File size: 33,591 Bytes
f1069cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
# coding=utf-8
# Copyright 2023 The HuggingFace Inc. team.
#
# 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.
""" Conversion script for the Versatile Stable Diffusion checkpoints. """

import argparse
from argparse import Namespace

import torch
from transformers import (
    CLIPImageProcessor,
    CLIPTextModelWithProjection,
    CLIPTokenizer,
    CLIPVisionModelWithProjection,
)

from diffusers import (
    AutoencoderKL,
    DDIMScheduler,
    DPMSolverMultistepScheduler,
    EulerAncestralDiscreteScheduler,
    EulerDiscreteScheduler,
    LMSDiscreteScheduler,
    PNDMScheduler,
    UNet2DConditionModel,
    VersatileDiffusionPipeline,
)
from diffusers.pipelines.versatile_diffusion.modeling_text_unet import UNetFlatConditionModel


SCHEDULER_CONFIG = Namespace(
    **{
        "beta_linear_start": 0.00085,
        "beta_linear_end": 0.012,
        "timesteps": 1000,
        "scale_factor": 0.18215,
    }
)

IMAGE_UNET_CONFIG = Namespace(
    **{
        "input_channels": 4,
        "model_channels": 320,
        "output_channels": 4,
        "num_noattn_blocks": [2, 2, 2, 2],
        "channel_mult": [1, 2, 4, 4],
        "with_attn": [True, True, True, False],
        "num_heads": 8,
        "context_dim": 768,
        "use_checkpoint": True,
    }
)

TEXT_UNET_CONFIG = Namespace(
    **{
        "input_channels": 768,
        "model_channels": 320,
        "output_channels": 768,
        "num_noattn_blocks": [2, 2, 2, 2],
        "channel_mult": [1, 2, 4, 4],
        "second_dim": [4, 4, 4, 4],
        "with_attn": [True, True, True, False],
        "num_heads": 8,
        "context_dim": 768,
        "use_checkpoint": True,
    }
)

AUTOENCODER_CONFIG = Namespace(
    **{
        "double_z": True,
        "z_channels": 4,
        "resolution": 256,
        "in_channels": 3,
        "out_ch": 3,
        "ch": 128,
        "ch_mult": [1, 2, 4, 4],
        "num_res_blocks": 2,
        "attn_resolutions": [],
        "dropout": 0.0,
    }
)


def shave_segments(path, n_shave_prefix_segments=1):
    """
    Removes segments. Positive values shave the first segments, negative shave the last segments.
    """
    if n_shave_prefix_segments >= 0:
        return ".".join(path.split(".")[n_shave_prefix_segments:])
    else:
        return ".".join(path.split(".")[:n_shave_prefix_segments])


def renew_resnet_paths(old_list, n_shave_prefix_segments=0):
    """
    Updates paths inside resnets to the new naming scheme (local renaming)
    """
    mapping = []
    for old_item in old_list:
        new_item = old_item.replace("in_layers.0", "norm1")
        new_item = new_item.replace("in_layers.2", "conv1")

        new_item = new_item.replace("out_layers.0", "norm2")
        new_item = new_item.replace("out_layers.3", "conv2")

        new_item = new_item.replace("emb_layers.1", "time_emb_proj")
        new_item = new_item.replace("skip_connection", "conv_shortcut")

        new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments)

        mapping.append({"old": old_item, "new": new_item})

    return mapping


def renew_vae_resnet_paths(old_list, n_shave_prefix_segments=0):
    """
    Updates paths inside resnets to the new naming scheme (local renaming)
    """
    mapping = []
    for old_item in old_list:
        new_item = old_item

        new_item = new_item.replace("nin_shortcut", "conv_shortcut")
        new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments)

        mapping.append({"old": old_item, "new": new_item})

    return mapping


def renew_attention_paths(old_list, n_shave_prefix_segments=0):
    """
    Updates paths inside attentions to the new naming scheme (local renaming)
    """
    mapping = []
    for old_item in old_list:
        new_item = old_item

