File size: 25,466 Bytes
12f772a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import inspect
from dataclasses import dataclass
from typing import Callable, Dict, List, Optional, Union

import numpy as np
import PIL.Image
import torch
from transformers import CLIPImageProcessor, CLIPVisionModelWithProjection
from models.svdxt_featureflow_forward_controlnet_s2d_fixcmp_norefine import FlowControlNet

from diffusers.image_processor import VaeImageProcessor
from diffusers.models import AutoencoderKLTemporalDecoder
from diffusers.utils import BaseOutput, logging
from diffusers.utils.torch_utils import randn_tensor
from diffusers.pipelines.pipeline_utils import DiffusionPipeline
from utils.scheduling_euler_discrete_karras_fix import EulerDiscreteScheduler

from models.unet_spatio_temporal_condition_controlnet import UNetSpatioTemporalConditionControlNetModel


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


def _get_add_time_ids(
        noise_aug_strength,
        dtype,
        batch_size,
        fps=4,
        motion_bucket_id=128,
        unet=None,
    ):
        add_time_ids = [fps, motion_bucket_id, noise_aug_strength]

        passed_add_embed_dim = unet.config.addition_time_embed_dim * len(add_time_ids)
        expected_add_embed_dim = unet.add_embedding.linear_1.in_features

        if expected_add_embed_dim != passed_add_embed_dim:
            raise ValueError(
                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
            )

        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
        # add_time_ids = add_time_ids.repeat(batch_size * num_videos_per_prompt, 1)


        return add_time_ids


def _append_dims(x, target_dims):
    """Appends dimensions to the end of a tensor until it has target_dims dimensions."""
    dims_to_append = target_dims - x.ndim
    if dims_to_append < 0:
        raise ValueError(f"input has {x.ndim} dims but target_dims is {target_dims}, which is less")
    return x[(...,) + (None,) * dims_to_append]


def tensor2vid(video: torch.Tensor, processor, output_type="np"):
    # Based on:
    # https://github.com/modelscope/modelscope/blob/1509fdb973e5871f37148a4b5e5964cafd43e64d/modelscope/pipelines/multi_modal/text_to_video_synthesis_pipeline.py#L78

    batch_size, channels, num_frames, height, width = video.shape
    outputs = []
    for batch_idx in range(batch_size):
        batch_vid = video[batch_idx].permute(1, 0, 2, 3)
        batch_output = processor.postprocess(batch_vid, output_type)

        outputs.append(batch_output)

    return outputs


@dataclass
class FlowControlNetPipelineOutput(BaseOutput):
    r"""
    Output class for zero-shot text-to-video pipeline.

    Args:
        frames (`[List[PIL.Image.Image]`, `np.ndarray`]):
            List of denoised PIL images of length `batch_size` or NumPy array of shape `(batch_size, height, width,
            num_channels)`.
    """

    frames: Union[List[PIL.Image.Image], np.ndarray]
    controlnet_flow: torch.Tensor


class FlowControlNetPipeline(DiffusionPipeline):
    model_cpu_offload_seq = "image_encoder->unet->vae"
    _callback_tensor_inputs = ["latents"]
    def __init__(
        self,
        vae: AutoencoderKLTemporalDecoder,
        image_encoder: CLIPVisionModelWithProjection,
        unet: UNetSpatioTemporalConditionControlNetModel,
        controlnet: FlowControlNet,
        scheduler: EulerDiscreteScheduler,
        feature_extractor: CLIPImageProcessor,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            image_encoder=image_encoder,
            controlnet=controlnet,
            unet=unet,
            scheduler=scheduler,
            feature_extractor=feature_extractor,
        )
        
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)


    def _encode_image(self, image, device, num_videos_per_prompt, do_classifier_free_guidance):
        dtype = next(self.image_encoder.parameters()).dtype

        if not isinstance(image, torch.Tensor):
            image = self.image_processor.pil_to_numpy(image)
            image = self.image_processor.numpy_to_pt(image)

        #image = image.unsqueeze(0)
        image = _resize_with_antialiasing(image, (224, 224))

        image = image.to(device=device, dtype=dtype)
        image_embeddings = self.image_encoder(image).image_embeds
        image_embeddings = image_embeddings.unsqueeze(1)

