File size: 11,414 Bytes
1fe8a15
69e4d47
1fe8a15
 
 
 
 
69e4d47
1fe8a15
 
 
 
 
 
 
 
 
 
 
 
7302472
 
 
69e4d47
d42c56f
6a0fc9c
 
 
1fe8a15
69e4d47
1fe8a15
 
 
 
 
7302472
 
 
 
 
 
 
 
 
 
 
 
1fe8a15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69e4d47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1fe8a15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69e4d47
 
 
 
 
1fe8a15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97f4a6d
d42c56f
69e4d47
d42c56f
6a0fc9c
1fe8a15
 
d42c56f
1fe8a15
69e4d47
 
 
1fe8a15
 
 
d42c56f
1fe8a15
 
 
 
 
 
 
 
 
69e4d47
 
 
1fe8a15
 
13d077a
1fe8a15
 
 
 
 
 
 
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
import argparse, os, sys, glob
import cv2
import torch
import numpy as np
from omegaconf import OmegaConf
from PIL import Image
from tqdm import tqdm, trange
from imwatermark import WatermarkEncoder
from itertools import islice
from einops import rearrange
from torchvision.utils import make_grid
import time
from pytorch_lightning import seed_everything
from torch import autocast
from contextlib import contextmanager, nullcontext

from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler

from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
from transformers import AutoFeatureExtractor


# load safety model
safety_model_id = "CompVis/stable-diffusion-safety-checker"
safety_feature_extractor = AutoFeatureExtractor.from_pretrained(safety_model_id)
safety_checker = StableDiffusionSafetyChecker.from_pretrained(safety_model_id)


def chunk(it, size):
    it = iter(it)
    return iter(lambda: tuple(islice(it, size)), ())


def numpy_to_pil(images):
    """
    Convert a numpy image or a batch of images to a PIL image.
    """
    if images.ndim == 3:
        images = images[None, ...]
    images = (images * 255).round().astype("uint8")
    pil_images = [Image.fromarray(image) for image in images]

    return pil_images


def load_model_from_config(config, ckpt, verbose=False):
    print(f"Loading model from {ckpt}")
    pl_sd = torch.load(ckpt, map_location="cpu")
    if "global_step" in pl_sd:
        print(f"Global Step: {pl_sd['global_step']}")
    sd = pl_sd["state_dict"]
    model = instantiate_from_config(config.model)
    m, u = model.load_state_dict(sd, strict=False)
    if len(m) > 0 and verbose:
        print("missing keys:")
        print(m)
    if len(u) > 0 and verbose:
        print("unexpected keys:")
        print(u)

    model.cuda()
    model.eval()
    return model


def put_watermark(img, wm_encoder=None):
    if wm_encoder is not None:
        img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
        img = wm_encoder.encode(img, 'dwtDct')
        img = Image.fromarray(img[:, :, ::-1])
    return img


def load_replacement(x):
    try:
        hwc = x.shape
        y = Image.open("assets/rick.jpeg").convert("RGB").resize((hwc[1], hwc[0]))
        y = (np.array(y)/255.0).astype(x.dtype)
        assert y.shape == x.shape
        return y
    except Exception:
        return x


def check_safety(x_image):
    safety_checker_input = safety_feature_extractor(numpy_to_pil(x_image), return_tensors="pt")
    x_checked_image, has_nsfw_concept = safety_checker(images=x_image, clip_input=safety_checker_input.pixel_values)
    assert x_checked_image.shape[0] == len(has_nsfw_concept)
    for i in range(len(has_nsfw_concept)):
        if has_nsfw_concept[i]:
            x_checked_image[i] = load_replacement(x_checked_image[i])
    return x_checked_image, has_nsfw_concept


def main():
    parser = argparse.ArgumentParser()

    parser.add_argument(
        "--prompt",
        type=str,
        nargs="?",
        default="a painting of a virus monster playing guitar",
        help="the prompt to render"
    )
    parser.add_argument(
        "--outdir",
        type=str,
        nargs="?",
        help="dir to write results to",
        default="outputs/txt2img-samples"
    )
    parser.add_argument(
        "--skip_grid",
        action='store_true',
        help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",
    )
    parser.add_argument(
        "--skip_save",
        action='store_true',
        help="do not save individual samples. For speed measurements.",
    )
    parser.add_argument(
        "--ddim_steps",
        type=int,
        default=50,
        help="number of ddim sampling steps",
    )
    parser.add_argument(
        "--plms",
        action='store_true',
        help="use plms sampling",
    )
    parser.add_argument(
        "--laion400m",
        action='store_true',
        help="uses the LAION400M model",
    )
    parser.add_argument(
        "--fixed_code",
        action='store_true',
        help="if enabled, uses the same starting code across samples ",
    )
    parser.add_argument(
        "--ddim_eta",
        type=float,
        default=0.0,
        help="ddim eta (eta=0.0 corresponds to deterministic sampling",
    )
    parser.add_argument(
        "--n_iter",
        type=int,
        default=2,
        help="sample this often",
    )
    parser.add_argument(
        "--H",
        type=int,
        default=512,
        help="image height, in pixel space",
    )
    parser.add_argument(
        "--W",
        type=int,
        default=512,
        help="image width, in pixel space",
    )
    parser.add_argument(
        "--C",
        type=int,
        default=4,
        help="latent channels",
    )
    parser.add_argument(
        "--f",
        type=int,
        default=8,
        help="downsampling factor",
    )
    parser.add_argument(
        "--n_samples",
        type=int,
        default=3,
        help="how many samples to produce for each given prompt. A.k.a. batch size",
    )
    parser.add_argument(
        "--n_rows",
        type=int,
        default=0,
        help="rows in the grid (default: n_samples)",
    )
    parser.add_argument(
        "--scale",
        type=float,
        default=7.5,
        help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
    )
    parser.add_argument(
        "--from-file",
        type=str,
        help="if specified, load prompts from this file",
    )
    parser.add_argument(
        "--config",
        type=str,
        default="configs/stable-diffusion/v1-inference.yaml",
        help="path to config which constructs model",
    )
    parser.add_argument(
        "--ckpt",
        type=str,
        default="models/ldm/stable-diffusion-v1/model.ckpt",
        help="path to checkpoint of model",
    )
    parser.add_argument(
        "--seed",
        type=int,
        default=42,
        help="the seed (for reproducible sampling)",
    )
    parser.add_argument(
        "--precision",
        type=str,
        help="evaluate at this precision",
        choices=["full", "autocast"],
        default="autocast"
    )
    opt = parser.parse_args()

