diffusers/src/diffusers/image_processor.py at main · danieldai/diffusers · GitHub

History

648 lines (547 loc) · 25.2 KB

Raw

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

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

# http://www.apache.org/licenses/LICENSE-2.0

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

import warnings

from typing import List, Optional, Tuple, Union

import numpy as np

import PIL.Image

import torch

from PIL import Image

from .configuration_utils import ConfigMixin, register_to_config

from .utils import CONFIG_NAME, PIL_INTERPOLATION, deprecate

PipelineImageInput = Union[

PIL.Image.Image,

np.ndarray,

torch.FloatTensor,

List[PIL.Image.Image],

List[np.ndarray],

List[torch.FloatTensor],

]

PipelineDepthInput = Union[

PIL.Image.Image,

np.ndarray,

torch.FloatTensor,

List[PIL.Image.Image],

List[np.ndarray],

List[torch.FloatTensor],

]

class VaeImageProcessor(ConfigMixin):

"""

Image processor for VAE.

Args:

do_resize (`bool`, *optional*, defaults to `True`):

Whether to downscale the image's (height, width) dimensions to multiples of `vae_scale_factor`. Can accept

`height` and `width` arguments from [`image_processor.VaeImageProcessor.preprocess`] method.

vae_scale_factor (`int`, *optional*, defaults to `8`):

VAE scale factor. If `do_resize` is `True`, the image is automatically resized to multiples of this factor.

resample (`str`, *optional*, defaults to `lanczos`):

Resampling filter to use when resizing the image.

do_normalize (`bool`, *optional*, defaults to `True`):

Whether to normalize the image to [-1,1].

do_binarize (`bool`, *optional*, defaults to `False`):

Whether to binarize the image to 0/1.

do_convert_rgb (`bool`, *optional*, defaults to be `False`):

Whether to convert the images to RGB format.

do_convert_grayscale (`bool`, *optional*, defaults to be `False`):

Whether to convert the images to grayscale format.

"""

config_name = CONFIG_NAME

@register_to_config

def __init__(

self,

do_resize: bool = True,

vae_scale_factor: int = 8,

resample: str = "lanczos",

do_normalize: bool = True,

do_binarize: bool = False,

do_convert_rgb: bool = False,

do_convert_grayscale: bool = False,

super().__init__()

if do_convert_rgb and do_convert_grayscale:

raise ValueError(

"`do_convert_rgb` and `do_convert_grayscale` can not both be set to `True`,"

" if you intended to convert the image into RGB format, please set `do_convert_grayscale = False`.",

" if you intended to convert the image into grayscale format, please set `do_convert_rgb = False`",

)

self.config.do_convert_rgb = False

@staticmethod

def numpy_to_pil(images: np.ndarray) -> List[PIL.Image.Image]:

"""

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")

if images.shape[-1] == 1:

# special case for grayscale (single channel) images

pil_images = [Image.fromarray(image.squeeze(), mode="L") for image in images]

else:

pil_images = [Image.fromarray(image) for image in images]

return pil_images

@staticmethod

def pil_to_numpy(images: Union[List[PIL.Image.Image], PIL.Image.Image]) -> np.ndarray:

"""

Convert a PIL image or a list of PIL images to NumPy arrays.

"""

if not isinstance(images, list):

images = [images]

images = [np.array(image).astype(np.float32) / 255.0 for image in images]

images = np.stack(images, axis=0)

return images

@staticmethod

def numpy_to_pt(images: np.ndarray) -> torch.FloatTensor:

"""

Convert a NumPy image to a PyTorch tensor.

"""

if images.ndim == 3:

images = images[..., None]

images = torch.from_numpy(images.transpose(0, 3, 1, 2))

return images

@staticmethod

def pt_to_numpy(images: torch.FloatTensor) -> np.ndarray:

"""

Convert a PyTorch tensor to a NumPy image.

"""

images = images.cpu().permute(0, 2, 3, 1).float().numpy()

return images

@staticmethod

def normalize(images: Union[np.ndarray, torch.Tensor]) -> Union[np.ndarray, torch.Tensor]:

"""

Normalize an image array to [-1,1].

"""

return 2.0 * images - 1.0

@staticmethod

def denormalize(images: Union[np.ndarray, torch.Tensor]) -> Union[np.ndarray, torch.Tensor]:

"""

Denormalize an image array to [0,1].