        #         new_item = new_item.replace('norm.weight', 'group_norm.weight')
        #         new_item = new_item.replace('norm.bias', 'group_norm.bias')

        #         new_item = new_item.replace('proj_out.weight', 'proj_attn.weight')
        #         new_item = new_item.replace('proj_out.bias', 'proj_attn.bias')

        #         new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments)

        mapping.append({"old": old_item, "new": new_item})

    return mapping


def renew_vae_attention_paths(old_list, n_shave_prefix_segments=0):
    """
    Updates paths inside attentions to the new naming scheme (local renaming)
    """
    mapping = []
    for old_item in old_list:
        new_item = old_item

        new_item = new_item.replace("norm.weight", "group_norm.weight")
        new_item = new_item.replace("norm.bias", "group_norm.bias")

        new_item = new_item.replace("q.weight", "query.weight")
        new_item = new_item.replace("q.bias", "query.bias")

        new_item = new_item.replace("k.weight", "key.weight")
        new_item = new_item.replace("k.bias", "key.bias")

        new_item = new_item.replace("v.weight", "value.weight")
        new_item = new_item.replace("v.bias", "value.bias")

        new_item = new_item.replace("proj_out.weight", "proj_attn.weight")
        new_item = new_item.replace("proj_out.bias", "proj_attn.bias")

        new_item = shave_segments(new_item, n_shave_prefix_segments=n_shave_prefix_segments)

        mapping.append({"old": old_item, "new": new_item})

    return mapping


def assign_to_checkpoint(
    paths, checkpoint, old_checkpoint, attention_paths_to_split=None, additional_replacements=None, config=None
):
    """
    This does the final conversion step: take locally converted weights and apply a global renaming
    to them. It splits attention layers, and takes into account additional replacements
    that may arise.

    Assigns the weights to the new checkpoint.
    """
    assert isinstance(paths, list), "Paths should be a list of dicts containing 'old' and 'new' keys."

    # Splits the attention layers into three variables.
    if attention_paths_to_split is not None:
        for path, path_map in attention_paths_to_split.items():
            old_tensor = old_checkpoint[path]
            channels = old_tensor.shape[0] // 3

            target_shape = (-1, channels) if len(old_tensor.shape) == 3 else (-1)

            num_heads = old_tensor.shape[0] // config["num_head_channels"] // 3

            old_tensor = old_tensor.reshape((num_heads, 3 * channels // num_heads) + old_tensor.shape[1:])
            query, key, value = old_tensor.split(channels // num_heads, dim=1)

            checkpoint[path_map["query"]] = query.reshape(target_shape)
            checkpoint[path_map["key"]] = key.reshape(target_shape)
            checkpoint[path_map["value"]] = value.reshape(target_shape)

    for path in paths:
        new_path = path["new"]

        # These have already been assigned
        if attention_paths_to_split is not None and new_path in attention_paths_to_split:
            continue

        # Global renaming happens here
        new_path = new_path.replace("middle_block.0", "mid_block.resnets.0")
        new_path = new_path.replace("middle_block.1", "mid_block.attentions.0")
        new_path = new_path.replace("middle_block.2", "mid_block.resnets.1")

        if additional_replacements is not None:
            for replacement in additional_replacements:
                new_path = new_path.replace(replacement["old"], replacement["new"])

        # proj_attn.weight has to be converted from conv 1D to linear
        if "proj_attn.weight" in new_path:
            checkpoint[new_path] = old_checkpoint[path["old"]][:, :, 0]
        elif path["old"] in old_checkpoint:
            checkpoint[new_path] = old_checkpoint[path["old"]]


def conv_attn_to_linear(checkpoint):
    keys = list(checkpoint.keys())
    attn_keys = ["query.weight", "key.weight", "value.weight"]
    for key in keys:
        if ".".join(key.split(".")[-2:]) in attn_keys:
            if checkpoint[key].ndim > 2:
                checkpoint[key] = checkpoint[key][:, :, 0, 0]
        elif "proj_attn.weight" in key:
            if checkpoint[key].ndim > 2:
                checkpoint[key] = checkpoint[key][:, :, 0]


