File size: 17,969 Bytes
6c6eb37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2024 The HuggingFace Team. All rights reserved.
#
# 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.
from typing import Any, Dict, Optional, Tuple, Union

import torch
import torch.utils.checkpoint
from diffusers.models.unets.unet_2d_condition import UNet2DConditionOutput
from diffusers.utils import (
    USE_PEFT_BACKEND,
    deprecate,
    logging,
    scale_lora_layers,
    unscale_lora_layers,
)

logger = logging.get_logger(__name__)  # pylint: disable=invalid-name


def UNet2DConditionModel_forward(

    self,

    sample: torch.FloatTensor,

    timestep: Union[torch.Tensor, float, int],

    encoder_hidden_states: torch.Tensor,

    class_labels: Optional[torch.Tensor] = None,

    timestep_cond: Optional[torch.Tensor] = None,

    attention_mask: Optional[torch.Tensor] = None,

    cross_attention_kwargs: Optional[Dict[str, Any]] = None,

    added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,

    down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,

    mid_block_additional_residual: Optional[torch.Tensor] = None,

    down_intrablock_additional_residuals: Optional[Tuple[torch.Tensor]] = None,

    encoder_attention_mask: Optional[torch.Tensor] = None,

    return_dict: bool = True,

    down_block_add_samples: Optional[Tuple[torch.Tensor]] = None,

    mid_block_add_sample: Optional[Tuple[torch.Tensor]] = None,

    up_block_add_samples: Optional[Tuple[torch.Tensor]] = None,

) -> Union[UNet2DConditionOutput, Tuple]:
    r"""

    The [`UNet2DConditionModel`] forward method.



    Args:

        sample (`torch.FloatTensor`):

            The noisy input tensor with the following shape `(batch, channel, height, width)`.

        timestep (`torch.FloatTensor` or `float` or `int`): The number of timesteps to denoise an input.

        encoder_hidden_states (`torch.FloatTensor`):

            The encoder hidden states with shape `(batch, sequence_length, feature_dim)`.

        class_labels (`torch.Tensor`, *optional*, defaults to `None`):

            Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.

        timestep_cond: (`torch.Tensor`, *optional*, defaults to `None`):

            Conditional embeddings for timestep. If provided, the embeddings will be summed with the samples passed

            through the `self.time_embedding` layer to obtain the timestep embeddings.

        attention_mask (`torch.Tensor`, *optional*, defaults to `None`):

            An attention mask of shape `(batch, key_tokens)` is applied to `encoder_hidden_states`. If `1` the mask

            is kept, otherwise if `0` it is discarded. Mask will be converted into a bias, which adds large

            negative values to the attention scores corresponding to "discard" tokens.

        cross_attention_kwargs (`dict`, *optional*):

            A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under

            `self.processor` in

            [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).

        added_cond_kwargs: (`dict`, *optional*):

            A kwargs dictionary containing additional embeddings that if specified are added to the embeddings that

            are passed along to the UNet blocks.

        down_block_additional_residuals: (`tuple` of `torch.Tensor`, *optional*):

            A tuple of tensors that if specified are added to the residuals of down unet blocks.

        mid_block_additional_residual: (`torch.Tensor`, *optional*):

            A tensor that if specified is added to the residual of the middle unet block.

        encoder_attention_mask (`torch.Tensor`):

            A cross-attention mask of shape `(batch, sequence_length)` is applied to `encoder_hidden_states`. If

            `True` the mask is kept, otherwise if `False` it is discarded. Mask will be converted into a bias,

            which adds large negative values to the attention scores corresponding to "discard" tokens.

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

            Whether or not to return a [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] instead of a plain

            tuple.

        cross_attention_kwargs (`dict`, *optional*):

            A kwargs dictionary that if specified is passed along to the [`AttnProcessor`].

        added_cond_kwargs: (`dict`, *optional*):

            A kwargs dictionary containin additional embeddings that if specified are added to the embeddings that

            are passed along to the UNet blocks.

        down_block_additional_residuals (`tuple` of `torch.Tensor`, *optional*):

            additional residuals to be added to UNet long skip connections from down blocks to up blocks for

            example from ControlNet side model(s)

        mid_block_additional_residual (`torch.Tensor`, *optional*):

            additional residual to be added to UNet mid block output, for example from ControlNet side model

        down_intrablock_additional_residuals (`tuple` of `torch.Tensor`, *optional*):

            additional residuals to be added within UNet down blocks, for example from T2I-Adapter side model(s)



    Returns:

        [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] or `tuple`:

            If `return_dict` is True, an [`~models.unets.unet_2d_condition.UNet2DConditionOutput`] is returned, otherwise

            a `tuple` is returned where the first element is the sample tensor.