"""

return (images / 2 + 0.5).clamp(0, 1)

@staticmethod

def convert_to_rgb(image: PIL.Image.Image) -> PIL.Image.Image:

"""

Converts a PIL image to RGB format.

"""

image = image.convert("RGB")

return image

@staticmethod

def convert_to_grayscale(image: PIL.Image.Image) -> PIL.Image.Image:

"""

Converts a PIL image to grayscale format.

"""

image = image.convert("L")

return image

def get_default_height_width(

self,

image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],

height: Optional[int] = None,

width: Optional[int] = None,

) -> Tuple[int, int]:

"""

This function return the height and width that are downscaled to the next integer multiple of

`vae_scale_factor`.

Args:

image(`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`):

The image input, can be a PIL image, numpy array or pytorch tensor. if it is a numpy array, should have

shape `[batch, height, width]` or `[batch, height, width, channel]` if it is a pytorch tensor, should

have shape `[batch, channel, height, width]`.

height (`int`, *optional*, defaults to `None`):

The height in preprocessed image. If `None`, will use the height of `image` input.

width (`int`, *optional*`, defaults to `None`):

The width in preprocessed. If `None`, will use the width of the `image` input.

"""

if height is None:

if isinstance(image, PIL.Image.Image):

height = image.height

elif isinstance(image, torch.Tensor):

height = image.shape[2]

else:

height = image.shape[1]

if width is None:

if isinstance(image, PIL.Image.Image):

width = image.width

elif isinstance(image, torch.Tensor):

width = image.shape[3]

else:

width = image.shape[2]

width, height = (

x - x % self.config.vae_scale_factor for x in (width, height)

) # resize to integer multiple of vae_scale_factor

return height, width

def resize(

self,

image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],

height: Optional[int] = None,

width: Optional[int] = None,

) -> Union[PIL.Image.Image, np.ndarray, torch.Tensor]:

"""

Resize image.

Args:

image (`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`):

The image input, can be a PIL image, numpy array or pytorch tensor.

height (`int`, *optional*, defaults to `None`):

The height to resize to.

width (`int`, *optional*`, defaults to `None`):

The width to resize to.

Returns:

`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`:

The resized image.

"""

if isinstance(image, PIL.Image.Image):

image = image.resize((width, height), resample=PIL_INTERPOLATION[self.config.resample])

elif isinstance(image, torch.Tensor):

image = torch.nn.functional.interpolate(

image,

size=(height, width),

)

elif isinstance(image, np.ndarray):

image = self.numpy_to_pt(image)

image = torch.nn.functional.interpolate(

image,

size=(height, width),

)

image = self.pt_to_numpy(image)

return image

def binarize(self, image: PIL.Image.Image) -> PIL.Image.Image:

"""

Create a mask.

Args:

image (`PIL.Image.Image`):

The image input, should be a PIL image.

Returns:

`PIL.Image.Image`:

The binarized image. Values less than 0.5 are set to 0, values greater than 0.5 are set to 1.

"""

image[image < 0.5] = 0

image[image >= 0.5] = 1

return image

def preprocess(

self,

image: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],

height: Optional[int] = None,

width: Optional[int] = None,

) -> torch.Tensor:

"""

Preprocess the image input. Accepted formats are PIL images, NumPy arrays or PyTorch tensors.

"""

supported_formats = (PIL.Image.Image, np.ndarray, torch.Tensor)

# Expand the missing dimension for 3-dimensional pytorch tensor or numpy array that represents grayscale image

if self.config.do_convert_grayscale and isinstance(image, (torch.Tensor, np.ndarray)) and image.ndim == 3:

if isinstance(image, torch.Tensor):

# if image is a pytorch tensor could have 2 possible shapes:

# 1. batch x height x width: we should insert the channel dimension at position 1

# 2. channnel x height x width: we should insert batch dimension at position 0,

# however, since both channel and batch dimension has same size 1, it is same to insert at position 1

# for simplicity, we insert a dimension of size 1 at position 1 for both cases

image = image.unsqueeze(1)

else:

# if it is a numpy array, it could have 2 possible shapes:

# 1. batch x height x width: insert channel dimension on last position

# 2. height x width x channel: insert batch dimension on first position

if image.shape[-1] == 1:

image = np.expand_dims(image, axis=0)

else:

image = np.expand_dims(image, axis=-1)

if isinstance(image, supported_formats):

image = [image]

elif not (isinstance(image, list) and all(isinstance(i, supported_formats) for i in image)):

raise ValueError(

f"Input is in incorrect format: {[type(i) for i in image]}. Currently, we only support {', '.join(supported_formats)}"

)

if isinstance(image[0], PIL.Image.Image):

if self.config.do_convert_rgb:

image = [self.convert_to_rgb(i) for i in image]

elif self.config.do_convert_grayscale:

image = [self.convert_to_grayscale(i) for i in image]

if self.config.do_resize:

height, width = self.get_default_height_width(image[0], height, width)

image = [self.resize(i, height, width) for i in image]

image = self.pil_to_numpy(image) # to np

image = self.numpy_to_pt(image) # to pt

elif isinstance(image[0], np.ndarray):

image = np.concatenate(image, axis=0) if image[0].ndim == 4 else np.stack(image, axis=0)

image = self.numpy_to_pt(image)

height, width = self.get_default_height_width(image, height, width)

if self.config.do_resize:

image = self.resize(image, height, width)

elif isinstance(image[0], torch.Tensor):

image = torch.cat(image, axis=0) if image[0].ndim == 4 else torch.stack(image, axis=0)

if self.config.do_convert_grayscale and image.ndim == 3:

image = image.unsqueeze(1)

channel = image.shape[1]

# don't need any preprocess if the image is latents

if channel == 4:

return image

height, width = self.get_default_height_width(image, height, width)

if self.config.do_resize:

image = self.resize(image, height, width)

# expected range [0,1], normalize to [-1,1]

do_normalize = self.config.do_normalize

if do_normalize and image.min() < 0:

warnings.warn(

"Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] "

f"when passing as pytorch tensor or numpy Array. You passed `image` with value range [{image.min()},{image.max()}]",

FutureWarning,

)

do_normalize = False

if do_normalize:

image = self.normalize(image)

if self.config.do_binarize:

image = self.binarize(image)

return image

def postprocess(

self,

image: torch.FloatTensor,

output_type: str = "pil",

do_denormalize: Optional[List[bool]] = None,

) -> Union[PIL.Image.Image, np.ndarray, torch.FloatTensor]:

"""

Postprocess the image output from tensor to `output_type`.

Args:

image (`torch.FloatTensor`):

The image input, should be a pytorch tensor with shape `B x C x H x W`.

output_type (`str`, *optional*, defaults to `pil`):

The output type of the image, can be one of `pil`, `np`, `pt`, `latent`.

do_denormalize (`List[bool]`, *optional*, defaults to `None`):

Whether to denormalize the image to [0,1]. If `None`, will use the value of `do_normalize` in the

`VaeImageProcessor` config.

Returns:

`PIL.Image.Image`, `np.ndarray` or `torch.FloatTensor`:

The postprocessed image.

"""

if not isinstance(image, torch.Tensor):

raise ValueError(

f"Input for postprocessing is in incorrect format: {type(image)}. We only support pytorch tensor"

)

if output_type not in ["latent", "pt", "np", "pil"]:

deprecation_message = (

f"the output_type {output_type} is outdated and has been set to `np`. Please make sure to set it to one of these instead: "

"`pil`, `np`, `pt`, `latent`"

)

deprecate("Unsupported output_type", "1.0.0", deprecation_message, standard_warn=False)

output_type = "np"

if output_type == "latent":

return image

if do_denormalize is None:

do_denormalize = [self.config.do_normalize] * image.shape[0]

image = torch.stack(

[self.denormalize(image[i]) if do_denormalize[i] else image[i] for i in range(image.shape[0])]

)

if output_type == "pt":

return image

image = self.pt_to_numpy(image)

if output_type == "np":

return image

if output_type == "pil":

return self.numpy_to_pil(image)

class VaeImageProcessorLDM3D(VaeImageProcessor):

"""

Image processor for VAE LDM3D.

Args:

do_resize (`bool`, *optional*, defaults to `True`):

Whether to downscale the image's (height, width) dimensions to multiples of `vae_scale_factor`.

vae_scale_factor (`int`, *optional*, defaults to `8`):

VAE scale factor. If `do_resize` is `True`, the image is automatically resized to multiples of this factor.

resample (`str`, *optional*, defaults to `lanczos`):

Resampling filter to use when resizing the image.

do_normalize (`bool`, *optional*, defaults to `True`):

Whether to normalize the image to [-1,1].

