File size: 10,982 Bytes
9842c28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
import os
import random

import autocuda
from pyabsa.utils.pyabsa_utils import fprint

from diffusers import (
    AutoencoderKL,
    UNet2DConditionModel,
    StableDiffusionPipeline,
    StableDiffusionImg2ImgPipeline,
    DPMSolverMultistepScheduler,
)
import gradio as gr
import torch
from PIL import Image
import utils
import datetime
import time
import psutil

from Waifu2x.magnify import ImageMagnifier

start_time = time.time()
is_colab = utils.is_google_colab()

device = autocuda.auto_cuda()

magnifier = ImageMagnifier()


class Model:
    def __init__(self, name, path="", prefix=""):
        self.name = name
        self.path = path
        self.prefix = prefix
        self.pipe_t2i = None
        self.pipe_i2i = None


models = [
    # Model("anything v3", "anything-v3.0", "anything v3 style"),
    Model("anything v3", "Linaqruf/anything-v3.0", "anything v3 style"),
]
#  Model("Spider-Verse", "nitrosocke/spider-verse-diffusion", "spiderverse style "),
#  Model("Balloon Art", "Fictiverse/Stable_Diffusion_BalloonArt_Model", "BalloonArt "),
#  Model("Elden Ring", "nitrosocke/elden-ring-diffusion", "elden ring style "),
#  Model("Tron Legacy", "dallinmackay/Tron-Legacy-diffusion", "trnlgcy ")
# Model("Pokémon", "lambdalabs/sd-pokemon-diffusers", ""),
# Model("Pony Diffusion", "AstraliteHeart/pony-diffusion", ""),
# Model("Robo Diffusion", "nousr/robo-diffusion", ""),

scheduler = DPMSolverMultistepScheduler(
    beta_start=0.00085,
    beta_end=0.012,
    beta_schedule="scaled_linear",
    num_train_timesteps=1000,
    trained_betas=None,
    predict_epsilon=True,
    thresholding=False,
    algorithm_type="dpmsolver++",
    solver_type="midpoint",
    lower_order_final=True,
)

custom_model = None
if is_colab:
    models.insert(0, Model("Custom model"))
    custom_model = models[0]

last_mode = "txt2img"
current_model = models[1] if is_colab else models[0]
current_model_path = current_model.path

if is_colab:
    pipe = StableDiffusionPipeline.from_pretrained(
        current_model.path,
        torch_dtype=torch.float16,
        scheduler=scheduler,
        safety_checker=lambda images, clip_input: (images, False),
    )

else:  # download all models
    print(f"{datetime.datetime.now()} Downloading vae...")
    vae = AutoencoderKL.from_pretrained(
        current_model.path, subfolder="vae", torch_dtype=torch.float16
    )
    for model in models:
        try:
            print(f"{datetime.datetime.now()} Downloading {model.name} model...")
            unet = UNet2DConditionModel.from_pretrained(
                model.path, subfolder="unet", torch_dtype=torch.float16
            )
            model.pipe_t2i = StableDiffusionPipeline.from_pretrained(
                model.path,
                unet=unet,
                vae=vae,
                torch_dtype=torch.float16,
                scheduler=scheduler,
            )
            model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
                model.path,
                unet=unet,
                vae=vae,
                torch_dtype=torch.float16,
                scheduler=scheduler,
            )
        except Exception as e:
            print(
                f"{datetime.datetime.now()} Failed to load model "
                + model.name
                + ": "
                + str(e)
            )
            models.remove(model)
    pipe = models[0].pipe_t2i

if torch.cuda.is_available():
    pipe = pipe.to(device)

device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"


def error_str(error, title="Error"):
    return (
        f"""#### {title}
            {error}"""
        if error
        else ""
    )


def custom_model_changed(path):
    models[0].path = path
    global current_model
    current_model = models[0]


def on_model_change(model_name):
    prefix = (
        'Enter prompt. "'
        + next((m.prefix for m in models if m.name == model_name), None)
        + '" is prefixed automatically'
        if model_name != models[0].name
        else "Don't forget to use the custom model prefix in the prompt!"
    )

    return gr.update(visible=model_name == models[0].name), gr.update(
        placeholder=prefix
    )


def inference(
    model_name,
    prompt,
    guidance,
    steps,
    width=512,
    height=512,
    seed=0,
    img=None,
    strength=0.5,
    neg_prompt="",
):
    print(psutil.virtual_memory())  # print memory usage

    global current_model
    for model in models:
        if model.name == model_name:
            current_model = model
            model_path = current_model.path

    generator = torch.Generator("cuda").manual_seed(seed) if seed != 0 else None

    try:
        if img is not None:
            return (
                img_to_img(
                    model_path,
                    prompt,
                    neg_prompt,
                    img,
                    strength,
                    guidance,
                    steps,
                    width,
                    height,
                    generator,
                ),
                None,
            )
        else:
            return (
                txt_to_img(
                    model_path,
                    prompt,
                    neg_prompt,
                    guidance,
                    steps,
                    width,
                    height,
                    generator,
                ),
                None,
            )
    except Exception as e:
        fprint(e)
        return None, error_str(e)


