale_refiner,
                        num_inference_steps=num_inference_steps_refiner,
                        image=latents,
                        generator=generator).images[0]
        return image

with gr.Blocks(css='style.css') as demo:
    gr.Markdown(DESCRIPTION)
    with gr.Group():
        with gr.Row():
            secret_token = gr.Text(
                label='Secret Token',
                max_lines=1,
                placeholder='Enter your secret token',
            )
            prompt = gr.Text(
                label='Prompt',
                show_label=False,
                max_lines=1,
                placeholder='Enter your prompt',
                container=False,
            )
            run_button = gr.Button('Run', scale=0)
        result = gr.Image(label='Result', show_label=False)
        with gr.Accordion('Advanced options', open=False):
            with gr.Row():
                use_negative_prompt = gr.Checkbox(label='Use negative prompt',
                                                  value=False)
                use_prompt_2 = gr.Checkbox(label='Use prompt 2', value=False)
                use_negative_prompt_2 = gr.Checkbox(
                    label='Use negative prompt 2', value=False)
            negative_prompt = gr.Text(
                label='Negative prompt',
                max_lines=1,
                placeholder='Enter a negative prompt',
                visible=False,
            )
            prompt_2 = gr.Text(
                label='Prompt 2',
                max_lines=1,
                placeholder='Enter your prompt',
                visible=False,
            )
            negative_prompt_2 = gr.Text(
                label='Negative prompt 2',
                max_lines=1,
                placeholder='Enter a negative prompt',
                visible=False,
            )

            seed = gr.Slider(label='Seed',
                             minimum=0,
                             maximum=MAX_SEED,
                             step=1,
                             value=0)
            randomize_seed = gr.Checkbox(label='Randomize seed', value=True)
            with gr.Row():
                width = gr.Slider(
                    label='Width',
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
                height = gr.Slider(
                    label='Height',
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
            apply_refiner = gr.Checkbox(label='Apply refiner', value=False)
            with gr.Row():
                guidance_scale_base = gr.Slider(
                    label='Guidance scale for base',
                    minimum=1,
                    maximum=20,
                    step=0.1,
                    value=5.0)
                num_inference_steps_base = gr.Slider(
                    label='Number of inference steps for base',
                    minimum=10,
                    maximum=100,
                    step=1,
                    value=25)
            with gr.Row(visible=False) as refiner_params:
                guidance_scale_refiner = gr.Slider(
                    label='Guidance scale for refiner',
                    minimum=1,
                    maximum=20,
                    step=0.1,
                    value=5.0)
                num_inference_steps_refiner = gr.Slider(
                    label='Number of inference steps for refiner',
                    minimum=10,
                    maximum=100,
                    step=1,
                    value=25)

    use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt,
        outputs=negative_prompt,
        queue=False,
        api_name=False,
    )
    use_prompt_2.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_prompt_2,
        outputs=prompt_2,
        queue=False,
        api_name=False,
    )
    use_negative_prompt_2.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt_2,
        outputs=negative_prompt_2,
        queue=False,
        api_name=False,
    )
    apply_refiner.change(
        fn=lambda x: gr.update(visible=x),
        inputs=apply_refiner,
        outputs=refiner_params,
        queue=False,
        api_name=False,
    )

    inputs = [
        prompt,
        negative_prompt,
        prompt_2,
        negative_prompt_2,
        use_negative_prompt,
        use_prompt_2,
        use_negative_prompt_2,
        seed,
        width,
        height,
        guidance_scale_base,
        guidance_scale_refiner,
        num_inference_steps_base,
        num_inference_steps_refiner,
        apply_refiner,
        secret_token,
    ]
    prompt.submit(
        fn=randomize_seed_fn,
        inputs=[seed, randomize_seed],
        outputs=seed,
        queue=False,
        api_name=False,
    ).then(
        fn=generate,
        inputs=inputs,
        outputs=result,
        api_name='run',
    )
    negative_prompt.submit(
        fn=randomize_seed_fn,
        inputs=[seed, randomize_seed],
        outputs=seed,
        queue=False,
        api_name=False,
    ).then(
        fn=generate,
        inputs=inputs,
        outputs=result,
        api_name=False,
    )
    run_button.click(
        fn=randomize_seed_fn,
        inputs=[seed, randomize_seed],
        outputs=seed,
        queue=False,
        api_name=False,
    ).then(
        fn=generate,
        inputs=inputs,
        outputs=result,
        api_name=False,
    )
demo.queue(max_size=6).launch()