        # duplicate image embeddings for each generation per prompt, using mps friendly method
        bs_embed, seq_len, _ = image_embeddings.shape
        image_embeddings = image_embeddings.repeat(1, num_videos_per_prompt, 1)
        image_embeddings = image_embeddings.view(bs_embed * num_videos_per_prompt, seq_len, -1)

        if do_classifier_free_guidance:
            negative_image_embeddings = torch.zeros_like(image_embeddings)

            # For classifier free guidance, we need to do two forward passes.
            # Here we concatenate the unconditional and text embeddings into a single batch
            # to avoid doing two forward passes
            image_embeddings = torch.cat([negative_image_embeddings, image_embeddings])

        return image_embeddings

    def _encode_vae_image(
        self,
        image: torch.Tensor,
        device,
        num_videos_per_prompt,
        do_classifier_free_guidance,
    ):
        image = image.to(device=device)
        image_latents = self.vae.encode(image).latent_dist.mode()

        if do_classifier_free_guidance:
            negative_image_latents = torch.zeros_like(image_latents)

            # For classifier free guidance, we need to do two forward passes.
            # Here we concatenate the unconditional and text embeddings into a single batch
            # to avoid doing two forward passes
            image_latents = torch.cat([negative_image_latents, image_latents])

        # duplicate image_latents for each generation per prompt, using mps friendly method
        image_latents = image_latents.repeat(num_videos_per_prompt, 1, 1, 1)

        return image_latents

    def _get_add_time_ids(
        self,
        fps,
        motion_bucket_id,
        noise_aug_strength,
        dtype,
        batch_size,
        num_videos_per_prompt,
        do_classifier_free_guidance,
    ):
        add_time_ids = [fps, motion_bucket_id, noise_aug_strength]

        passed_add_embed_dim = self.unet.config.addition_time_embed_dim * len(add_time_ids)
        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features

        if expected_add_embed_dim != passed_add_embed_dim:
            raise ValueError(
                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
            )

        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
        add_time_ids = add_time_ids.repeat(batch_size * num_videos_per_prompt, 1)

        if do_classifier_free_guidance:
            add_time_ids = torch.cat([add_time_ids, add_time_ids])

        return add_time_ids

    def decode_latents(self, latents, num_frames, decode_chunk_size=14):
        # [batch, frames, channels, height, width] -> [batch*frames, channels, height, width]
        latents = latents.flatten(0, 1)

        latents = 1 / self.vae.config.scaling_factor * latents

        accepts_num_frames = "num_frames" in set(inspect.signature(self.vae.forward).parameters.keys())

        # decode decode_chunk_size frames at a time to avoid OOM
        frames = []
        for i in range(0, latents.shape[0], decode_chunk_size):
            num_frames_in = latents[i : i + decode_chunk_size].shape[0]
            decode_kwargs = {}
            if accepts_num_frames:
                # we only pass num_frames_in if it's expected
                decode_kwargs["num_frames"] = num_frames_in

            frame = self.vae.decode(latents[i : i + decode_chunk_size], **decode_kwargs).sample
            frames.append(frame)
        frames = torch.cat(frames, dim=0)

        # [batch*frames, channels, height, width] -> [batch, channels, frames, height, width]
        frames = frames.reshape(-1, num_frames, *frames.shape[1:]).permute(0, 2, 1, 3, 4)

        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        frames = frames.float()
        return frames

    def check_inputs(self, image, height, width):
        if (
            not isinstance(image, torch.Tensor)
            and not isinstance(image, PIL.Image.Image)
            and not isinstance(image, list)
        ):
            raise ValueError(
                "`image` has to be of type `torch.FloatTensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
                f" {type(image)}"
            )

        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

    def prepare_latents(
        self,
        batch_size,
        num_frames,
        num_channels_latents,
        height,
        width,
        dtype,
        device,
        generator,
        latents=None,
    ):
        shape = (
            batch_size,
            num_frames,
            num_channels_latents // 2,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if latents is None:
            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
        else:
            latents = latents.to(device)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = latents * self.scheduler.init_noise_sigma
        return latents

