File size: 23,182 Bytes
f0e1e27
a8a63dd
 
8747d5d
 
 
 
a8a63dd
 
 
 
 
 
 
 
3a2ea0a
 
a8a63dd
3a2ea0a
a8a63dd
b861db3
a8a63dd
 
 
 
 
 
 
b861db3
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8747d5d
 
 
a8a63dd
 
 
 
8747d5d
 
 
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8747d5d
 
 
 
 
 
 
 
a8a63dd
 
 
 
 
 
 
 
 
b861db3
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbd4c7f
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbd4c7f
a8a63dd
 
 
 
 
fbd4c7f
a8a63dd
 
8747d5d
 
 
a8a63dd
 
 
 
 
8747d5d
 
 
a8a63dd
 
 
 
 
 
 
 
 
 
8747d5d
 
 
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f0e1e27
a8a63dd
 
 
 
 
 
 
 
8747d5d
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8747d5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a2ea0a
 
b861db3
a8a63dd
 
f0e1e27
 
a8a63dd
 
 
 
8747d5d
 
 
a8a63dd
 
8747d5d
 
 
a8a63dd
 
 
 
 
 
 
 
 
8747d5d
 
 
 
a8a63dd
3a2ea0a
a8a63dd
 
8747d5d
 
 
 
 
 
 
 
 
 
 
 
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
3a2ea0a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a8a63dd
 
fbd4c7f
a8a63dd
fbd4c7f
a8a63dd
 
 
 
 
fbd4c7f
a8a63dd
fbd4c7f
a8a63dd
 
 
 
 
 
 
 
 
 
8747d5d
 
 
 
 
 
 
a8a63dd
 
 
8747d5d
 
b861db3
8747d5d
 
 
 
a8a63dd
 
 
 
 
 
8747d5d
 
 
 
 
 
 
 
 
 
 
a8a63dd
 
 
 
 
 
 
 
 
8747d5d
f0e1e27
8747d5d
 
 
 
3a2ea0a
8747d5d
3a2ea0a
 
8747d5d
 
b861db3
a8a63dd
 
 
 
8747d5d
b861db3
8747d5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a8a63dd
 
 
 
 
 
 
 
 
 
f0e1e27
b861db3
a8a63dd
 
 
 
 
 
 
 
f0e1e27
8747d5d
 
 
 
3a2ea0a
8747d5d
3a2ea0a
 
f0e1e27
a8a63dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8747d5d
 
 
 
 
 
 
 
 
 
 
a8a63dd
 
 
 
 
 
 
 
 
8747d5d
f0e1e27
8747d5d
 
 
 
3a2ea0a
8747d5d
3a2ea0a
 
8747d5d
 
a8a63dd
 
8747d5d
 
 
 
 
 
 
 
 
 
 
 
 
 
a8a63dd
b861db3
a8a63dd
 
 
fbd4c7f
a8a63dd
 
 
 
 
fbd4c7f
a8a63dd
8747d5d
a8a63dd
 
8747d5d
 
 
 
 
3a2ea0a
8747d5d
 
3a2ea0a
 
8747d5d
 
a8a63dd
 
 
 
 
 
 
 
 
8747d5d
 
3a2ea0a
8747d5d
 
 
3a2ea0a
a8a63dd
3a2ea0a
 
8747d5d
a8a63dd
 
 
 
 
 
 
 
 
 
3a2ea0a
 
 
 
 
 
a8a63dd
 
 
 
 
 
 
f0e1e27
a8a63dd
 
 
 
 
 
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
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
import torch
import torch.nn as nn
import torch.nn.functional as F
from diffusers.configuration_utils import ConfigMixin
from diffusers.models.modeling_utils import ModelMixin
from typing import Any, List, Optional
from torch import Tensor

from .util import (
    checkpoint,
    conv_nd,
    avg_pool_nd,
    zero_module,
    timestep_embedding,
)
from .attention import SpatialTransformer3D
from .adaptor import Resampler, ImageProjModel

import kiui

class CondSequential(nn.Sequential):
    """
    A sequential module that passes timestep embeddings to the children that
    support it as an extra input.
    """

    def forward(self, x, emb, context=None, num_frames=1):
        for layer in self:
            if isinstance(layer, ResBlock):
                x = layer(x, emb)
            elif isinstance(layer, SpatialTransformer3D):
                x = layer(x, context, num_frames=num_frames)
            else:
                x = layer(x)
        return x


