File size: 12,716 Bytes
d9cf60c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
#!/usr/bin/env python
#patch 0.01
import os
import random
import uuid
import gradio as gr
import numpy as np
from PIL import Image
import spaces
import torch
from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDiscreteScheduler

huggingface_token = os.getenv("HUGGINGFACE_TOKEN")

examples = [
    ["assets/1.png", "Change the picture to black and white."],
    ["assets/2.png", "Add the chocolate topping to the ice cream."],
    ["assets/3.png", "Make the burger look spicy."],
    ["assets/4.png", "Change the color of the jacket to white."],
]

model_id = "timbrooks/instruct-pix2pix"
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None)
pipe.to("cuda")
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)

DESCRIPTION = """
"""
if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>⚠️Running on CPU, This may not work on CPU.</p>"

MAX_SEED = np.iinfo(np.int32).max
CACHE_EXAMPLES = False
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name

def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed

@spaces.GPU
def img2img_generate(
    prompt: str,
    init_image: gr.Image,
    negative_prompt: str = "",
    use_negative_prompt: bool = False,
    seed: int = 0,
    guidance_scale: float = 7,
    randomize_seed: bool = False,
    num_inference_steps=30,
    strength: float = 0.8,
    NUM_IMAGES_PER_PROMPT=1,
    use_resolution_binning: bool = True,
    progress=gr.Progress(track_tqdm=True),
):
    pipe.to(device)
    seed = int(randomize_seed_fn(seed, randomize_seed))
    generator = torch.Generator().manual_seed(seed)
    
    if not use_negative_prompt:
        negative_prompt = None  # type: ignore
    
    init_image = init_image.resize((768, 768))

    
    output = pipe(
        prompt=prompt,
        image=init_image,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        generator=generator,
        strength=strength,
        num_images_per_prompt=NUM_IMAGES_PER_PROMPT,
        output_type="pil",
    ).images

    return output

css = '''
.gradio-container{max-width: 800px !important}
h1{text-align:center}
'''
with gr.Blocks(css=css, theme="xiaobaiyuan/theme_brief") as demo:
    gr.Markdown(DESCRIPTION)
    with gr.Group():
        with gr.Row(equal_height=True):
            with gr.Column(scale=1):
                img2img_prompt = gr.Text(
                    label="Instruct",
                    show_label=False,
                    max_lines=1,
                    placeholder="Enter your prompt",
                    container=False,
                )
                init_image = gr.Image(label="Image", type="pil")
                with gr.Row():
                    img2img_run_button = gr.Button("Generate", variant="primary")
            with gr.Column(scale=1):
                img2img_output = gr.Gallery(label="Result", elem_id="gallery")
        with gr.Accordion("Advanced options", open=False, visible=False):
            with gr.Row():
                img2img_use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
                img2img_negative_prompt = gr.Text(
                    label="Negative prompt",
                    max_lines=1,
                    value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
                    visible=True,
                )
            img2img_seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )
            img2img_steps = gr.Slider(
                label="Steps",
                minimum=0,
                maximum=60,
                step=1,
                value=25,
            )
            img2img_number_image = gr.Slider(
                label="No.of.Images",
                minimum=1,
                maximum=4,
                step=1,
                value=1,
            )
            img2img_randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
            with gr.Row():
                img2img_guidance_scale = gr.Slider(
                    label="Guidance Scale",
                    minimum=0.1,
                    maximum=10,
                    step=0.1,
                    value=5.0,
                )
                strength = gr.Slider(label="Confidence", minimum=0.0, maximum=1.0, step=0.01, value=0.8)

    gr.Examples(
        examples=examples,
        inputs=[init_image, img2img_prompt],
        outputs=img2img_output,
        fn=img2img_generate,
        cache_examples=CACHE_EXAMPLES,
    )

    img2img_use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=img2img_use_negative_prompt,
        outputs=img2img_negative_prompt,
        api_name=False,
    )

    gr.on(
        triggers=[
            img2img_prompt.submit,
            img2img_negative_prompt.submit,
            img2img_run_button.click,
        ],
        fn=img2img_generate,
        inputs=[
            img2img_prompt,
            init_image,
            img2img_negative_prompt,
            img2img_use_negative_prompt,
            img2img_seed,
            img2img_guidance_scale,
            img2img_randomize_seed,
            img2img_steps,
            strength,
            img2img_number_image,
        ],
        outputs=[img2img_output],
        api_name="img-to-img",
    )

if __name__ == "__main__":
    demo.queue().launch(show_api=False, debug=False#!/usr/bin/env python
#patch 0.01
import os
import random
import uuid
import gradio as gr
import numpy as np
from PIL import Image
import spaces
import torch
from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDiscreteScheduler

huggingface_token = os.getenv("HUGGINGFACE_TOKEN")

examples = [
    ["assets/1.png", "Change the picture to black and white."],
    ["assets/2.png", "Add the chocolate topping to the ice cream."],
    ["assets/3.png", "Make the burger look spicy."],
    ["assets/4.png", "Change the color of the jacket to white."],
]

model_id = "timbrooks/instruct-pix2pix"
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None)
pipe.to("cuda")
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)