def create_image_unet_diffusers_config(unet_params):
    """
    Creates a config for the diffusers based on the config of the VD model.
    """

    block_out_channels = [unet_params.model_channels * mult for mult in unet_params.channel_mult]

    down_block_types = []
    resolution = 1
    for i in range(len(block_out_channels)):
        block_type = "CrossAttnDownBlock2D" if unet_params.with_attn[i] else "DownBlock2D"
        down_block_types.append(block_type)
        if i != len(block_out_channels) - 1:
            resolution *= 2

    up_block_types = []
    for i in range(len(block_out_channels)):
        block_type = "CrossAttnUpBlock2D" if unet_params.with_attn[-i - 1] else "UpBlock2D"
        up_block_types.append(block_type)
        resolution //= 2

    if not all(n == unet_params.num_noattn_blocks[0] for n in unet_params.num_noattn_blocks):
        raise ValueError("Not all num_res_blocks are equal, which is not supported in this script.")

    config = {
        "sample_size": None,
        "in_channels": unet_params.input_channels,
        "out_channels": unet_params.output_channels,
        "down_block_types": tuple(down_block_types),
        "up_block_types": tuple(up_block_types),
        "block_out_channels": tuple(block_out_channels),
        "layers_per_block": unet_params.num_noattn_blocks[0],
        "cross_attention_dim": unet_params.context_dim,
        "attention_head_dim": unet_params.num_heads,
    }

    return config


def create_text_unet_diffusers_config(unet_params):
    """
    Creates a config for the diffusers based on the config of the VD model.
    """

    block_out_channels = [unet_params.model_channels * mult for mult in unet_params.channel_mult]

    down_block_types = []
    resolution = 1
    for i in range(len(block_out_channels)):
        block_type = "CrossAttnDownBlockFlat" if unet_params.with_attn[i] else "DownBlockFlat"
        down_block_types.append(block_type)
        if i != len(block_out_channels) - 1:
            resolution *= 2

    up_block_types = []
    for i in range(len(block_out_channels)):
        block_type = "CrossAttnUpBlockFlat" if unet_params.with_attn[-i - 1] else "UpBlockFlat"
        up_block_types.append(block_type)
        resolution //= 2

    if not all(n == unet_params.num_noattn_blocks[0] for n in unet_params.num_noattn_blocks):
        raise ValueError("Not all num_res_blocks are equal, which is not supported in this script.")

    config = {
        "sample_size": None,
        "in_channels": (unet_params.input_channels, 1, 1),
        "out_channels": (unet_params.output_channels, 1, 1),
        "down_block_types": tuple(down_block_types),
        "up_block_types": tuple(up_block_types),
        "block_out_channels": tuple(block_out_channels),
        "layers_per_block": unet_params.num_noattn_blocks[0],
        "cross_attention_dim": unet_params.context_dim,
        "attention_head_dim": unet_params.num_heads,
    }

    return config


def create_vae_diffusers_config(vae_params):
    """
    Creates a config for the diffusers based on the config of the VD model.
    """

    block_out_channels = [vae_params.ch * mult for mult in vae_params.ch_mult]
    down_block_types = ["DownEncoderBlock2D"] * len(block_out_channels)
    up_block_types = ["UpDecoderBlock2D"] * len(block_out_channels)

    config = {
        "sample_size": vae_params.resolution,
        "in_channels": vae_params.in_channels,
        "out_channels": vae_params.out_ch,
        "down_block_types": tuple(down_block_types),
        "up_block_types": tuple(up_block_types),
        "block_out_channels": tuple(block_out_channels),
        "latent_channels": vae_params.z_channels,
        "layers_per_block": vae_params.num_res_blocks,
    }
    return config


def create_diffusers_scheduler(original_config):
    schedular = DDIMScheduler(
        num_train_timesteps=original_config.model.params.timesteps,
        beta_start=original_config.model.params.linear_start,
        beta_end=original_config.model.params.linear_end,
        beta_schedule="scaled_linear",
    )
    return schedular


def convert_vd_unet_checkpoint(checkpoint, config, unet_key, extract_ema=False):
    """
    Takes a state dict and a config, and returns a converted checkpoint.
    """

