Each rank should sample a different timestep in dmd_forward and faker_score_forward

examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py

@@ -0,0 +1,46 @@
+# NOTE: This is still a work in progress, and the checkpoints are not released yet.
+
+from fastvideo import VideoGenerator, SamplingParam
+import json
+# from fastvideo.configs.sample import SamplingParam
+
+OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_i2v"
+def main():
+    # FastVideo will automatically use the optimal default arguments for the
+    # model.
+    # If a local path is provided, FastVideo will make a best effort
+    # attempt to identify the optimal arguments.
+    generator = VideoGenerator.from_pretrained(
+        "rand0nmr/SFWan2.2-T2V-A14B-Diffusers",
+        # FastVideo will automatically handle distributed setup
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=True, # DiT need to be offloaded for MoE
+        dit_precision="fp32",
+        vae_cpu_offload=False,
+        text_encoder_cpu_offload=True,
+        dmd_denoising_steps=[1000, 850, 700, 550, 350, 275, 200, 125],
+        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
+        pin_cpu_memory=True,
+        init_weights_from_safetensors="/mnt/sharefs/users/hao.zhang/wei/SFwan2.2_distill_self_forcing_release_x0_CacheAppend_1333/checkpoint-442_weight_only/ema/generator_ema.safetensors",
+        init_weights_from_safetensors_2="/mnt/sharefs/users/hao.zhang/wei/SFwan2.2_distill_self_forcing_release_x0_CacheAppend_1333/checkpoint-442_weight_only/ema/generator_ema_2.safetensors",
+        # image_encoder_cpu_offload=False,
+    )
+
+    sampling_param = SamplingParam.from_pretrained("rand0nmr/SFWan2.2-T2V-A14B-Diffusers")
+    sampling_param.num_frames = 73
+    sampling_param.width = 832
+    sampling_param.height = 480
+    sampling_param.seed = 1000
+
+    with open("prompts/mixkit_i2v.jsonl", "r") as f:
+        prompt_image_pairs = json.load(f)
+
+    for prompt_image_pair in prompt_image_pairs:
+        prompt = prompt_image_pair["prompt"]
+        image_path = prompt_image_pair["image_path"]
+        _ = generator.generate_video(prompt, image_path=image_path, output_path=OUTPUT_PATH, save_video=True, sampling_param=sampling_param)
+
+
+if __name__ == "__main__":
+    main()

fastvideo/configs/pipelines/wan.py

@@ -186,3 +186,7 @@ class SelfForcingWan2_2_T2V480PConfig(Wan2_2_T2V_A14B_Config):
     dmd_denoising_steps: list[int] | None = field(
         default_factory=lambda: [1000, 850, 700, 550, 350, 275, 200, 125])
     warp_denoising_step: bool = True
+
+    def __post_init__(self) -> None:
+        self.vae_config.load_encoder = True
+        self.vae_config.load_decoder = True

fastvideo/configs/sample/wan.py

@@ -191,8 +191,6 @@ class SelfForcingWan2_1_T2V_1_3B_480P_SamplingParam(
 @dataclass
 class SelfForcingWan2_2_T2V_A14B_480P_SamplingParam(
         Wan2_2_T2V_A14B_SamplingParam):
-    guidance_scale: float = 2.0
-    guidance_scale_2: float = 2.0
     num_inference_steps: int = 8
     num_frames: int = 81
     height: int = 448

fastvideo/models/schedulers/scheduling_self_forcing_flow_match.py

@@ -86,6 +86,12 @@ class SelfForcingFlowMatchScheduler(BaseScheduler, ConfigMixin, SchedulerMixin):
             return (prev_sample, )
         return SelfForcingFlowMatchSchedulerOutput(prev_sample=prev_sample)
 
+    @staticmethod
+    def calculate_alpha_beta_high(sigma, sigma_bound):
+        alpha = (1 - sigma) / (1 - sigma_bound)
+        beta = torch.sqrt(sigma ** 2 - (alpha * sigma_bound) ** 2)
+        return alpha, beta
+        
     def add_noise(self, original_samples, noise, timestep):
         """
         Diffusion forward corruption process.
@@ -105,6 +111,32 @@ class SelfForcingFlowMatchScheduler(BaseScheduler, ConfigMixin, SchedulerMixin):
         sample = (1 - sigma) * original_samples + sigma * noise
         return sample.type_as(noise)
 