DESCRIPTION = """
"""
if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>⚠️Running on CPU, This may not work on CPU.</p>"

MAX_SEED = np.iinfo(np.int32).max
CACHE_EXAMPLES = False
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name

def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed

@spaces.GPU
def img2img_generate(
    prompt: str,
    init_image: gr.Image,
    negative_prompt: str = "",
    use_negative_prompt: bool = False,
    seed: int = 0,
    guidance_scale: float = 7,
    randomize_seed: bool = False,
    num_inference_steps=30,
    strength: float = 0.8,
    NUM_IMAGES_PER_PROMPT=1,
    use_resolution_binning: bool = True,
    progress=gr.Progress(track_tqdm=True),
):
    pipe.to(device)
    seed = int(randomize_seed_fn(seed, randomize_seed))
    generator = torch.Generator().manual_seed(seed)
    
    if not use_negative_prompt:
        negative_prompt = None  # type: ignore
    
    init_image = init_image.resize((768, 768))

    
    output = pipe(
        prompt=prompt,
        image=init_image,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        generator=generator,
        strength=strength,
        num_images_per_prompt=NUM_IMAGES_PER_PROMPT,
        output_type="pil",
    ).images

    return output

css = '''
.gradio-container{max-width: 800px !important}
h1{text-align:center}
'''
with gr.Blocks(css=css, theme="xiaobaiyuan/theme_brief") as demo:
    gr.Markdown(DESCRIPTION)
    with gr.Group():
        with gr.Row(equal_height=True):
            with gr.Column(scale=1):
                img2img_prompt = gr.Text(
                    label="Instruct",
                    show_label=False,
                    max_lines=1,
                    placeholder="Enter your prompt",
                    container=False,
                )
                init_image = gr.Image(label="Image", type="pil")
                with gr.Row():
                    img2img_run_button = gr.Button("Generate", variant="primary")
            with gr.Column(scale=1):
                img2img_output = gr.Gallery(label="Result", elem_id="gallery")
        with gr.Accordion("Advanced options", open=False, visible=False):
            with gr.Row():
                img2img_use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
                img2img_negative_prompt = gr.Text(
                    label="Negative prompt",
                    max_lines=1,
                    value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
                    visible=True,
                )
            img2img_seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )
            img2img_steps = gr.Slider(
                label="Steps",
                minimum=0,
                maximum=60,
                step=1,
                value=25,
            )
            img2img_number_image = gr.Slider(
                label="No.of.Images",
                minimum=1,
                maximum=4,
                step=1,
                value=1,
            )
            img2img_randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
            with gr.Row():
                img2img_guidance_scale = gr.Slider(
                    label="Guidance Scale",
                    minimum=0.1,
                    maximum=10,
                    step=0.1,
                    value=5.0,
                )
                strength = gr.Slider(label="Confidence", minimum=0.0, maximum=1.0, step=0.01, value=0.8)

    gr.Examples(
        examples=examples,
        inputs=[init_image, img2img_prompt],
        outputs=img2img_output,
        fn=img2img_generate,
        cache_examples=CACHE_EXAMPLES,
    )

    img2img_use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=img2img_use_negative_prompt,
        outputs=img2img_negative_prompt,
        api_name=False,
    )

    gr.on(
        triggers=[
            img2img_prompt.submit,
            img2img_negative_prompt.submit,
            img2img_run_button.click,
        ],
        fn=img2img_generate,
        inputs=[
            img2img_prompt,
            init_image,
            img2img_negative_prompt,
            img2img_use_negative_prompt,
            img2img_seed,
            img2img_guidance_scale,
            img2img_randomize_seed,
            img2img_steps,
            strength,
            img2img_number_image,
        ],
        outputs=[img2img_output],
        api_name="img-to-img",
    )

if __name__ == "__main__":
    demo.queue().launch(show_api=False, debug=False