    """
    # By default samples have to be AT least a multiple of the overall upsampling factor.
    # The overall upsampling factor is equal to 2 ** (# num of upsampling layers).
    # However, the upsampling interpolation output size can be forced to fit any upsampling size
    # on the fly if necessary.
    default_overall_up_factor = 2**self.num_upsamplers

    # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
    forward_upsample_size = False
    upsample_size = None

    for dim in sample.shape[-2:]:
        if dim % default_overall_up_factor != 0:
            # Forward upsample size to force interpolation output size.
            forward_upsample_size = True
            break

    # ensure attention_mask is a bias, and give it a singleton query_tokens dimension
    # expects mask of shape:
    #   [batch, key_tokens]
    # adds singleton query_tokens dimension:
    #   [batch,                    1, key_tokens]
    # this helps to broadcast it as a bias over attention scores, which will be in one of the following shapes:
    #   [batch,  heads, query_tokens, key_tokens] (e.g. torch sdp attn)
    #   [batch * heads, query_tokens, key_tokens] (e.g. xformers or classic attn)
    if attention_mask is not None:
        # assume that mask is expressed as:
        #   (1 = keep,      0 = discard)
        # convert mask into a bias that can be added to attention scores:
        #       (keep = +0,     discard = -10000.0)
        attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
        attention_mask = attention_mask.unsqueeze(1)

    # convert encoder_attention_mask to a bias the same way we do for attention_mask
    if encoder_attention_mask is not None:
        encoder_attention_mask = (
            1 - encoder_attention_mask.to(sample.dtype)
        ) * -10000.0
        encoder_attention_mask = encoder_attention_mask.unsqueeze(1)

    # 0. center input if necessary
    if self.config.center_input_sample:
        sample = 2 * sample - 1.0

    # 1. time
    t_emb = self.get_time_embed(sample=sample, timestep=timestep)
    emb = self.time_embedding(t_emb, timestep_cond)
    aug_emb = None

    class_emb = self.get_class_embed(sample=sample, class_labels=class_labels)
    if class_emb is not None:
        if self.config.class_embeddings_concat:
            emb = torch.cat([emb, class_emb], dim=-1)
        else:
            emb = emb + class_emb

    aug_emb = self.get_aug_embed(
        emb=emb,
        encoder_hidden_states=encoder_hidden_states,
        added_cond_kwargs=added_cond_kwargs,
    )
    if self.config.addition_embed_type == "image_hint":
        aug_emb, hint = aug_emb
        sample = torch.cat([sample, hint], dim=1)

    emb = emb + aug_emb if aug_emb is not None else emb

    if self.time_embed_act is not None:
        emb = self.time_embed_act(emb)

    encoder_hidden_states = self.process_encoder_hidden_states(
        encoder_hidden_states=encoder_hidden_states,
        added_cond_kwargs=added_cond_kwargs,
    )

    # 2. pre-process
    sample = self.conv_in(sample)

    # 2.5 GLIGEN position net
    if (
        cross_attention_kwargs is not None
        and cross_attention_kwargs.get("gligen", None) is not None
    ):
        cross_attention_kwargs = cross_attention_kwargs.copy()
        gligen_args = cross_attention_kwargs.pop("gligen")
        cross_attention_kwargs["gligen"] = {"objs": self.position_net(**gligen_args)}

    # 3. down
    lora_scale = (
        cross_attention_kwargs.get("scale", 1.0)
        if cross_attention_kwargs is not None
        else 1.0
    )
    if USE_PEFT_BACKEND:
        # weight the lora layers by setting `lora_scale` for each PEFT layer
        scale_lora_layers(self, lora_scale)

    is_controlnet = (
        mid_block_additional_residual is not None
        and down_block_additional_residuals is not None
    )
    # using new arg down_intrablock_additional_residuals for T2I-Adapters, to distinguish from controlnets
    is_adapter = down_intrablock_additional_residuals is not None
    # maintain backward compatibility for legacy usage, where
    #       T2I-Adapter and ControlNet both use down_block_additional_residuals arg
    #       but can only use one or the other
    is_brushnet = (
        down_block_add_samples is not None
        and mid_block_add_sample is not None
        and up_block_add_samples is not None
    )
    if (
        not is_adapter
        and mid_block_additional_residual is None
        and down_block_additional_residuals is not None
    ):
        deprecate(
            "T2I should not use down_block_additional_residuals",
            "1.3.0",
            "Passing intrablock residual connections with `down_block_additional_residuals` is deprecated \

                   and will be removed in diffusers 1.3.0.  `down_block_additional_residuals` should only be used \

                   for ControlNet. Please make sure use `down_intrablock_additional_residuals` instead. ",
            standard_warn=False,
        )
        down_intrablock_additional_residuals = down_block_additional_residuals
        is_adapter = True

    down_block_res_samples = (sample,)

    if is_brushnet:
        sample = sample + down_block_add_samples.pop(0)

    for downsample_block in self.down_blocks:
        if (
            hasattr(downsample_block, "has_cross_attention")
            and downsample_block.has_cross_attention
        ):
            # For t2i-adapter CrossAttnDownBlock2D
            additional_residuals = {}
            if is_adapter and len(down_intrablock_additional_residuals) > 0:
                additional_residuals["additional_residuals"] = (
                    down_intrablock_additional_residuals.pop(0)
                )