    if opt.laion400m:
        print("Falling back to LAION 400M model...")
        opt.config = "configs/latent-diffusion/txt2img-1p4B-eval.yaml"
        opt.ckpt = "models/ldm/text2img-large/model.ckpt"
        opt.outdir = "outputs/txt2img-samples-laion400m"

    seed_everything(opt.seed)

    config = OmegaConf.load(f"{opt.config}")
    model = load_model_from_config(config, f"{opt.ckpt}")

    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
    model = model.to(device)

    if opt.plms:
        sampler = PLMSSampler(model)
    else:
        sampler = DDIMSampler(model)

    os.makedirs(opt.outdir, exist_ok=True)
    outpath = opt.outdir

    print("Creating invisible watermark encoder (see https://github.com/ShieldMnt/invisible-watermark)...")
    wm = "StableDiffusionV1"
    wm_encoder = WatermarkEncoder()
    wm_encoder.set_watermark('bytes', wm.encode('utf-8'))

    batch_size = opt.n_samples
    n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
    if not opt.from_file:
        prompt = opt.prompt
        assert prompt is not None
        data = [batch_size * [prompt]]

    else:
        print(f"reading prompts from {opt.from_file}")
        with open(opt.from_file, "r") as f:
            data = f.read().splitlines()
            data = list(chunk(data, batch_size))

    sample_path = os.path.join(outpath, "samples")
    os.makedirs(sample_path, exist_ok=True)
    base_count = len(os.listdir(sample_path))
    grid_count = len(os.listdir(outpath)) - 1

    start_code = None
    if opt.fixed_code:
        start_code = torch.randn([opt.n_samples, opt.C, opt.H // opt.f, opt.W // opt.f], device=device)

    precision_scope = autocast if opt.precision=="autocast" else nullcontext
    with torch.no_grad():
        with precision_scope("cuda"):
            with model.ema_scope():
                tic = time.time()
                all_samples = list()
                for n in trange(opt.n_iter, desc="Sampling"):
                    for prompts in tqdm(data, desc="data"):
                        uc = None
                        if opt.scale != 1.0:
                            uc = model.get_learned_conditioning(batch_size * [""])
                        if isinstance(prompts, tuple):
                            prompts = list(prompts)
                        c = model.get_learned_conditioning(prompts)
                        shape = [opt.C, opt.H // opt.f, opt.W // opt.f]
                        samples_ddim, _ = sampler.sample(S=opt.ddim_steps,
                                                         conditioning=c,
                                                         batch_size=opt.n_samples,
                                                         shape=shape,
                                                         verbose=False,
                                                         unconditional_guidance_scale=opt.scale,
                                                         unconditional_conditioning=uc,
                                                         eta=opt.ddim_eta,
                                                         x_T=start_code)

                        x_samples_ddim = model.decode_first_stage(samples_ddim)
                        x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
                        x_samples_ddim = x_samples_ddim.cpu().permute(0, 2, 3, 1).numpy()

                        x_checked_image, has_nsfw_concept = check_safety(x_samples_ddim)

                        x_checked_image_torch = torch.from_numpy(x_checked_image).permute(0, 3, 1, 2)

                        if not opt.skip_save:
                            for x_sample in x_checked_image_torch:
                                x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
                                img = Image.fromarray(x_sample.astype(np.uint8))
                                img = put_watermark(img, wm_encoder)
                                img.save(os.path.join(sample_path, f"{base_count:05}.png"))
                                base_count += 1

                        if not opt.skip_grid:
                            all_samples.append(x_checked_image_torch)

                if not opt.skip_grid:
                    # additionally, save as grid
                    grid = torch.stack(all_samples, 0)
                    grid = rearrange(grid, 'n b c h w -> (n b) c h w')
                    grid = make_grid(grid, nrow=n_rows)

                    # to image
                    grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
                    img = Image.fromarray(grid.astype(np.uint8))
                    img = put_watermark(img, wm_encoder)
                    img.save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
                    grid_count += 1

                toc = time.time()

    print(f"Your samples are ready and waiting for you here: \n{outpath} \n"
          f" \nEnjoy.")


if __name__ == "__main__":
    main()