File size: 14,776 Bytes
7ae68fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
# See more details in LICENSE.

from inspect import isfunction
import math
import torch
import torch.nn.functional as F
from torch import nn, einsum
from einops import rearrange, repeat

from ldm.modules.diffusionmodules.util import checkpoint


def exists(val):
    return val is not None


def uniq(arr):
    return{el: True for el in arr}.keys()


def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d


def max_neg_value(t):
    return -torch.finfo(t.dtype).max


def init_(tensor):
    dim = tensor.shape[-1]
    std = 1 / math.sqrt(dim)
    tensor.uniform_(-std, std)
    return tensor


# feedforward
class GEGLU(nn.Module):
    def __init__(self, dim_in, dim_out):
        super().__init__()
        self.proj = nn.Linear(dim_in, dim_out * 2)

    def forward(self, x):
        x, gate = self.proj(x).chunk(2, dim=-1)
        return x * F.gelu(gate)


class FeedForward(nn.Module):
    def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.):
        super().__init__()
        inner_dim = int(dim * mult)
        dim_out = default(dim_out, dim)
        project_in = nn.Sequential(
            nn.Linear(dim, inner_dim),
            nn.GELU()
        ) if not glu else GEGLU(dim, inner_dim)

        self.net = nn.Sequential(
            project_in,
            nn.Dropout(dropout),
            nn.Linear(inner_dim, dim_out)
        )

    def forward(self, x):
        return self.net(x)


def zero_module(module):
    """
    Zero out the parameters of a module and return it.
    """
    for p in module.parameters():
        p.detach().zero_()
    return module


def Normalize(in_channels, default_eps):
    if default_eps:
        return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, affine=True)
    else:
        return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)


class LinearAttention(nn.Module):
    def __init__(self, dim, heads=4, dim_head=32):
        super().__init__()
        self.heads = heads
        hidden_dim = dim_head * heads
        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias = False)
        self.to_out = nn.Conv2d(hidden_dim, dim, 1)

    def forward(self, x):
        b, c, h, w = x.shape
        qkv = self.to_qkv(x)
        q, k, v = rearrange(qkv, 'b (qkv heads c) h w -> qkv b heads c (h w)', heads = self.heads, qkv=3)
        k = torch.softmax(k.float(), dim=-1).type(k.dtype)
        # k = k.softmax(dim=-1) 
        context = torch.einsum('bhdn,bhen->bhde', k, v)
        out = torch.einsum('bhde,bhdn->bhen', context, q)
        out = rearrange(out, 'b heads c (h w) -> b (heads c) h w', heads=self.heads, h=h, w=w)
        return self.to_out(out)


class SpatialSelfAttention(nn.Module):
    def __init__(self, in_channels):
        super().__init__()
        self.in_channels = in_channels

        self.norm = Normalize(in_channels)
        self.q = torch.nn.Conv2d(in_channels,
                                 in_channels,
                                 kernel_size=1,
                                 stride=1,
                                 padding=0)
        self.k = torch.nn.Conv2d(in_channels,
                                 in_channels,
                                 kernel_size=1,
                                 stride=1,
                                 padding=0)
        self.v = torch.nn.Conv2d(in_channels,
                                 in_channels,
                                 kernel_size=1,
                                 stride=1,
                                 padding=0)
        self.proj_out = torch.nn.Conv2d(in_channels,
                                        in_channels,
                                        kernel_size=1,
                                        stride=1,
                                        padding=0)

    def forward(self, x):
        h_ = x
        h_ = self.norm(h_)
        q = self.q(h_)
        k = self.k(h_)
        v = self.v(h_)

        # compute attention
        b,c,h,w = q.shape
        q = rearrange(q, 'b c h w -> b (h w) c')
        k = rearrange(k, 'b c h w -> b c (h w)')
        w_ = torch.einsum('bij,bjk->bik', q, k)

        w_ = w_ * (int(c)**(-0.5))
        w_ = torch.softmax(w_.float(), dim=2).type(w_.dtype)
        # w_ = torch.nn.functional.softmax(w_, dim=2)