class Upsample(nn.Module):
    """
    An upsampling layer with an optional convolution.
    :param channels: channels in the inputs and outputs.
    :param use_conv: a bool determining if a convolution is applied.
    :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
                 upsampling occurs in the inner-two dimensions.
    """

    def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
        super().__init__()
        self.channels = channels
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.dims = dims
        if use_conv:
            self.conv = conv_nd(
                dims, self.channels, self.out_channels, 3, padding=padding
            )

    def forward(self, x):
        assert x.shape[1] == self.channels
        if self.dims == 3:
            x = F.interpolate(
                x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest"
            )
        else:
            x = F.interpolate(x, scale_factor=2, mode="nearest")
        if self.use_conv:
            x = self.conv(x)
        return x


class Downsample(nn.Module):
    """
    A downsampling layer with an optional convolution.
    :param channels: channels in the inputs and outputs.
    :param use_conv: a bool determining if a convolution is applied.
    :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
                 downsampling occurs in the inner-two dimensions.
    """

    def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
        super().__init__()
        self.channels = channels
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.dims = dims
        stride = 2 if dims != 3 else (1, 2, 2)
        if use_conv:
            self.op = conv_nd(
                dims,
                self.channels,
                self.out_channels,
                3,
                stride=stride,
                padding=padding,
            )
        else:
            assert self.channels == self.out_channels
            self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)

    def forward(self, x):
        assert x.shape[1] == self.channels
        return self.op(x)


class ResBlock(nn.Module):
    """
    A residual block that can optionally change the number of channels.
    :param channels: the number of input channels.
    :param emb_channels: the number of timestep embedding channels.
    :param dropout: the rate of dropout.
    :param out_channels: if specified, the number of out channels.
    :param use_conv: if True and out_channels is specified, use a spatial
        convolution instead of a smaller 1x1 convolution to change the
        channels in the skip connection.
    :param dims: determines if the signal is 1D, 2D, or 3D.
    :param use_checkpoint: if True, use gradient checkpointing on this module.
    :param up: if True, use this block for upsampling.
    :param down: if True, use this block for downsampling.
    """

    def __init__(
        self,
        channels,
        emb_channels,
        dropout,
        out_channels=None,
        use_conv=False,
        use_scale_shift_norm=False,
        dims=2,
        use_checkpoint=False,
        up=False,
        down=False,
    ):
        super().__init__()
        self.channels = channels
        self.emb_channels = emb_channels
        self.dropout = dropout
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.use_checkpoint = use_checkpoint
        self.use_scale_shift_norm = use_scale_shift_norm

        self.in_layers = nn.Sequential(
            nn.GroupNorm(32, channels),
            nn.SiLU(),
            conv_nd(dims, channels, self.out_channels, 3, padding=1),
        )

        self.updown = up or down

        if up:
            self.h_upd = Upsample(channels, False, dims)
            self.x_upd = Upsample(channels, False, dims)
        elif down:
            self.h_upd = Downsample(channels, False, dims)
            self.x_upd = Downsample(channels, False, dims)
        else:
            self.h_upd = self.x_upd = nn.Identity()

        self.emb_layers = nn.Sequential(
            nn.SiLU(),
            nn.Linear(
                emb_channels,
                2 * self.out_channels if use_scale_shift_norm else self.out_channels,
            ),
        )
        self.out_layers = nn.Sequential(
            nn.GroupNorm(32, self.out_channels),
            nn.SiLU(),
            nn.Dropout(p=dropout),
            zero_module(
                conv_nd(dims, self.out_channels, self.out_channels, 3, padding=1)
            ),
        )

        if self.out_channels == channels:
            self.skip_connection = nn.Identity()
        elif use_conv:
            self.skip_connection = conv_nd(
                dims, channels, self.out_channels, 3, padding=1
            )
        else:
            self.skip_connection = conv_nd(dims, channels, self.out_channels, 1)

    def forward(self, x, emb):
        """
        Apply the block to a Tensor, conditioned on a timestep embedding.
        :param x: an [N x C x ...] Tensor of features.
        :param emb: an [N x emb_channels] Tensor of timestep embeddings.
        :return: an [N x C x ...] Tensor of outputs.
        """
        return checkpoint(
            self._forward, (x, emb), self.parameters(), self.use_checkpoint
        )