    # extract state_dict for UNet
    unet_state_dict = {}
    keys = list(checkpoint.keys())

    # at least a 100 parameters have to start with `model_ema` in order for the checkpoint to be EMA
    if sum(k.startswith("model_ema") for k in keys) > 100:
        print("Checkpoint has both EMA and non-EMA weights.")
        if extract_ema:
            print(
                "In this conversion only the EMA weights are extracted. If you want to instead extract the non-EMA"
                " weights (useful to continue fine-tuning), please make sure to remove the `--extract_ema` flag."
            )
            for key in keys:
                if key.startswith("model.diffusion_model"):
                    flat_ema_key = "model_ema." + "".join(key.split(".")[1:])
                    unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(flat_ema_key)
        else:
            print(
                "In this conversion only the non-EMA weights are extracted. If you want to instead extract the EMA"
                " weights (usually better for inference), please make sure to add the `--extract_ema` flag."
            )

    for key in keys:
        if key.startswith(unet_key):
            unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(key)

    new_checkpoint = {}

    new_checkpoint["time_embedding.linear_1.weight"] = checkpoint["model.diffusion_model.time_embed.0.weight"]
    new_checkpoint["time_embedding.linear_1.bias"] = checkpoint["model.diffusion_model.time_embed.0.bias"]
    new_checkpoint["time_embedding.linear_2.weight"] = checkpoint["model.diffusion_model.time_embed.2.weight"]
    new_checkpoint["time_embedding.linear_2.bias"] = checkpoint["model.diffusion_model.time_embed.2.bias"]

    new_checkpoint["conv_in.weight"] = unet_state_dict["input_blocks.0.0.weight"]
    new_checkpoint["conv_in.bias"] = unet_state_dict["input_blocks.0.0.bias"]

    new_checkpoint["conv_norm_out.weight"] = unet_state_dict["out.0.weight"]
    new_checkpoint["conv_norm_out.bias"] = unet_state_dict["out.0.bias"]
    new_checkpoint["conv_out.weight"] = unet_state_dict["out.2.weight"]
    new_checkpoint["conv_out.bias"] = unet_state_dict["out.2.bias"]

    # Retrieves the keys for the input blocks only
    num_input_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "input_blocks" in layer})
    input_blocks = {
        layer_id: [key for key in unet_state_dict if f"input_blocks.{layer_id}" in key]
        for layer_id in range(num_input_blocks)
    }

    # Retrieves the keys for the middle blocks only
    num_middle_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "middle_block" in layer})
    middle_blocks = {
        layer_id: [key for key in unet_state_dict if f"middle_block.{layer_id}" in key]
        for layer_id in range(num_middle_blocks)
    }

    # Retrieves the keys for the output blocks only
    num_output_blocks = len({".".join(layer.split(".")[:2]) for layer in unet_state_dict if "output_blocks" in layer})
    output_blocks = {
        layer_id: [key for key in unet_state_dict if f"output_blocks.{layer_id}" in key]
        for layer_id in range(num_output_blocks)
    }

    for i in range(1, num_input_blocks):
        block_id = (i - 1) // (config["layers_per_block"] + 1)
        layer_in_block_id = (i - 1) % (config["layers_per_block"] + 1)

        resnets = [
            key for key in input_blocks[i] if f"input_blocks.{i}.0" in key and f"input_blocks.{i}.0.op" not in key
        ]
        attentions = [key for key in input_blocks[i] if f"input_blocks.{i}.1" in key]