        # attend to values
        v = rearrange(v, 'b c h w -> b c (h w)')
        w_ = rearrange(w_, 'b i j -> b j i')
        h_ = torch.einsum('bij,bjk->bik', v, w_)
        h_ = rearrange(h_, 'b c (h w) -> b c h w', h=h)
        h_ = self.proj_out(h_)

        return x+h_


class CrossAttention(nn.Module):
    def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.):
        super().__init__()
        inner_dim = dim_head * heads
        context_dim = default(context_dim, query_dim)

        self.scale = dim_head ** -0.5
        self.heads = heads

        self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
        self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
        self.to_v = nn.Linear(context_dim, inner_dim, bias=False)

        self.to_out = nn.Sequential(
            nn.Linear(inner_dim, query_dim),
            nn.Dropout(dropout)
        )

        self.prompt_to_prompt = False

    def forward(self, x, context=None, mask=None):
        is_self_attn = context is None

        h = self.heads

        q = self.to_q(x)
        context = default(context, x)
        k = self.to_k(context)
        v = self.to_v(context)

        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))

        sim = einsum('b i d, b j d -> b i j', q, k) * self.scale

        if self.prompt_to_prompt and is_self_attn:
            # Unlike the original Prompt-to-Prompt which uses cross-attention layers, we copy attention maps for self-attention layers.
            # There must be 4 elements in the batch: {conditional, unconditional} x {prompt 1, prompt 2}
            assert x.size(0) == 4
            sims = sim.chunk(4)
            sim = torch.cat((sims[0], sims[0], sims[2], sims[2]))

        if exists(mask):
            mask = rearrange(mask, 'b ... -> b (...)')
            max_neg_value = -torch.finfo(sim.dtype).max
            mask = repeat(mask, 'b j -> (b h) () j', h=h)
            sim.masked_fill_(~mask, max_neg_value)

        # attention, what we cannot get enough of
        # attn = sim.softmax(dim=-1)
        attn = torch.softmax(sim.float(), dim=-1).type(sim.dtype)

        out = einsum('b i j, b j d -> b i d', attn, v)
        out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
        return self.to_out(out)


# class BasicTransformerBlock(nn.Module):
#     def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True):
#         super().__init__()
#         self.attn1 = CrossAttention(query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout)  # is a self-attention
#         self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
#         self.attn2 = CrossAttention(query_dim=dim, context_dim=context_dim,
#                                     heads=n_heads, dim_head=d_head, dropout=dropout)  # is self-attn if context is none
#         self.norm1 = nn.LayerNorm(dim)
#         self.norm2 = nn.LayerNorm(dim)
#         self.norm3 = nn.LayerNorm(dim)
#         self.checkpoint = checkpoint

#     def forward(self, x, context=None):
#         # return checkpoint(self._forward, (x, context), self.checkpoint)
#         return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)

#     def _forward(self, x, context=None):
#         x = x.type(self.norm1.weight.dtype)
#         if context is not None:
#             context = context.type(self.norm1.weight.dtype)
#         x = self.attn1(self.norm1(x)) + x
#         x = self.attn2(self.norm2(x), context=context) + x
#         x = self.ff(self.norm3(x)) + x
#         return x


class BasicTransformerBlock(nn.Module):
    ATTENTION_MODES = {
        "softmax": CrossAttention,  # vanilla attention
    }
    def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True,
                 disable_self_attn=False):
        super().__init__()
        attn_mode = "softmax"
        assert attn_mode in self.ATTENTION_MODES
        attn_cls = self.ATTENTION_MODES[attn_mode]
        self.disable_self_attn = disable_self_attn
        self.attn1 = attn_cls(query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout,
                              context_dim=context_dim if self.disable_self_attn else None)  # is a self-attention if not self.disable_self_attn
        self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
        self.attn2 = attn_cls(query_dim=dim, context_dim=context_dim,
                              heads=n_heads, dim_head=d_head, dropout=dropout)  # is self-attn if context is none
        self.norm1 = nn.LayerNorm(dim)
        self.norm2 = nn.LayerNorm(dim)
        self.norm3 = nn.LayerNorm(dim)
        self.checkpoint = checkpoint

    def forward(self, x, context=None):
        return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)

    def _forward(self, x, context=None):
        x = x.type(self.norm1.weight.dtype)
        if context is not None:
            context = context.type(self.norm1.weight.dtype)
        x = self.attn1(self.norm1(x)) + x
        x = self.attn2(self.norm2(x), context=context) + x
        x = self.ff(self.norm3(x)) + x
        return x
        # x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x
        # x = self.attn2(self.norm2(x), context=context) + x
        # x = self.ff(self.norm3(x)) + x
        # return x