    @property
    def guidance_scale(self):
        return self._guidance_scale

    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None

    @property
    def num_timesteps(self):
        return self._num_timesteps

    @torch.no_grad()
    def __call__(
        self,
        image: Union[PIL.Image.Image, List[PIL.Image.Image], torch.FloatTensor],  # PIL
        controlnet_condition: [torch.FloatTensor] = None,  # PIL
        controlnet_flow: [torch.FloatTensor] = None,  # [1, 13, 2, h, w]
        # controlnet_mask: [torch.FloatTensor] = None,  # [1, 13, 2, h, w]
        # val_pixel_values_384: [torch.FloatTensor] = None,
        # val_sparse_optical_flow_384: [torch.FloatTensor] = None,
        # val_mask_384: [torch.FloatTensor] = None,
        height: int = 576,
        width: int = 1024,
        num_frames: Optional[int] = None,
        num_inference_steps: int = 25,
        min_guidance_scale: float = 1.0,
        max_guidance_scale: float = 3.0,
        fps: int = 7,
        motion_bucket_id: int = 127,
        noise_aug_strength: int = 0.02,
        decode_chunk_size: Optional[int] = None,
        num_videos_per_prompt: Optional[int] = 1,
        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
        latents: Optional[torch.FloatTensor] = None,
        output_type: Optional[str] = "pil",
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        return_dict: bool = True,
        controlnet_cond_scale=1.0,
        batch_size=1,
    ):

        # 0. Default height and width to unet
        height = height or self.unet.config.sample_size * self.vae_scale_factor
        width = width or self.unet.config.sample_size * self.vae_scale_factor

        num_frames = num_frames if num_frames is not None else self.unet.config.num_frames
        decode_chunk_size = decode_chunk_size if decode_chunk_size is not None else num_frames

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(image, height, width)

        # 2. Define call parameters
        device = self._execution_device
        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = max_guidance_scale > 1.0

        # 3. Encode input image
        image_embeddings = self._encode_image(image, device, num_videos_per_prompt, do_classifier_free_guidance)

        # NOTE: Stable Diffusion Video was conditioned on fps - 1, which
        # is why it is reduced here.
        # See: https://github.com/Stability-AI/generative-models/blob/ed0997173f98eaf8f4edf7ba5fe8f15c6b877fd3/scripts/sampling/simple_video_sample.py#L188
        fps = fps - 1

        # 4. Encode input image using VAE
        image = self.image_processor.preprocess(image, height=height, width=width)
        noise = randn_tensor(image.shape, generator=generator, device=image.device, dtype=image.dtype)
        image = image + noise_aug_strength * noise

        needs_upcasting = self.vae.dtype == torch.float16 and self.vae.config.force_upcast
        if needs_upcasting:
            self.vae.to(dtype=torch.float32)

        image_latents = self._encode_vae_image(image, device, num_videos_per_prompt, do_classifier_free_guidance)
        image_latents = image_latents.to(image_embeddings.dtype)

        # cast back to fp16 if needed
        if needs_upcasting:
            self.vae.to(dtype=torch.float16)

        # Repeat the image latents for each frame so we can concatenate them with the noise
        # image_latents [batch, channels, height, width] ->[batch, num_frames, channels, height, width]
        image_latents = image_latents.unsqueeze(1).repeat(1, num_frames, 1, 1, 1)
        #image_latents = torch.cat([image_latents] * 2) if do_classifier_free_guidance else image_latents
        
        # 5. Get Added Time IDs
        added_time_ids = self._get_add_time_ids(
            fps,
            motion_bucket_id,
            noise_aug_strength,
            image_embeddings.dtype,
            batch_size,
            num_videos_per_prompt,
            do_classifier_free_guidance,
        )
        added_time_ids = added_time_ids.to(device)

        # 4. Prepare timesteps
        self.scheduler.set_timesteps(num_inference_steps, device=device)
        timesteps = self.scheduler.timesteps

        # 5. Prepare latent variables
 
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            num_frames,
            num_channels_latents,
            height,
            width,
            image_embeddings.dtype,
            device,
            generator,
            latents,
        )
        
        #prepare controlnet condition
        controlnet_condition = self.image_processor.preprocess(controlnet_condition, height=height, width=width)
        # controlnet_condition = controlnet_condition.unsqueeze(0)
        controlnet_condition = torch.cat([controlnet_condition] * 2) if do_classifier_free_guidance else latents
        controlnet_condition = controlnet_condition.to(device, latents.dtype)

        controlnet_flow = torch.cat([controlnet_flow] * 2) if do_classifier_free_guidance else latents
        controlnet_flow = controlnet_flow.to(device, latents.dtype)