        if f"input_blocks.{i}.0.op.weight" in unet_state_dict:
            new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.conv.weight"] = unet_state_dict.pop(
                f"input_blocks.{i}.0.op.weight"
            )
            new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.conv.bias"] = unet_state_dict.pop(
                f"input_blocks.{i}.0.op.bias"
            )
        elif f"input_blocks.{i}.0.weight" in unet_state_dict:
            # text_unet uses linear layers in place of downsamplers
            shape = unet_state_dict[f"input_blocks.{i}.0.weight"].shape
            if shape[0] != shape[1]:
                continue
            new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.weight"] = unet_state_dict.pop(
                f"input_blocks.{i}.0.weight"
            )
            new_checkpoint[f"down_blocks.{block_id}.downsamplers.0.bias"] = unet_state_dict.pop(
                f"input_blocks.{i}.0.bias"
            )

        paths = renew_resnet_paths(resnets)
        meta_path = {"old": f"input_blocks.{i}.0", "new": f"down_blocks.{block_id}.resnets.{layer_in_block_id}"}
        assign_to_checkpoint(
            paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config
        )

        if len(attentions):
            paths = renew_attention_paths(attentions)
            meta_path = {"old": f"input_blocks.{i}.1", "new": f"down_blocks.{block_id}.attentions.{layer_in_block_id}"}
            assign_to_checkpoint(
                paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config
            )

    resnet_0 = middle_blocks[0]
    attentions = middle_blocks[1]
    resnet_1 = middle_blocks[2]

    resnet_0_paths = renew_resnet_paths(resnet_0)
    assign_to_checkpoint(resnet_0_paths, new_checkpoint, unet_state_dict, config=config)

    resnet_1_paths = renew_resnet_paths(resnet_1)
    assign_to_checkpoint(resnet_1_paths, new_checkpoint, unet_state_dict, config=config)

    attentions_paths = renew_attention_paths(attentions)
    meta_path = {"old": "middle_block.1", "new": "mid_block.attentions.0"}
    assign_to_checkpoint(
        attentions_paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config
    )

    for i in range(num_output_blocks):
        block_id = i // (config["layers_per_block"] + 1)
        layer_in_block_id = i % (config["layers_per_block"] + 1)
        output_block_layers = [shave_segments(name, 2) for name in output_blocks[i]]
        output_block_list = {}

        for layer in output_block_layers:
            layer_id, layer_name = layer.split(".")[0], shave_segments(layer, 1)
            if layer_id in output_block_list:
                output_block_list[layer_id].append(layer_name)
            else:
                output_block_list[layer_id] = [layer_name]

        if len(output_block_list) > 1:
            resnets = [key for key in output_blocks[i] if f"output_blocks.{i}.0" in key]
            attentions = [key for key in output_blocks[i] if f"output_blocks.{i}.1" in key]

            paths = renew_resnet_paths(resnets)

            meta_path = {"old": f"output_blocks.{i}.0", "new": f"up_blocks.{block_id}.resnets.{layer_in_block_id}"}
            assign_to_checkpoint(
                paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config
            )

            if ["conv.weight", "conv.bias"] in output_block_list.values():
                index = list(output_block_list.values()).index(["conv.weight", "conv.bias"])
                new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.conv.weight"] = unet_state_dict[
                    f"output_blocks.{i}.{index}.conv.weight"
                ]
                new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.conv.bias"] = unet_state_dict[
                    f"output_blocks.{i}.{index}.conv.bias"
                ]
                # Clear attentions as they have been attributed above.
                if len(attentions) == 2:
                    attentions = []
            elif f"output_blocks.{i}.1.weight" in unet_state_dict:
                # text_unet uses linear layers in place of upsamplers
                shape = unet_state_dict[f"output_blocks.{i}.1.weight"].shape
                if shape[0] != shape[1]:
                    continue
                new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.weight"] = unet_state_dict.pop(
                    f"output_blocks.{i}.1.weight"
                )
                new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.bias"] = unet_state_dict.pop(
                    f"output_blocks.{i}.1.bias"
                )
                # Clear attentions as they have been attributed above.
                if len(attentions) == 2:
                    attentions = []
            elif f"output_blocks.{i}.2.weight" in unet_state_dict:
                # text_unet uses linear layers in place of upsamplers
                shape = unet_state_dict[f"output_blocks.{i}.2.weight"].shape
                if shape[0] != shape[1]:
                    continue
                new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.weight"] = unet_state_dict.pop(
                    f"output_blocks.{i}.2.weight"
                )
                new_checkpoint[f"up_blocks.{block_id}.upsamplers.0.bias"] = unet_state_dict.pop(
                    f"output_blocks.{i}.2.bias"
                )