# class SpatialTransformer(nn.Module):
#     """
#     Transformer block for image-like data.
#     First, project the input (aka embedding)
#     and reshape to b, t, d.
#     Then apply standard transformer action.
#     Finally, reshape to image
#     """
#     def __init__(self, in_channels, n_heads, d_head, default_eps, force_type_convert, 
#                  depth=1, dropout=0., context_dim=None):
#         super().__init__()
#         self.in_channels = in_channels
#         inner_dim = n_heads * d_head
#         self.force_type_convert = force_type_convert
#         self.norm = Normalize(in_channels, default_eps)

#         self.proj_in = nn.Conv2d(in_channels,
#                                  inner_dim,
#                                  kernel_size=1,
#                                  stride=1,
#                                  padding=0)

#         self.transformer_blocks = nn.ModuleList(
#             [BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim)
#                 for d in range(depth)]
#         )

#         self.proj_out = zero_module(nn.Conv2d(inner_dim,
#                                               in_channels,
#                                               kernel_size=1,
#                                               stride=1,
#                                               padding=0))

#     def forward(self, x, context=None):
#         # note: if no context is given, cross-attention defaults to self-attention
#         b, c, h, w = x.shape
#         x_in = x
#         if self.force_type_convert:
#             x = self.norm.float()(x.float())
#             x = x.half()
#         else:
#             x = self.norm(x)
#         x = self.proj_in(x)
#         x = rearrange(x, 'b c h w -> b (h w) c')
#         for block in self.transformer_blocks:
#             x = block(x, context=context)
#         x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w)
#         x = self.proj_out(x)
#         return x + x_in

class SpatialTransformer(nn.Module):
    """
    Transformer block for image-like data.
    First, project the input (aka embedding)
    and reshape to b, t, d.
    Then apply standard transformer action.
    Finally, reshape to image
    NEW: use_linear for more efficiency instead of the 1x1 convs
    """
    def __init__(self, in_channels, n_heads, d_head, default_eps, force_type_convert,
                 depth=1, dropout=0., context_dim=None,
                 disable_self_attn=False, use_linear=False,
                 use_checkpoint=True):
        super().__init__()
        if exists(context_dim) and not isinstance(context_dim, list):
            context_dim = [context_dim]
        self.in_channels = in_channels
        inner_dim = n_heads * d_head
        self.force_type_convert = force_type_convert
        self.norm = Normalize(in_channels, default_eps)
        if not use_linear:
            self.proj_in = nn.Conv2d(in_channels,
                                     inner_dim,
                                     kernel_size=1,
                                     stride=1,
                                     padding=0)
        else:
            self.proj_in = nn.Linear(in_channels, inner_dim)

        self.transformer_blocks = nn.ModuleList(
            [BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim[d],
                                   disable_self_attn=disable_self_attn, checkpoint=use_checkpoint)
                for d in range(depth)]
        )
        if not use_linear:
            self.proj_out = zero_module(nn.Conv2d(inner_dim,
                                                  in_channels,
                                                  kernel_size=1,
                                                  stride=1,
                                                  padding=0))
        else:
            self.proj_out = zero_module(nn.Linear(in_channels, inner_dim))
        self.use_linear = use_linear

    def forward(self, x, context=None):
        # note: if no context is given, cross-attention defaults to self-attention
        if not isinstance(context, list):
            context = [context]
        b, c, h, w = x.shape
        x_in = x
        if self.force_type_convert:
            x = self.norm.float()(x.float())
            x = x.half()
        else:
            x = self.norm(x)
        if not self.use_linear:
            x = self.proj_in(x)
        x = rearrange(x, 'b c h w -> b (h w) c').contiguous()
        if self.use_linear:
            x = self.proj_in(x)
        for i, block in enumerate(self.transformer_blocks):
            x = block(x, context=context[i])
        if self.use_linear:
            x = self.proj_out(x)
        x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w).contiguous()
        if not self.use_linear:
            x = self.proj_out(x)
        return x + x_in