"""

config_name = CONFIG_NAME

@register_to_config

def __init__(

self,

do_resize: bool = True,

vae_scale_factor: int = 8,

resample: str = "lanczos",

do_normalize: bool = True,

super().__init__()

@staticmethod

def numpy_to_pil(images: np.ndarray) -> List[PIL.Image.Image]:

"""

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")

if images.shape[-1] == 1:

# special case for grayscale (single channel) images

pil_images = [Image.fromarray(image.squeeze(), mode="L") for image in images]

else:

pil_images = [Image.fromarray(image[:, :, :3]) for image in images]

return pil_images

@staticmethod

def depth_pil_to_numpy(images: Union[List[PIL.Image.Image], PIL.Image.Image]) -> np.ndarray:

"""

Convert a PIL image or a list of PIL images to NumPy arrays.

"""

if not isinstance(images, list):

images = [images]

images = [np.array(image).astype(np.float32) / (2**16 - 1) for image in images]

images = np.stack(images, axis=0)

return images

@staticmethod

def rgblike_to_depthmap(image: Union[np.ndarray, torch.Tensor]) -> Union[np.ndarray, torch.Tensor]:

"""

Args:

image: RGB-like depth image

Returns: depth map

"""

return image[:, :, 1] * 2**8 + image[:, :, 2]

def numpy_to_depth(self, images: np.ndarray) -> List[PIL.Image.Image]:

"""

Convert a NumPy depth image or a batch of images to a PIL image.

"""

if images.ndim == 3:

images = images[None, ...]

images_depth = images[:, :, :, 3:]

if images.shape[-1] == 6:

images_depth = (images_depth * 255).round().astype("uint8")

pil_images = [

Image.fromarray(self.rgblike_to_depthmap(image_depth), mode="I;16") for image_depth in images_depth

]

elif images.shape[-1] == 4:

images_depth = (images_depth * 65535.0).astype(np.uint16)

pil_images = [Image.fromarray(image_depth, mode="I;16") for image_depth in images_depth]

else:

raise Exception("Not supported")

return pil_images

def postprocess(

self,

image: torch.FloatTensor,

output_type: str = "pil",

do_denormalize: Optional[List[bool]] = None,

) -> Union[PIL.Image.Image, np.ndarray, torch.FloatTensor]:

"""

Postprocess the image output from tensor to `output_type`.

Args:

image (`torch.FloatTensor`):

The image input, should be a pytorch tensor with shape `B x C x H x W`.

output_type (`str`, *optional*, defaults to `pil`):

The output type of the image, can be one of `pil`, `np`, `pt`, `latent`.

do_denormalize (`List[bool]`, *optional*, defaults to `None`):

Whether to denormalize the image to [0,1]. If `None`, will use the value of `do_normalize` in the

`VaeImageProcessor` config.

Returns:

`PIL.Image.Image`, `np.ndarray` or `torch.FloatTensor`:

The postprocessed image.

"""

if not isinstance(image, torch.Tensor):

raise ValueError(

f"Input for postprocessing is in incorrect format: {type(image)}. We only support pytorch tensor"

)

if output_type not in ["latent", "pt", "np", "pil"]:

deprecation_message = (

f"the output_type {output_type} is outdated and has been set to `np`. Please make sure to set it to one of these instead: "

"`pil`, `np`, `pt`, `latent`"

)

deprecate("Unsupported output_type", "1.0.0", deprecation_message, standard_warn=False)

output_type = "np"

if do_denormalize is None:

do_denormalize = [self.config.do_normalize] * image.shape[0]

image = torch.stack(

[self.denormalize(image[i]) if do_denormalize[i] else image[i] for i in range(image.shape[0])]

)

image = self.pt_to_numpy(image)

if output_type == "np":

if image.shape[-1] == 6:

image_depth = np.stack([self.rgblike_to_depthmap(im[:, :, 3:]) for im in image], axis=0)

else:

image_depth = image[:, :, :, 3:]

return image[:, :, :, :3], image_depth

if output_type == "pil":

return self.numpy_to_pil(image), self.numpy_to_depth(image)

else:

raise Exception(f"This type {output_type} is not supported")

def preprocess(

self,

rgb: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],

depth: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],

height: Optional[int] = None,

width: Optional[int] = None,

target_res: Optional[int] = None,

) -> torch.Tensor:

"""

Preprocess the image input. Accepted formats are PIL images, NumPy arrays or PyTorch tensors.