            if len(attentions):
                paths = renew_attention_paths(attentions)
                meta_path = {
                    "old": f"output_blocks.{i}.1",
                    "new": f"up_blocks.{block_id}.attentions.{layer_in_block_id}",
                }
                assign_to_checkpoint(
                    paths, new_checkpoint, unet_state_dict, additional_replacements=[meta_path], config=config
                )
        else:
            resnet_0_paths = renew_resnet_paths(output_block_layers, n_shave_prefix_segments=1)
            for path in resnet_0_paths:
                old_path = ".".join(["output_blocks", str(i), path["old"]])
                new_path = ".".join(["up_blocks", str(block_id), "resnets", str(layer_in_block_id), path["new"]])

                new_checkpoint[new_path] = unet_state_dict[old_path]

    return new_checkpoint


def convert_vd_vae_checkpoint(checkpoint, config):
    # extract state dict for VAE
    vae_state_dict = {}
    keys = list(checkpoint.keys())
    for key in keys:
        vae_state_dict[key] = checkpoint.get(key)

    new_checkpoint = {}

    new_checkpoint["encoder.conv_in.weight"] = vae_state_dict["encoder.conv_in.weight"]
    new_checkpoint["encoder.conv_in.bias"] = vae_state_dict["encoder.conv_in.bias"]
    new_checkpoint["encoder.conv_out.weight"] = vae_state_dict["encoder.conv_out.weight"]
    new_checkpoint["encoder.conv_out.bias"] = vae_state_dict["encoder.conv_out.bias"]
    new_checkpoint["encoder.conv_norm_out.weight"] = vae_state_dict["encoder.norm_out.weight"]
    new_checkpoint["encoder.conv_norm_out.bias"] = vae_state_dict["encoder.norm_out.bias"]

    new_checkpoint["decoder.conv_in.weight"] = vae_state_dict["decoder.conv_in.weight"]
    new_checkpoint["decoder.conv_in.bias"] = vae_state_dict["decoder.conv_in.bias"]
    new_checkpoint["decoder.conv_out.weight"] = vae_state_dict["decoder.conv_out.weight"]
    new_checkpoint["decoder.conv_out.bias"] = vae_state_dict["decoder.conv_out.bias"]
    new_checkpoint["decoder.conv_norm_out.weight"] = vae_state_dict["decoder.norm_out.weight"]
    new_checkpoint["decoder.conv_norm_out.bias"] = vae_state_dict["decoder.norm_out.bias"]

    new_checkpoint["quant_conv.weight"] = vae_state_dict["quant_conv.weight"]
    new_checkpoint["quant_conv.bias"] = vae_state_dict["quant_conv.bias"]
    new_checkpoint["post_quant_conv.weight"] = vae_state_dict["post_quant_conv.weight"]
    new_checkpoint["post_quant_conv.bias"] = vae_state_dict["post_quant_conv.bias"]

    # Retrieves the keys for the encoder down blocks only
    num_down_blocks = len({".".join(layer.split(".")[:3]) for layer in vae_state_dict if "encoder.down" in layer})
    down_blocks = {
        layer_id: [key for key in vae_state_dict if f"down.{layer_id}" in key] for layer_id in range(num_down_blocks)
    }

    # Retrieves the keys for the decoder up blocks only
    num_up_blocks = len({".".join(layer.split(".")[:3]) for layer in vae_state_dict if "decoder.up" in layer})
    up_blocks = {
        layer_id: [key for key in vae_state_dict if f"up.{layer_id}" in key] for layer_id in range(num_up_blocks)
    }

    for i in range(num_down_blocks):
        resnets = [key for key in down_blocks[i] if f"down.{i}" in key and f"down.{i}.downsample" not in key]

        if f"encoder.down.{i}.downsample.conv.weight" in vae_state_dict:
            new_checkpoint[f"encoder.down_blocks.{i}.downsamplers.0.conv.weight"] = vae_state_dict.pop(
                f"encoder.down.{i}.downsample.conv.weight"
            )
            new_checkpoint[f"encoder.down_blocks.{i}.downsamplers.0.conv.bias"] = vae_state_dict.pop(
                f"encoder.down.{i}.downsample.conv.bias"
            )