    def _forward(self, x, emb):
        if self.updown:
            in_rest, in_conv = self.in_layers[:-1], self.in_layers[-1]
            h = in_rest(x)
            h = self.h_upd(h)
            x = self.x_upd(x)
            h = in_conv(h)
        else:
            h = self.in_layers(x)
        emb_out = self.emb_layers(emb).type(h.dtype)
        while len(emb_out.shape) < len(h.shape):
            emb_out = emb_out[..., None]
        if self.use_scale_shift_norm:
            out_norm, out_rest = self.out_layers[0], self.out_layers[1:]
            scale, shift = torch.chunk(emb_out, 2, dim=1)
            h = out_norm(h) * (1 + scale) + shift
            h = out_rest(h)
        else:
            h = h + emb_out
            h = self.out_layers(h)
        return self.skip_connection(x) + h


class MultiViewUNetModel(ModelMixin, ConfigMixin):
    """
    The full multi-view UNet model with attention, timestep embedding and camera embedding.
    :param in_channels: channels in the input Tensor.
    :param model_channels: base channel count for the model.
    :param out_channels: channels in the output Tensor.
    :param num_res_blocks: number of residual blocks per downsample.
    :param attention_resolutions: a collection of downsample rates at which
        attention will take place. May be a set, list, or tuple.
        For example, if this contains 4, then at 4x downsampling, attention
        will be used.
    :param dropout: the dropout probability.
    :param channel_mult: channel multiplier for each level of the UNet.
    :param conv_resample: if True, use learned convolutions for upsampling and
        downsampling.
    :param dims: determines if the signal is 1D, 2D, or 3D.
    :param num_classes: if specified (as an int), then this model will be
        class-conditional with `num_classes` classes.
    :param use_checkpoint: use gradient checkpointing to reduce memory usage.
    :param num_heads: the number of attention heads in each attention layer.
    :param num_heads_channels: if specified, ignore num_heads and instead use
                               a fixed channel width per attention head.
    :param num_heads_upsample: works with num_heads to set a different number
                               of heads for upsampling. Deprecated.
    :param use_scale_shift_norm: use a FiLM-like conditioning mechanism.
    :param resblock_updown: use residual blocks for up/downsampling.
    :param use_new_attention_order: use a different attention pattern for potentially
                                    increased efficiency.
    :param camera_dim: dimensionality of camera input.
    """

    def __init__(
        self,
        image_size,
        in_channels,
        model_channels,
        out_channels,
        num_res_blocks,
        attention_resolutions,
        dropout=0,
        channel_mult=(1, 2, 4, 8),
        conv_resample=True,
        dims=2,
        num_classes=None,
        use_checkpoint=False,
        num_heads=-1,
        num_head_channels=-1,
        num_heads_upsample=-1,
        use_scale_shift_norm=False,
        resblock_updown=False,
        transformer_depth=1,  # custom transformer support
        context_dim=None,  # custom transformer support
        n_embed=None,  # custom support for prediction of discrete ids into codebook of first stage vq model
        disable_self_attentions=None,
        num_attention_blocks=None,
        disable_middle_self_attn=False,
        adm_in_channels=None,
        camera_dim=None,
        ip_dim=0,
        ip_weight=1.0,
        **kwargs,
    ):
        super().__init__()
        assert context_dim is not None
        
        if num_heads_upsample == -1:
            num_heads_upsample = num_heads

        if num_heads == -1:
            assert (
                num_head_channels != -1
            ), "Either num_heads or num_head_channels has to be set"

        if num_head_channels == -1:
            assert (
                num_heads != -1
            ), "Either num_heads or num_head_channels has to be set"

        self.image_size = image_size
        self.in_channels = in_channels
        self.model_channels = model_channels
        self.out_channels = out_channels
        if isinstance(num_res_blocks, int):
            self.num_res_blocks = len(channel_mult) * [num_res_blocks]
        else:
            if len(num_res_blocks) != len(channel_mult):
                raise ValueError(
                    "provide num_res_blocks either as an int (globally constant) or "
                    "as a list/tuple (per-level) with the same length as channel_mult"
                )
            self.num_res_blocks = num_res_blocks
        
        if num_attention_blocks is not None:
            assert len(num_attention_blocks) == len(self.num_res_blocks)
            assert all(
                map(
                    lambda i: self.num_res_blocks[i] >= num_attention_blocks[i],
                    range(len(num_attention_blocks)),
                )
            )
            print(
                f"Constructor of UNetModel received num_attention_blocks={num_attention_blocks}. "
                f"This option has LESS priority than attention_resolutions {attention_resolutions}, "
                f"i.e., in cases where num_attention_blocks[i] > 0 but 2**i not in attention_resolutions, "
                f"attention will still not be set."
            )