+    def add_noise_high(self, original_samples, noise, timestep, boundary_timestep):
+        """
+        Diffusion forward corruption process.
+        Input:
+            - clean_latent: the clean latent with shape [B*T, C, H, W]
+            - noise: the noise with shape [B*T, C, H, W]
+            - timestep: the timestep with shape [B*T]
+        Output: the corrupted latent with shape [B*T, C, H, W]
+        """
+        if timestep.ndim == 2:
+            timestep = timestep.flatten(0, 1)
+        if boundary_timestep.ndim == 2:
+            boundary_timestep = boundary_timestep.flatten(0, 1)
+        self.sigmas = self.sigmas.to(noise.device)
+        self.timesteps = self.timesteps.to(noise.device)
+        timestep_id = torch.argmin(
+            (self.timesteps.unsqueeze(0) - timestep.unsqueeze(1)).abs(), dim=1)
+        sigma = self.sigmas[timestep_id].reshape(-1, 1, 1, 1)
+
+        boundary_timestep_id = torch.argmin(
+            (self.timesteps.unsqueeze(0) - boundary_timestep.unsqueeze(1)).abs(), dim=1)
+        sigma_boundary = self.sigmas[boundary_timestep_id].reshape(-1, 1, 1, 1)
+        alpha, beta = self.calculate_alpha_beta_high(sigma, sigma_boundary)
+        sample = alpha * original_samples + beta * noise
+        return sample.type_as(noise)
+
     def training_target(self, sample, noise, timestep):
         target = noise - sample
         return target

fastvideo/models/utils.py

@@ -180,3 +180,51 @@ def pred_noise_to_pred_video(pred_noise: torch.Tensor,
     sigma_t = sigmas[timestep_id].reshape(-1, 1, 1, 1)
     pred_video = noise_input_latent - sigma_t * pred_noise
     return pred_video.to(dtype)
+
+def pred_noise_to_x_bound(pred_noise: torch.Tensor,
+                             noise_input_latent: torch.Tensor,
+                             timestep: torch.Tensor,
+                             boundary_timestep: torch.Tensor,
+                             scheduler: Any) -> torch.Tensor:
+    """
+    Convert predicted noise to clean latent.
+
+    Args:
+    pred_noise: the predicted noise with shape [B, C, H, W]
+        where B is batch_size or batch_size * num_frames
+    noise_input_latent: the noisy latent with shape [B, C, H, W],
+    timestep: the timestep with shape [1] or [bs * num_frames] or [bs, num_frames]
+    boundary_timestep: the boundary timestep with shape [1] or [bs * num_frames] or [bs, num_frames]
+    scheduler: the scheduler
+
+    Returns:
+        the predicted video with shape [B, C, H, W]
+    """
+    # If timestep is [bs, num_frames]
+    if timestep.ndim == 2:
+        timestep = timestep.flatten(0, 1)
+        assert timestep.numel() == noise_input_latent.shape[0]
+    elif timestep.ndim == 1:
+        # If timestep is [1]
+        if timestep.shape[0] == 1:
+            timestep = timestep.expand(noise_input_latent.shape[0])
+        else:
+            assert timestep.numel() == noise_input_latent.shape[0]
+    else:
+        raise ValueError(f"[pred_noise_to_pred_video] Invalid timestep shape: {timestep.shape}")
+    # timestep shape should be [B]
+    dtype = pred_noise.dtype
+    device = pred_noise.device
+    pred_noise = pred_noise.double().to(device)
+    noise_input_latent = noise_input_latent.double().to(device)
+    sigmas = scheduler.sigmas.double().to(device)
+    timesteps = scheduler.timesteps.double().to(device)
+    timestep_id = torch.argmin(
+        (timesteps.unsqueeze(0) - timestep.unsqueeze(1)).abs(), dim=1)
+    sigma_t = sigmas[timestep_id].reshape(-1, 1, 1, 1)
+
+    boundary_timestep_id = torch.argmin(
+        (timesteps.unsqueeze(0) - boundary_timestep.unsqueeze(1)).abs(), dim=1)
+    sigma_t_boundary = sigmas[boundary_timestep_id].reshape(-1, 1, 1, 1)
+    pred_video = noise_input_latent - (sigma_t - sigma_t_boundary) * pred_noise
+    return pred_video.to(dtype)