            if is_brushnet and len(down_block_add_samples) > 0:
                additional_residuals["down_block_add_samples"] = [
                    down_block_add_samples.pop(0)
                    for _ in range(
                        len(downsample_block.resnets)
                        + (downsample_block.downsamplers != None)
                    )
                ]

            sample, res_samples = downsample_block(
                hidden_states=sample,
                temb=emb,
                encoder_hidden_states=encoder_hidden_states,
                attention_mask=attention_mask,
                cross_attention_kwargs=cross_attention_kwargs,
                encoder_attention_mask=encoder_attention_mask,
                **additional_residuals,
            )
        else:
            additional_residuals = {}
            if is_brushnet and len(down_block_add_samples) > 0:
                additional_residuals["down_block_add_samples"] = [
                    down_block_add_samples.pop(0)
                    for _ in range(
                        len(downsample_block.resnets)
                        + (downsample_block.downsamplers != None)
                    )
                ]

            sample, res_samples = downsample_block(
                hidden_states=sample,
                temb=emb,
                scale=lora_scale,
                **additional_residuals,
            )
            if is_adapter and len(down_intrablock_additional_residuals) > 0:
                sample += down_intrablock_additional_residuals.pop(0)

        down_block_res_samples += res_samples

    if is_controlnet:
        new_down_block_res_samples = ()

        for down_block_res_sample, down_block_additional_residual in zip(
            down_block_res_samples, down_block_additional_residuals
        ):
            down_block_res_sample = (
                down_block_res_sample + down_block_additional_residual
            )
            new_down_block_res_samples = new_down_block_res_samples + (
                down_block_res_sample,
            )

        down_block_res_samples = new_down_block_res_samples

    # 4. mid
    if self.mid_block is not None:
        if (
            hasattr(self.mid_block, "has_cross_attention")
            and self.mid_block.has_cross_attention
        ):
            sample = self.mid_block(
                sample,
                emb,
                encoder_hidden_states=encoder_hidden_states,
                attention_mask=attention_mask,
                cross_attention_kwargs=cross_attention_kwargs,
                encoder_attention_mask=encoder_attention_mask,
            )
        else:
            sample = self.mid_block(sample, emb)

        # To support T2I-Adapter-XL
        if (
            is_adapter
            and len(down_intrablock_additional_residuals) > 0
            and sample.shape == down_intrablock_additional_residuals[0].shape
        ):
            sample += down_intrablock_additional_residuals.pop(0)

    if is_controlnet:
        sample = sample + mid_block_additional_residual

    if is_brushnet:
        sample = sample + mid_block_add_sample

    # 5. up
    for i, upsample_block in enumerate(self.up_blocks):
        is_final_block = i == len(self.up_blocks) - 1

        res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
        down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]

        # if we have not reached the final block and need to forward the
        # upsample size, we do it here
        if not is_final_block and forward_upsample_size:
            upsample_size = down_block_res_samples[-1].shape[2:]

        if (
            hasattr(upsample_block, "has_cross_attention")
            and upsample_block.has_cross_attention
        ):
            additional_residuals = {}
            if is_brushnet and len(up_block_add_samples) > 0:
                additional_residuals["up_block_add_samples"] = [
                    up_block_add_samples.pop(0)
                    for _ in range(
                        len(upsample_block.resnets)
                        + (upsample_block.upsamplers != None)
                    )
                ]

            sample = upsample_block(
                hidden_states=sample,
                temb=emb,
                res_hidden_states_tuple=res_samples,
                encoder_hidden_states=encoder_hidden_states,
                cross_attention_kwargs=cross_attention_kwargs,
                upsample_size=upsample_size,
                attention_mask=attention_mask,
                encoder_attention_mask=encoder_attention_mask,
                **additional_residuals,
            )
        else:
            additional_residuals = {}
            if is_brushnet and len(up_block_add_samples) > 0:
                additional_residuals["up_block_add_samples"] = [
                    up_block_add_samples.pop(0)
                    for _ in range(
                        len(upsample_block.resnets)
                        + (upsample_block.upsamplers != None)
                    )
                ]

            sample = upsample_block(
                hidden_states=sample,
                temb=emb,
                res_hidden_states_tuple=res_samples,
                upsample_size=upsample_size,
                scale=lora_scale,
                **additional_residuals,
            )

    # 6. post-process
    if self.conv_norm_out:
        sample = self.conv_norm_out(sample)
        sample = self.conv_act(sample)
    sample = self.conv_out(sample)

    if USE_PEFT_BACKEND:
        # remove `lora_scale` from each PEFT layer
        unscale_lora_layers(self, lora_scale)

    if not return_dict:
        return (sample,)

    return UNet2DConditionOutput(sample=sample)