        self.attention_resolutions = attention_resolutions
        self.dropout = dropout
        self.channel_mult = channel_mult
        self.conv_resample = conv_resample
        self.num_classes = num_classes
        self.use_checkpoint = use_checkpoint
        self.num_heads = num_heads
        self.num_head_channels = num_head_channels
        self.num_heads_upsample = num_heads_upsample
        self.predict_codebook_ids = n_embed is not None

        self.ip_dim = ip_dim
        self.ip_weight = ip_weight

        if self.ip_dim > 0:
            self.image_embed = Resampler(
                dim=context_dim,
                depth=4,
                dim_head=64,
                heads=12,
                num_queries=ip_dim,  # num token
                embedding_dim=1280,
                output_dim=context_dim,
                ff_mult=4,
            )

        time_embed_dim = model_channels * 4
        self.time_embed = nn.Sequential(
            nn.Linear(model_channels, time_embed_dim),
            nn.SiLU(),
            nn.Linear(time_embed_dim, time_embed_dim),
        )

        if camera_dim is not None:
            time_embed_dim = model_channels * 4
            self.camera_embed = nn.Sequential(
                nn.Linear(camera_dim, time_embed_dim),
                nn.SiLU(),
                nn.Linear(time_embed_dim, time_embed_dim),
            )

        if self.num_classes is not None:
            if isinstance(self.num_classes, int):
                self.label_emb = nn.Embedding(self.num_classes, time_embed_dim)
            elif self.num_classes == "continuous":
                # print("setting up linear c_adm embedding layer")
                self.label_emb = nn.Linear(1, time_embed_dim)
            elif self.num_classes == "sequential":
                assert adm_in_channels is not None
                self.label_emb = nn.Sequential(
                    nn.Sequential(
                        nn.Linear(adm_in_channels, time_embed_dim),
                        nn.SiLU(),
                        nn.Linear(time_embed_dim, time_embed_dim),
                    )
                )
            else:
                raise ValueError()

        self.input_blocks = nn.ModuleList(
            [
                CondSequential(
                    conv_nd(dims, in_channels, model_channels, 3, padding=1)
                )
            ]
        )
        self._feature_size = model_channels
        input_block_chans = [model_channels]
        ch = model_channels
        ds = 1
        for level, mult in enumerate(channel_mult):
            for nr in range(self.num_res_blocks[level]):
                layers: List[Any] = [
                    ResBlock(
                        ch,
                        time_embed_dim,
                        dropout,
                        out_channels=mult * model_channels,
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = mult * model_channels
                if ds in attention_resolutions:
                    if num_head_channels == -1:
                        dim_head = ch // num_heads
                    else:
                        num_heads = ch // num_head_channels
                        dim_head = num_head_channels

                    if num_attention_blocks is None or nr < num_attention_blocks[level]:
                        layers.append(
                            SpatialTransformer3D(
                                ch,
                                num_heads,
                                dim_head,
                                context_dim=context_dim,
                                depth=transformer_depth,
                                use_checkpoint=use_checkpoint,
                                ip_dim=self.ip_dim,
                                ip_weight=self.ip_weight,
                            )
                        )
                self.input_blocks.append(CondSequential(*layers))
                self._feature_size += ch
                input_block_chans.append(ch)
            if level != len(channel_mult) - 1:
                out_ch = ch
                self.input_blocks.append(
                    CondSequential(
                        ResBlock(
                            ch,
                            time_embed_dim,
                            dropout,
                            out_channels=out_ch,
                            dims=dims,
                            use_checkpoint=use_checkpoint,
                            use_scale_shift_norm=use_scale_shift_norm,
                            down=True,
                        )
                        if resblock_updown
                        else Downsample(
                            ch, conv_resample, dims=dims, out_channels=out_ch
                        )
                    )
                )
                ch = out_ch
                input_block_chans.append(ch)
                ds *= 2
                self._feature_size += ch

        if num_head_channels == -1:
            dim_head = ch // num_heads
        else:
            num_heads = ch // num_head_channels
            dim_head = num_head_channels
        
        self.middle_block = CondSequential(
            ResBlock(
                ch,
                time_embed_dim,
                dropout,
                dims=dims,
                use_checkpoint=use_checkpoint,
                use_scale_shift_norm=use_scale_shift_norm,
            ),
            SpatialTransformer3D(
                ch,
                num_heads,
                dim_head,
                context_dim=context_dim,
                depth=transformer_depth,
                use_checkpoint=use_checkpoint,
                ip_dim=self.ip_dim,
                ip_weight=self.ip_weight,
            ), 
            ResBlock(
                ch,
                time_embed_dim,
                dropout,
                dims=dims,
                use_checkpoint=use_checkpoint,
                use_scale_shift_norm=use_scale_shift_norm,
            ),
        )
        self._feature_size += ch

