Spaces:
Running
on
Zero
Running
on
Zero
File size: 18,633 Bytes
2ac1c2d |
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 |
# 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 Callable, List, Optional, Tuple, Union
import os
import torch
import torch.nn.functional as F
from diffusers.models.attention_processor import Attention
from diffusers.utils import logging
from diffusers.utils.import_utils import is_torch_npu_available, is_xformers_available
from diffusers.utils.torch_utils import is_torch_version, maybe_allow_in_graph
from einops import rearrange
from torch import nn
# add sageattention support
scaled_dot_product_attention = F.scaled_dot_product_attention
if os.environ.get("USE_SAGEATTN", "0") == "1":
try:
from sageattention import sageattn
except ImportError:
raise ImportError(
'Please install the package "sageattention" to use this USE_SAGEATTN.'
)
scaled_dot_product_attention = sageattn
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
class AttnProcessor2_0:
r"""
Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).
"""
def __init__(self):
if not hasattr(F, "scaled_dot_product_attention"):
raise ImportError(
"AttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0."
)
def __call__(
self,
attn: Attention,
hidden_states: torch.Tensor,
encoder_hidden_states: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
temb: Optional[torch.Tensor] = None,
*args,
**kwargs,
) -> torch.Tensor:
if len(args) > 0 or kwargs.get("scale", None) is not None:
deprecation_message = "The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`."
deprecate("scale", "1.0.0", deprecation_message)
residual = hidden_states
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
input_ndim = hidden_states.ndim
if input_ndim == 4:
batch_size, channel, height, width = hidden_states.shape
hidden_states = hidden_states.view(
batch_size, channel, height * width
).transpose(1, 2)
batch_size, sequence_length, _ = (
hidden_states.shape
if encoder_hidden_states is None
else encoder_hidden_states.shape
)
if attention_mask is not None:
attention_mask = attn.prepare_attention_mask(
attention_mask, sequence_length, batch_size
)
# scaled_dot_product_attention expects attention_mask shape to be
# (batch, heads, source_length, target_length)
attention_mask = attention_mask.view(
batch_size, attn.heads, -1, attention_mask.shape[-1]
)
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(
1, 2
)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(
encoder_hidden_states
)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
inner_dim = key.shape[-1]
head_dim = inner_dim // attn.heads
query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
if attn.norm_q is not None:
query = attn.norm_q(query)
if attn.norm_k is not None:
key = attn.norm_k(key)
# the output of sdp = (batch, num_heads, seq_len, head_dim)
# TODO: add support for attn.scale when we move to Torch 2.1
hidden_states = scaled_dot_product_attention(
query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
)
hidden_states = hidden_states.transpose(1, 2).reshape(
batch_size, -1, attn.heads * head_dim
)
hidden_states = hidden_states.to(query.dtype)
# linear proj
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
if input_ndim == 4:
hidden_states = hidden_states.transpose(-1, -2).reshape(
batch_size, channel, height, width
)
if attn.residual_connection:
hidden_states = hidden_states + residual
hidden_states = hidden_states / attn.rescale_output_factor
return hidden_states
class FusedAttnProcessor2_0:
r"""
Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0). It uses
fused projection layers. For self-attention modules, all projection matrices (i.e., query, key, value) are fused.
For cross-attention modules, key and value projection matrices are fused.
<Tip warning={true}>
This API is currently 🧪 experimental in nature and can change in future.
</Tip>
"""
def __init__(self):
if not hasattr(F, "scaled_dot_product_attention"):
raise ImportError(
"FusedAttnProcessor2_0 requires at least PyTorch 2.0, to use it. Please upgrade PyTorch to > 2.0."