        # print(height, width)
        # print(controlnet_condition.shape)
        # print(controlnet_flow.shape)
        # print(image.shape)

        # assert False


        # controlnet_mask = torch.cat([controlnet_mask] * 2) if do_classifier_free_guidance else latents
        # controlnet_mask = controlnet_mask.to(device, latents.dtype)

        # controlnet_init_flow = torch.cat([controlnet_init_flow] * 2) if do_classifier_free_guidance else latents
        # controlnet_init_flow = controlnet_init_flow.to(device, latents.dtype)

        # val_pixel_values_384 = torch.cat([val_pixel_values_384] * 2) if do_classifier_free_guidance else latents
        # val_pixel_values_384 = val_pixel_values_384.to(device, latents.dtype)

        # val_sparse_optical_flow_384 = torch.cat([val_sparse_optical_flow_384] * 2) if do_classifier_free_guidance else latents
        # val_sparse_optical_flow_384 = val_sparse_optical_flow_384.to(device, latents.dtype)

        # val_mask_384 = torch.cat([val_mask_384] * 2) if do_classifier_free_guidance else latents
        # val_mask_384 = val_mask_384.to(device, latents.dtype)
        
        # 7. Prepare guidance scale
        guidance_scale = torch.linspace(min_guidance_scale, max_guidance_scale, num_frames).unsqueeze(0)
        guidance_scale = guidance_scale.to(device, latents.dtype)
        guidance_scale = guidance_scale.repeat(batch_size * num_videos_per_prompt, 1)
        guidance_scale = _append_dims(guidance_scale, latents.ndim)

        self._guidance_scale = guidance_scale

        noise_aug_strength = 0.02 #"¯\_(ツ)_/¯
        added_time_ids = _get_add_time_ids(
            noise_aug_strength,
            image_embeddings.dtype,
            batch_size,
            6,
            128,
            unet=self.unet,
        )
        added_time_ids = torch.cat([added_time_ids] * 2) 
        added_time_ids = added_time_ids.to(latents.device)

        
        # 8. Denoising loop
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
        self._num_timesteps = len(timesteps)
        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                # expand the latents if we are doing classifier free guidance
                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                # Concatenate image_latents over channels dimention
                
                latent_model_input = torch.cat([latent_model_input, image_latents], dim=2)

                # print(latent_model_input.shape)
                # print(controlnet_flow.shape)

                # assert False

                # controlnet_flow = None

                down_block_res_samples, mid_block_res_sample, controlnet_flow, _ = self.controlnet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=image_embeddings,
                    controlnet_cond=controlnet_condition,
                    controlnet_flow=controlnet_flow,
                    # controlnet_mask=controlnet_mask,
                    # pixel_values_384=val_pixel_values_384,
                    # sparse_optical_flow_384=val_sparse_optical_flow_384,
                    # mask_384=val_mask_384,
                    added_time_ids=added_time_ids,
                    conditioning_scale=controlnet_cond_scale,
                    guess_mode=False,
                    return_dict=False,
                )

                # predict the noise residual
                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=image_embeddings,
                    down_block_additional_residuals=down_block_res_samples,
                    mid_block_additional_residual=mid_block_res_sample,
                    added_time_ids=added_time_ids,
                    return_dict=False,
                )[0]
                

                # assert False

                
                # perform guidance
                if do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_cond = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_cond - noise_pred_uncond)

                # compute the previous noisy sample x_t -> x_t-1
                latents = self.scheduler.step(noise_pred, t, latents).prev_sample

                if callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)

                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        if not output_type == "latent":
            # cast back to fp16 if needed
            if needs_upcasting:
                self.vae.to(dtype=torch.float16)
            frames = self.decode_latents(latents.to(self.vae.dtype), num_frames, decode_chunk_size)
            frames = tensor2vid(frames, self.image_processor, output_type=output_type)
        else:
            frames = latents

        self.maybe_free_model_hooks()

        if not return_dict:
            return frames, controlnet_flow

        return FlowControlNetPipelineOutput(frames=frames, controlnet_flow=controlnet_flow)
    