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"down.{i}.block", "new": f"down_blocks.{i}.resnets"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_resnets = [key for key in vae_state_dict if "encoder.mid.block" in key]
    num_mid_res_blocks = 2
    for i in range(1, num_mid_res_blocks + 1):
        resnets = [key for key in mid_resnets if f"encoder.mid.block_{i}" in key]

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"mid.block_{i}", "new": f"mid_block.resnets.{i - 1}"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_attentions = [key for key in vae_state_dict if "encoder.mid.attn" in key]
    paths = renew_vae_attention_paths(mid_attentions)
    meta_path = {"old": "mid.attn_1", "new": "mid_block.attentions.0"}
    assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)
    conv_attn_to_linear(new_checkpoint)

    for i in range(num_up_blocks):
        block_id = num_up_blocks - 1 - i
        resnets = [
            key for key in up_blocks[block_id] if f"up.{block_id}" in key and f"up.{block_id}.upsample" not in key
        ]

        if f"decoder.up.{block_id}.upsample.conv.weight" in vae_state_dict:
            new_checkpoint[f"decoder.up_blocks.{i}.upsamplers.0.conv.weight"] = vae_state_dict[
                f"decoder.up.{block_id}.upsample.conv.weight"
            ]
            new_checkpoint[f"decoder.up_blocks.{i}.upsamplers.0.conv.bias"] = vae_state_dict[
                f"decoder.up.{block_id}.upsample.conv.bias"
            ]

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"up.{block_id}.block", "new": f"up_blocks.{i}.resnets"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_resnets = [key for key in vae_state_dict if "decoder.mid.block" in key]
    num_mid_res_blocks = 2
    for i in range(1, num_mid_res_blocks + 1):
        resnets = [key for key in mid_resnets if f"decoder.mid.block_{i}" in key]

        paths = renew_vae_resnet_paths(resnets)
        meta_path = {"old": f"mid.block_{i}", "new": f"mid_block.resnets.{i - 1}"}
        assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)

    mid_attentions = [key for key in vae_state_dict if "decoder.mid.attn" in key]
    paths = renew_vae_attention_paths(mid_attentions)
    meta_path = {"old": "mid.attn_1", "new": "mid_block.attentions.0"}
    assign_to_checkpoint(paths, new_checkpoint, vae_state_dict, additional_replacements=[meta_path], config=config)
    conv_attn_to_linear(new_checkpoint)
    return new_checkpoint


if __name__ == "__main__":
    parser = argparse.ArgumentParser()

    parser.add_argument(
        "--unet_checkpoint_path", default=None, type=str, required=False, help="Path to the checkpoint to convert."
    )
    parser.add_argument(
        "--vae_checkpoint_path", default=None, type=str, required=False, help="Path to the checkpoint to convert."
    )
    parser.add_argument(
        "--optimus_checkpoint_path", default=None, type=str, required=False, help="Path to the checkpoint to convert."
    )
    parser.add_argument(
        "--scheduler_type",
        default="pndm",
        type=str,
        help="Type of scheduler to use. Should be one of ['pndm', 'lms', 'ddim', 'euler', 'euler-ancestral', 'dpm']",
    )
    parser.add_argument(
        "--extract_ema",
        action="store_true",
        help=(
            "Only relevant for checkpoints that have both EMA and non-EMA weights. Whether to extract the EMA weights"
            " or not. Defaults to `False`. Add `--extract_ema` to extract the EMA weights. EMA weights usually yield"
            " higher quality images for inference. Non-EMA weights are usually better to continue fine-tuning."
        ),
    )
    parser.add_argument("--dump_path", default=None, type=str, required=True, help="Path to the output model.")