)
def __call__(
self,
attn: Attention,
hidden_states: torch.Tensor,
encoder_hidden_states: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
temb: Optional[torch.Tensor] = None,
*args,
**kwargs,
) -> torch.Tensor:
if len(args) > 0 or kwargs.get("scale", None) is not None:
deprecation_message = "The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`."
deprecate("scale", "1.0.0", deprecation_message)
residual = hidden_states
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
input_ndim = hidden_states.ndim
if input_ndim == 4:
batch_size, channel, height, width = hidden_states.shape
hidden_states = hidden_states.view(
batch_size, channel, height * width
).transpose(1, 2)
batch_size, sequence_length, _ = (
hidden_states.shape
if encoder_hidden_states is None
else encoder_hidden_states.shape
)
if attention_mask is not None:
attention_mask = attn.prepare_attention_mask(
attention_mask, sequence_length, batch_size
)
# scaled_dot_product_attention expects attention_mask shape to be
# (batch, heads, source_length, target_length)
attention_mask = attention_mask.view(
batch_size, attn.heads, -1, attention_mask.shape[-1]
)
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(
1, 2
)
if encoder_hidden_states is None:
qkv = attn.to_qkv(hidden_states)
split_size = qkv.shape[-1] // 3
query, key, value = torch.split(qkv, split_size, dim=-1)
else:
if attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(
encoder_hidden_states
)
query = attn.to_q(hidden_states)
kv = attn.to_kv(encoder_hidden_states)
split_size = kv.shape[-1] // 2
key, value = torch.split(kv, split_size, dim=-1)
inner_dim = key.shape[-1]
head_dim = inner_dim // attn.heads
query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
if attn.norm_q is not None:
query = attn.norm_q(query)
if attn.norm_k is not None:
key = attn.norm_k(key)
# the output of sdp = (batch, num_heads, seq_len, head_dim)
# TODO: add support for attn.scale when we move to Torch 2.1
hidden_states = F.scaled_dot_product_attention(
query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
)
hidden_states = hidden_states.transpose(1, 2).reshape(
batch_size, -1, attn.heads * head_dim
)
hidden_states = hidden_states.to(query.dtype)
# linear proj
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
if input_ndim == 4:
hidden_states = hidden_states.transpose(-1, -2).reshape(
batch_size, channel, height, width
)
if attn.residual_connection:
hidden_states = hidden_states + residual
hidden_states = hidden_states / attn.rescale_output_factor
return hidden_states
class FluxAttnProcessor2_0:
"""Attention processor used typically in processing the SD3-like self-attention projections."""
def __init__(self):
if not hasattr(F, "scaled_dot_product_attention"):
raise ImportError(
"FluxAttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0."
)
def __call__(
self,
attn: Attention,
hidden_states: torch.FloatTensor,
encoder_hidden_states: torch.FloatTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
image_rotary_emb: Optional[torch.Tensor] = None,
) -> torch.FloatTensor:
batch_size, _, _ = (
hidden_states.shape
if encoder_hidden_states is None
else encoder_hidden_states.shape
)
# `sample` projections.
query = attn.to_q(hidden_states)
key = attn.to_k(hidden_states)
value = attn.to_v(hidden_states)
inner_dim = key.shape[-1]
head_dim = inner_dim // attn.heads
query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
if attn.norm_q is not None:
query = attn.norm_q(query)
if attn.norm_k is not None:
key = attn.norm_k(key)
# the attention in FluxSingleTransformerBlock does not use `encoder_hidden_states`
if encoder_hidden_states is not None:
# `context` projections.
encoder_hidden_states_query_proj = attn.add_q_proj(encoder_hidden_states)
encoder_hidden_states_key_proj = attn.add_k_proj(encoder_hidden_states)
encoder_hidden_states_value_proj = attn.add_v_proj(encoder_hidden_states)
encoder_hidden_states_query_proj = encoder_hidden_states_query_proj.view(
batch_size, -1, attn.heads, head_dim
).transpose(1, 2)
encoder_hidden_states_key_proj = encoder_hidden_states_key_proj.view(
batch_size, -1, attn.heads, head_dim
).transpose(1, 2)
encoder_hidden_states_value_proj = encoder_hidden_states_value_proj.view(
batch_size, -1, attn.heads, head_dim
).transpose(1, 2)
if attn.norm_added_q is not None:
encoder_hidden_states_query_proj = attn.norm_added_q(
encoder_hidden_states_query_proj
)
if attn.norm_added_k is not None:
encoder_hidden_states_key_proj = attn.norm_added_k(
encoder_hidden_states_key_proj
)
# attention
query = torch.cat([encoder_hidden_states_query_proj, query], dim=2)
key = torch.cat([encoder_hidden_states_key_proj, key], dim=2)
value = torch.cat([encoder_hidden_states_value_proj, value], dim=2)
if image_rotary_emb is not None:
from .embeddings import apply_rotary_emb
query = apply_rotary_emb(query, image_rotary_emb)
key = apply_rotary_emb(key, image_rotary_emb)
hidden_states = scaled_dot_product_attention(
query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
)
hidden_states = hidden_states.transpose(1, 2).reshape(
batch_size, -1, attn.heads * head_dim
)
hidden_states = hidden_states.to(query.dtype)
if encoder_hidden_states is not None:
encoder_hidden_states, hidden_states = (
hidden_states[:, : encoder_hidden_states.shape[1]],
hidden_states[:, encoder_hidden_states.shape[1] :],
)
# linear proj
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
return hidden_states, encoder_hidden_states
else:
return hidden_states
class FusedFluxAttnProcessor2_0:
"""Attention processor used typically in processing the SD3-like self-attention projections."""