# resizing utils
# TODO: clean up later
def _resize_with_antialiasing(input, size, interpolation="bicubic", align_corners=True):
    
    if input.ndim == 3:
        input = input.unsqueeze(0)  # Add a batch dimension
        
    h, w = input.shape[-2:]
    factors = (h / size[0], w / size[1])

    # First, we have to determine sigma
    # Taken from skimage: https://github.com/scikit-image/scikit-image/blob/v0.19.2/skimage/transform/_warps.py#L171
    sigmas = (
        max((factors[0] - 1.0) / 2.0, 0.001),
        max((factors[1] - 1.0) / 2.0, 0.001),
    )

    # Now kernel size. Good results are for 3 sigma, but that is kind of slow. Pillow uses 1 sigma
    # https://github.com/python-pillow/Pillow/blob/master/src/libImaging/Resample.c#L206
    # But they do it in the 2 passes, which gives better results. Let's try 2 sigmas for now
    ks = int(max(2.0 * 2 * sigmas[0], 3)), int(max(2.0 * 2 * sigmas[1], 3))

    # Make sure it is odd
    if (ks[0] % 2) == 0:
        ks = ks[0] + 1, ks[1]

    if (ks[1] % 2) == 0:
        ks = ks[0], ks[1] + 1

    input = _gaussian_blur2d(input, ks, sigmas)

    output = torch.nn.functional.interpolate(input, size=size, mode=interpolation, align_corners=align_corners)
    return output


def _compute_padding(kernel_size):
    """Compute padding tuple."""
    # 4 or 6 ints:  (padding_left, padding_right,padding_top,padding_bottom)
    # https://pytorch.org/docs/stable/nn.html#torch.nn.functional.pad
    if len(kernel_size) < 2:
        raise AssertionError(kernel_size)
    computed = [k - 1 for k in kernel_size]

    # for even kernels we need to do asymmetric padding :(
    out_padding = 2 * len(kernel_size) * [0]

    for i in range(len(kernel_size)):
        computed_tmp = computed[-(i + 1)]

        pad_front = computed_tmp // 2
        pad_rear = computed_tmp - pad_front

        out_padding[2 * i + 0] = pad_front
        out_padding[2 * i + 1] = pad_rear

    return out_padding


def _filter2d(input, kernel):
    # prepare kernel
    b, c, h, w = input.shape
    tmp_kernel = kernel[:, None, ...].to(device=input.device, dtype=input.dtype)

    tmp_kernel = tmp_kernel.expand(-1, c, -1, -1)

    height, width = tmp_kernel.shape[-2:]

    padding_shape: list[int] = _compute_padding([height, width])
    input = torch.nn.functional.pad(input, padding_shape, mode="reflect")

    # kernel and input tensor reshape to align element-wise or batch-wise params
    tmp_kernel = tmp_kernel.reshape(-1, 1, height, width)
    input = input.view(-1, tmp_kernel.size(0), input.size(-2), input.size(-1))

    # convolve the tensor with the kernel.
    output = torch.nn.functional.conv2d(input, tmp_kernel, groups=tmp_kernel.size(0), padding=0, stride=1)

    out = output.view(b, c, h, w)
    return out


def _gaussian(window_size: int, sigma):
    if isinstance(sigma, float):
        sigma = torch.tensor([[sigma]])

    batch_size = sigma.shape[0]

    x = (torch.arange(window_size, device=sigma.device, dtype=sigma.dtype) - window_size // 2).expand(batch_size, -1)

    if window_size % 2 == 0:
        x = x + 0.5

    gauss = torch.exp(-x.pow(2.0) / (2 * sigma.pow(2.0)))

    return gauss / gauss.sum(-1, keepdim=True)


def _gaussian_blur2d(input, kernel_size, sigma):
    if isinstance(sigma, tuple):
        sigma = torch.tensor([sigma], dtype=input.dtype)
    else:
        sigma = sigma.to(dtype=input.dtype)

    ky, kx = int(kernel_size[0]), int(kernel_size[1])
    bs = sigma.shape[0]
    kernel_x = _gaussian(kx, sigma[:, 1].view(bs, 1))
    kernel_y = _gaussian(ky, sigma[:, 0].view(bs, 1))
    out_x = _filter2d(input, kernel_x[..., None, :])
    out = _filter2d(out_x, kernel_y[..., None])

    return out