"""

supported_formats = (PIL.Image.Image, np.ndarray, torch.Tensor)

# Expand the missing dimension for 3-dimensional pytorch tensor or numpy array that represents grayscale image

if self.config.do_convert_grayscale and isinstance(rgb, (torch.Tensor, np.ndarray)) and rgb.ndim == 3:

raise Exception("This is not yet supported")

if isinstance(rgb, supported_formats):

rgb = [rgb]

depth = [depth]

elif not (isinstance(rgb, list) and all(isinstance(i, supported_formats) for i in rgb)):

raise ValueError(

f"Input is in incorrect format: {[type(i) for i in rgb]}. Currently, we only support {', '.join(supported_formats)}"

)

if isinstance(rgb[0], PIL.Image.Image):

if self.config.do_convert_rgb:

raise Exception("This is not yet supported")

# rgb = [self.convert_to_rgb(i) for i in rgb]

# depth = [self.convert_to_depth(i) for i in depth] #TODO define convert_to_depth

if self.config.do_resize or target_res:

height, width = self.get_default_height_width(rgb[0], height, width) if not target_res else target_res

rgb = [self.resize(i, height, width) for i in rgb]

depth = [self.resize(i, height, width) for i in depth]

rgb = self.pil_to_numpy(rgb) # to np

rgb = self.numpy_to_pt(rgb) # to pt

depth = self.depth_pil_to_numpy(depth) # to np

depth = self.numpy_to_pt(depth) # to pt

elif isinstance(rgb[0], np.ndarray):

rgb = np.concatenate(rgb, axis=0) if rgb[0].ndim == 4 else np.stack(rgb, axis=0)

rgb = self.numpy_to_pt(rgb)

height, width = self.get_default_height_width(rgb, height, width)

if self.config.do_resize:

rgb = self.resize(rgb, height, width)

depth = np.concatenate(depth, axis=0) if rgb[0].ndim == 4 else np.stack(depth, axis=0)

depth = self.numpy_to_pt(depth)

height, width = self.get_default_height_width(depth, height, width)

if self.config.do_resize:

depth = self.resize(depth, height, width)

elif isinstance(rgb[0], torch.Tensor):

raise Exception("This is not yet supported")

# rgb = torch.cat(rgb, axis=0) if rgb[0].ndim == 4 else torch.stack(rgb, axis=0)

# if self.config.do_convert_grayscale and rgb.ndim == 3:

# rgb = rgb.unsqueeze(1)

# channel = rgb.shape[1]

# height, width = self.get_default_height_width(rgb, height, width)

# if self.config.do_resize:

# rgb = self.resize(rgb, height, width)

# depth = torch.cat(depth, axis=0) if depth[0].ndim == 4 else torch.stack(depth, axis=0)

# if self.config.do_convert_grayscale and depth.ndim == 3:

# depth = depth.unsqueeze(1)

# channel = depth.shape[1]

# # don't need any preprocess if the image is latents

# if depth == 4:

# return rgb, depth

# height, width = self.get_default_height_width(depth, height, width)

# if self.config.do_resize:

# depth = self.resize(depth, height, width)

# expected range [0,1], normalize to [-1,1]

do_normalize = self.config.do_normalize

if rgb.min() < 0 and do_normalize:

warnings.warn(

"Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] "

f"when passing as pytorch tensor or numpy Array. You passed `image` with value range [{rgb.min()},{rgb.max()}]",

FutureWarning,

)

do_normalize = False

if do_normalize:

rgb = self.normalize(rgb)

depth = self.normalize(depth)

if self.config.do_binarize:

rgb = self.binarize(rgb)

depth = self.binarize(depth)

return rgb, depth

diffusers/src/diffusers/image_processor.py at main · danieldai/diffusers · GitHub

Expand file tree

Breadcrumbs

image_processor.py

Latest commit

History

Breadcrumbs

image_processor.py

File metadata and controls