        self.output_blocks = nn.ModuleList([])
        for level, mult in list(enumerate(channel_mult))[::-1]:
            for i in range(self.num_res_blocks[level] + 1):
                ich = input_block_chans.pop()
                layers = [
                    ResBlock(
                        ch + ich,
                        time_embed_dim,
                        dropout,
                        out_channels=model_channels * mult,
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = model_channels * mult
                if ds in attention_resolutions:
                    if num_head_channels == -1:
                        dim_head = ch // num_heads
                    else:
                        num_heads = ch // num_head_channels
                        dim_head = num_head_channels

                    if num_attention_blocks is None or i < num_attention_blocks[level]:
                        layers.append(
                            SpatialTransformer3D(
                                ch,
                                num_heads,
                                dim_head,
                                context_dim=context_dim,
                                depth=transformer_depth,
                                use_checkpoint=use_checkpoint,
                                ip_dim=self.ip_dim,
                                ip_weight=self.ip_weight,
                            )
                        )
                if level and i == self.num_res_blocks[level]:
                    out_ch = ch
                    layers.append(
                        ResBlock(
                            ch,
                            time_embed_dim,
                            dropout,
                            out_channels=out_ch,
                            dims=dims,
                            use_checkpoint=use_checkpoint,
                            use_scale_shift_norm=use_scale_shift_norm,
                            up=True,
                        )
                        if resblock_updown
                        else Upsample(ch, conv_resample, dims=dims, out_channels=out_ch)
                    )
                    ds //= 2
                self.output_blocks.append(CondSequential(*layers))
                self._feature_size += ch

        self.out = nn.Sequential(
            nn.GroupNorm(32, ch),
            nn.SiLU(),
            zero_module(conv_nd(dims, model_channels, out_channels, 3, padding=1)),
        )
        if self.predict_codebook_ids:
            self.id_predictor = nn.Sequential(
                nn.GroupNorm(32, ch),
                conv_nd(dims, model_channels, n_embed, 1),
                # nn.LogSoftmax(dim=1)  # change to cross_entropy and produce non-normalized logits
            )

    def forward(
        self,
        x,
        timesteps=None,
        context=None,
        y=None,
        camera=None,
        num_frames=1,
        ip=None,
        ip_img=None,
        **kwargs,
    ):
        """
        Apply the model to an input batch.
        :param x: an [(N x F) x C x ...] Tensor of inputs. F is the number of frames (views).
        :param timesteps: a 1-D batch of timesteps.
        :param context: conditioning plugged in via crossattn
        :param y: an [N] Tensor of labels, if class-conditional.
        :param num_frames: a integer indicating number of frames for tensor reshaping.
        :return: an [(N x F) x C x ...] Tensor of outputs. F is the number of frames (views).
        """
        assert (
            x.shape[0] % num_frames == 0
        ), "input batch size must be dividable by num_frames!"
        assert (y is not None) == (
            self.num_classes is not None
        ), "must specify y if and only if the model is class-conditional"

        hs = []

        t_emb = timestep_embedding(timesteps, self.model_channels, repeat_only=False).to(x.dtype)

        emb = self.time_embed(t_emb)

        if self.num_classes is not None:
            assert y is not None
            assert y.shape[0] == x.shape[0]
            emb = emb + self.label_emb(y)

        # Add camera embeddings
        if camera is not None:
            emb = emb + self.camera_embed(camera)
        
        # imagedream variant
        if self.ip_dim > 0:
            x[(num_frames - 1) :: num_frames, :, :, :] = ip_img
            ip_emb = self.image_embed(ip)
            context = torch.cat((context, ip_emb), 1)

        h = x
        for module in self.input_blocks:
            h = module(h, emb, context, num_frames=num_frames)
            hs.append(h)
        h = self.middle_block(h, emb, context, num_frames=num_frames)
        for module in self.output_blocks:
            h = torch.cat([h, hs.pop()], dim=1)
            h = module(h, emb, context, num_frames=num_frames)
        h = h.type(x.dtype)
        if self.predict_codebook_ids:
            return self.id_predictor(h)
        else:
            return self.out(h)