fastvideo/pipelines/basic/wan/wan_causal_dmd_pipeline.py

@@ -50,7 +50,8 @@ class WanCausalDMDPipeline(LoRAPipeline, ComposedPipelineBase):
                        stage=CausalDMDDenosingStage(
                            transformer=self.get_module("transformer"),
                            transformer_2=self.get_module("transformer_2", None),
-                           scheduler=self.get_module("scheduler")))
+                           scheduler=self.get_module("scheduler"),
+                           vae=self.get_module("vae")))
 
         self.add_stage(stage_name="decoding_stage",
                        stage=DecodingStage(vae=self.get_module("vae")))

fastvideo/pipelines/stages/causal_denoising.py

@@ -4,7 +4,7 @@ from fastvideo.distributed import get_local_torch_device
 from fastvideo.fastvideo_args import FastVideoArgs
 from fastvideo.forward_context import set_forward_context
 from fastvideo.logger import init_logger
-from fastvideo.models.utils import pred_noise_to_pred_video
+from fastvideo.models.utils import pred_noise_to_pred_video, pred_noise_to_x_bound
 from fastvideo.pipelines.pipeline_batch_info import ForwardBatch
 from fastvideo.pipelines.stages.denoising import DenoisingStage
 from fastvideo.pipelines.stages.validators import StageValidators as V
@@ -34,13 +34,16 @@ class CausalDMDDenosingStage(DenoisingStage):
     Denoising stage for causal diffusion.
     """
 
-    def __init__(self, transformer, scheduler, transformer_2=None) -> None:
+    def __init__(self,
+                 transformer,
+                 scheduler,
+                 transformer_2=None,
+                 vae=None) -> None:
         super().__init__(transformer, scheduler, transformer_2)
         # KV and cross-attention cache state (initialized on first forward)
         self.transformer = transformer
         self.transformer_2 = transformer_2
-        self.kv_cache1: list | None = None
-        self.crossattn_cache: list | None = None
+        self.vae = vae
         # Model-dependent constants (aligned with causal_inference.py assumptions)
         self.num_transformer_blocks = len(self.transformer.blocks)
         self.num_frames_per_block = self.transformer.config.arch_config.num_frames_per_block
@@ -80,6 +83,13 @@ class CausalDMDDenosingStage(DenoisingStage):
             timesteps = scheduler_timesteps[1000 - timesteps]
         timesteps = timesteps.to(get_local_torch_device())
 
+        if fastvideo_args.pipeline_config.dit_config.boundary_ratio is not None:
+            boundary_timestep = fastvideo_args.pipeline_config.dit_config.boundary_ratio * self.scheduler.num_train_timesteps
+        else:
+            boundary_timestep = None
+
+        high_noise_timesteps = timesteps[timesteps >= boundary_timestep]
+
         # Image kwargs (kept empty unless caller provides compatible args)
         image_kwargs: dict = {}
 
@@ -103,113 +113,101 @@ class CausalDMDDenosingStage(DenoisingStage):
         assert torch.isnan(prompt_embeds[0]).sum() == 0
 
         # Initialize or reset caches
-        if self.kv_cache1 is None:
-            self._initialize_kv_cache(batch_size=latents.shape[0],
-                                      dtype=target_dtype,
-                                      device=latents.device)
-            self._initialize_crossattn_cache(
-                batch_size=latents.shape[0],
-                max_text_len=fastvideo_args.pipeline_config.
-                text_encoder_configs[0].arch_config.text_len,
-                dtype=target_dtype,
-                device=latents.device)
-        else:
-            assert self.crossattn_cache is not None
-            # reset cross-attention cache
-            for block_index in range(self.num_transformer_blocks):
-                self.crossattn_cache[block_index][
-                    "is_init"] = False  # type: ignore
-            # reset kv cache pointers
-            for block_index in range(len(self.kv_cache1)):
-                self.kv_cache1[block_index][
-                    "global_end_index"] = torch.tensor(  # type: ignore
-                        [0],
-                        dtype=torch.long,
-                        device=latents.device)
-                self.kv_cache1[block_index][
-                    "local_end_index"] = torch.tensor(  # type: ignore
-                        [0],
-                        dtype=torch.long,
-                        device=latents.device)
+        kv_cache1 = self._initialize_kv_cache(batch_size=latents.shape[0],
+                                              dtype=target_dtype,
+                                              device=latents.device)
+        kv_cache2 = None
+        if boundary_timestep is not None:
+            # Initialize the low noise kv cache
+            kv_cache2 = self._initialize_kv_cache(batch_size=latents.shape[0],
+                                                  dtype=target_dtype,
+                                                  device=latents.device)
 