def txt_to_img(
    model_path, prompt, neg_prompt, guidance, steps, width, height, generator
):
    print(f"{datetime.datetime.now()} txt_to_img, model: {current_model.name}")

    global last_mode
    global pipe
    global current_model_path
    if model_path != current_model_path or last_mode != "txt2img":
        current_model_path = model_path

        if is_colab or current_model == custom_model:
            pipe = StableDiffusionPipeline.from_pretrained(
                current_model_path,
                torch_dtype=torch.float16,
                scheduler=scheduler,
                safety_checker=lambda images, clip_input: (images, False),
            )
        else:
            pipe = pipe.to("cpu")
            pipe = current_model.pipe_t2i

        if torch.cuda.is_available():
            pipe = pipe.to(device)
        last_mode = "txt2img"

    prompt = current_model.prefix + prompt
    result = pipe(
        prompt,
        negative_prompt=neg_prompt,
        # num_images_per_prompt=n_images,
        num_inference_steps=int(steps),
        guidance_scale=guidance,
        width=width,
        height=height,
        generator=generator,
    )
    result.images[0] = magnifier.magnify(result.images[0])
    result.images[0] = magnifier.magnify(result.images[0])

    # save image
    result.images[0].save(
        "{}/{}.{}.{}.{}.{}.{}.{}.{}.png".format(
            saved_path,
            datetime.datetime.now().strftime("%Y%m%d-%H%M%S"),
            model_name,
            prompt,
            guidance,
            steps,
            width,
            height,
            seed,
        )
    )
    return replace_nsfw_images(result)


def img_to_img(
    model_path,
    prompt,
    neg_prompt,
    img,
    strength,
    guidance,
    steps,
    width,
    height,
    generator,
):
    print(f"{datetime.datetime.now()} img_to_img, model: {model_path}")

    global last_mode
    global pipe
    global current_model_path
    if model_path != current_model_path or last_mode != "img2img":
        current_model_path = model_path

        if is_colab or current_model == custom_model:
            pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
                current_model_path,
                torch_dtype=torch.float16,
                scheduler=scheduler,
                safety_checker=lambda images, clip_input: (images, False),
            )
        else:
            pipe = pipe.to("cpu")
            pipe = current_model.pipe_i2i

        if torch.cuda.is_available():
            pipe = pipe.to(device)
        last_mode = "img2img"

    prompt = current_model.prefix + prompt
    ratio = min(height / img.height, width / img.width)
    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
    result = pipe(
        prompt,
        negative_prompt=neg_prompt,
        # num_images_per_prompt=n_images,
        init_image=img,
        num_inference_steps=int(steps),
        strength=strength,
        guidance_scale=guidance,
        width=width,
        height=height,
        generator=generator,
    )
    result.images[0] = magnifier.magnify(result.images[0])
    result.images[0] = magnifier.magnify(result.images[0])

    # save image
    result.images[0].save(
        "{}/{}.{}.{}.{}.{}.{}.{}.{}.png".format(
            saved_path,
            datetime.datetime.now().strftime("%Y%m%d-%H%M%S"),
            model_name,
            prompt,
            guidance,
            steps,
            width,
            height,
            seed,
        )
    )
    return replace_nsfw_images(result)


def replace_nsfw_images(results):
    if is_colab:
        return results.images[0]

    for i in range(len(results.images)):
        if results.nsfw_content_detected[i]:
            results.images[i] = Image.open("nsfw.png")
    return results.images[0]


if __name__ == "__main__":
    # inference("DALL-E", "a dog", 0, 1000, 512, 512, 0, None, 0.5, "")
    model_name = "anything v3"
    saved_path = r"imgs"
    if not os.path.exists(saved_path):
        os.mkdir(saved_path)
    n = 0
    while True:
        prompt_keys = [
            "beautiful eyes",
            "cumulonimbus clouds",
            "sky",
            "detailed fingers",
            random.choice(
                [
                    "white hair",
                    "red hair",
                    "blonde hair",
                    "black hair",
                    "green hair",
                ]
            ),
            random.choice(
                [
                    "blue eyes",
                    "green eyes",
                    "red eyes",
                    "black eyes",
                    "yellow eyes",
                ]
            ),
            random.choice(["flower meadow", "garden", "city", "river", "beach"]),
            random.choice(["Elif", "Angel"]),
        ]
        guidance = 7.5
        steps = 25
        # width = 1024
        # height = 1024
        # width = 768
        # height = 1024
        width = 512
        height = 888
        seed = 0
        img = None
        strength = 0.5
        neg_prompt = ""
        inference(
            model_name,
            ".".join(prompt_keys),
            guidance,
            steps,
            width=width,
            height=height,
            seed=seed,
            img=img,
            strength=strength,
            neg_prompt=neg_prompt,
        )
        n += 1
        fprint(n)