def __init__(self):
if not hasattr(F, "scaled_dot_product_attention"):
raise ImportError(
"FusedFluxAttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0."
)
def __call__(
self,
attn: Attention,
hidden_states: torch.FloatTensor,
encoder_hidden_states: torch.FloatTensor = None,
attention_mask: Optional[torch.FloatTensor] = None,
image_rotary_emb: Optional[torch.Tensor] = None,
) -> torch.FloatTensor:
batch_size, _, _ = (
hidden_states.shape
if encoder_hidden_states is None
else encoder_hidden_states.shape
)
# `sample` projections.
qkv = attn.to_qkv(hidden_states)
split_size = qkv.shape[-1] // 3
query, key, value = torch.split(qkv, split_size, dim=-1)
inner_dim = key.shape[-1]
head_dim = inner_dim // attn.heads
query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
if attn.norm_q is not None:
query = attn.norm_q(query)
if attn.norm_k is not None:
key = attn.norm_k(key)
# the attention in FluxSingleTransformerBlock does not use `encoder_hidden_states`
# `context` projections.
if encoder_hidden_states is not None:
encoder_qkv = attn.to_added_qkv(encoder_hidden_states)
split_size = encoder_qkv.shape[-1] // 3
(
encoder_hidden_states_query_proj,
encoder_hidden_states_key_proj,
encoder_hidden_states_value_proj,
) = torch.split(encoder_qkv, split_size, dim=-1)
encoder_hidden_states_query_proj = encoder_hidden_states_query_proj.view(
batch_size, -1, attn.heads, head_dim
).transpose(1, 2)
encoder_hidden_states_key_proj = encoder_hidden_states_key_proj.view(
batch_size, -1, attn.heads, head_dim
).transpose(1, 2)
encoder_hidden_states_value_proj = encoder_hidden_states_value_proj.view(
batch_size, -1, attn.heads, head_dim
).transpose(1, 2)
if attn.norm_added_q is not None:
encoder_hidden_states_query_proj = attn.norm_added_q(
encoder_hidden_states_query_proj
)
if attn.norm_added_k is not None:
encoder_hidden_states_key_proj = attn.norm_added_k(
encoder_hidden_states_key_proj
)
# attention
query = torch.cat([encoder_hidden_states_query_proj, query], dim=2)
key = torch.cat([encoder_hidden_states_key_proj, key], dim=2)
value = torch.cat([encoder_hidden_states_value_proj, value], dim=2)
if image_rotary_emb is not None:
from .embeddings import apply_rotary_emb
query = apply_rotary_emb(query, image_rotary_emb)
key = apply_rotary_emb(key, image_rotary_emb)
hidden_states = scaled_dot_product_attention(
query, key, value, dropout_p=0.0, is_causal=False
)
hidden_states = hidden_states.transpose(1, 2).reshape(
batch_size, -1, attn.heads * head_dim
)
hidden_states = hidden_states.to(query.dtype)
if encoder_hidden_states is not None:
encoder_hidden_states, hidden_states = (
hidden_states[:, : encoder_hidden_states.shape[1]],
hidden_states[:, encoder_hidden_states.shape[1] :],
)
# linear proj
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
encoder_hidden_states = attn.to_add_out(encoder_hidden_states)
return hidden_states, encoder_hidden_states
else:
return hidden_states
|