    args = parser.parse_args()

    scheduler_config = SCHEDULER_CONFIG

    num_train_timesteps = scheduler_config.timesteps
    beta_start = scheduler_config.beta_linear_start
    beta_end = scheduler_config.beta_linear_end
    if args.scheduler_type == "pndm":
        scheduler = PNDMScheduler(
            beta_end=beta_end,
            beta_schedule="scaled_linear",
            beta_start=beta_start,
            num_train_timesteps=num_train_timesteps,
            skip_prk_steps=True,
            steps_offset=1,
        )
    elif args.scheduler_type == "lms":
        scheduler = LMSDiscreteScheduler(beta_start=beta_start, beta_end=beta_end, beta_schedule="scaled_linear")
    elif args.scheduler_type == "euler":
        scheduler = EulerDiscreteScheduler(beta_start=beta_start, beta_end=beta_end, beta_schedule="scaled_linear")
    elif args.scheduler_type == "euler-ancestral":
        scheduler = EulerAncestralDiscreteScheduler(
            beta_start=beta_start, beta_end=beta_end, beta_schedule="scaled_linear"
        )
    elif args.scheduler_type == "dpm":
        scheduler = DPMSolverMultistepScheduler(
            beta_start=beta_start, beta_end=beta_end, beta_schedule="scaled_linear"
        )
    elif args.scheduler_type == "ddim":
        scheduler = DDIMScheduler(
            beta_start=beta_start,
            beta_end=beta_end,
            beta_schedule="scaled_linear",
            clip_sample=False,
            set_alpha_to_one=False,
            steps_offset=1,
        )
    else:
        raise ValueError(f"Scheduler of type {args.scheduler_type} doesn't exist!")

    # Convert the UNet2DConditionModel models.
    if args.unet_checkpoint_path is not None:
        # image UNet
        image_unet_config = create_image_unet_diffusers_config(IMAGE_UNET_CONFIG)
        checkpoint = torch.load(args.unet_checkpoint_path)
        converted_image_unet_checkpoint = convert_vd_unet_checkpoint(
            checkpoint, image_unet_config, unet_key="model.diffusion_model.unet_image.", extract_ema=args.extract_ema
        )
        image_unet = UNet2DConditionModel(**image_unet_config)
        image_unet.load_state_dict(converted_image_unet_checkpoint)

        # text UNet
        text_unet_config = create_text_unet_diffusers_config(TEXT_UNET_CONFIG)
        converted_text_unet_checkpoint = convert_vd_unet_checkpoint(
            checkpoint, text_unet_config, unet_key="model.diffusion_model.unet_text.", extract_ema=args.extract_ema
        )
        text_unet = UNetFlatConditionModel(**text_unet_config)
        text_unet.load_state_dict(converted_text_unet_checkpoint)

    # Convert the VAE model.
    if args.vae_checkpoint_path is not None:
        vae_config = create_vae_diffusers_config(AUTOENCODER_CONFIG)
        checkpoint = torch.load(args.vae_checkpoint_path)
        converted_vae_checkpoint = convert_vd_vae_checkpoint(checkpoint, vae_config)

        vae = AutoencoderKL(**vae_config)
        vae.load_state_dict(converted_vae_checkpoint)

    tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
    image_feature_extractor = CLIPImageProcessor.from_pretrained("openai/clip-vit-large-patch14")
    text_encoder = CLIPTextModelWithProjection.from_pretrained("openai/clip-vit-large-patch14")
    image_encoder = CLIPVisionModelWithProjection.from_pretrained("openai/clip-vit-large-patch14")

    pipe = VersatileDiffusionPipeline(
        scheduler=scheduler,
        tokenizer=tokenizer,
        image_feature_extractor=image_feature_extractor,
        text_encoder=text_encoder,
        image_encoder=image_encoder,
        image_unet=image_unet,
        text_unet=text_unet,
        vae=vae,
    )
    pipe.save_pretrained(args.dump_path)