-        # Optional: cache context features from provided image latents prior to generation
-        current_start_frame = 0
-        if getattr(batch, "image_latent", None) is not None:
-            image_latent = batch.image_latent
-            assert image_latent is not None
-            input_frames = image_latent.shape[2]
-            # timestep zero (or configured context noise) for cache warm-up
-            t_zero = torch.zeros([latents.shape[0]],
-                                 device=latents.device,
-                                 dtype=torch.long)
-            if independent_first_frame and input_frames >= 1:
-                # warm-up with the very first frame independently
-                image_first_btchw = image_latent[:, :, :1, :, :].to(
-                    target_dtype).permute(0, 2, 1, 3, 4)
-                with torch.autocast(device_type="cuda",
-                                    dtype=target_dtype,
-                                    enabled=autocast_enabled):
-                    _ = self.transformer(
-                        image_first_btchw,
-                        prompt_embeds,
-                        t_zero,
-                        kv_cache=self.kv_cache1,
-                        crossattn_cache=self.crossattn_cache,
-                        current_start=current_start_frame *
-                        self.frame_seq_length,
-                        **image_kwargs,
-                        **pos_cond_kwargs,
-                    )
-                current_start_frame += 1
-                remaining_frames = input_frames - 1
-            else:
-                remaining_frames = input_frames
+        def _get_kv_cache(timestep: float) -> dict:
+            if boundary_timestep is not None:
+                if timestep >= boundary_timestep:
+                    return kv_cache1
+                else:
+                    return kv_cache2
+            return kv_cache1
 
-            # process remaining input frames in blocks of num_frame_per_block
-            while remaining_frames > 0:
-                block = min(self.num_frames_per_block, remaining_frames)
-                ref_btchw = image_latent[:, :, current_start_frame:
-                                         current_start_frame +
-                                         block, :, :].to(target_dtype).permute(
-                                             0, 2, 1, 3, 4)
-                with torch.autocast(device_type="cuda",
-                                    dtype=target_dtype,
-                                    enabled=autocast_enabled):
-                    _ = self.transformer(
-                        ref_btchw,
-                        prompt_embeds,
-                        t_zero,
-                        kv_cache=self.kv_cache1,
-                        crossattn_cache=self.crossattn_cache,
-                        current_start=current_start_frame *
-                        self.frame_seq_length,
-                        **image_kwargs,
-                        **pos_cond_kwargs,
-                    )
-                current_start_frame += block
-                remaining_frames -= block
+        crossattn_cache = self._initialize_crossattn_cache(
+            batch_size=latents.shape[0],
+            max_text_len=fastvideo_args.pipeline_config.text_encoder_configs[0].
+            arch_config.text_len,
+            dtype=target_dtype,
+            device=latents.device)
 
-        # Base position offset from any cache warm-up
-        pos_start_base = current_start_frame
+        pos_start_base = 0
 
         # Determine block sizes
-        if not independent_first_frame or (independent_first_frame
-                                           and batch.image_latent is not None):
-            if t % self.num_frames_per_block != 0:
-                raise ValueError(
-                    "num_frames must be divisible by num_frames_per_block for causal DMD denoising"
+        block_sizes = [self.num_frames_per_block] * 7
+        block_sizes[0] = 1
+        start_index = 0
+
+        first_frame_latent = None
+        if batch.pil_image is not None:
+            # Causal video gen directly replaces the first frame of the latent with
+            # the image latent instead of appending along the channel dim
+            assert self.vae is not None, "VAE is not provided for causal video gen task"
+            self.vae = self.vae.to(get_local_torch_device())
+            first_frame_latent = self.vae.encode(batch.pil_image).mean.float()
+            if (hasattr(self.vae, "shift_factor")
+                    and self.vae.shift_factor is not None):
+                if isinstance(self.vae.shift_factor, torch.Tensor):
+                    first_frame_latent -= self.vae.shift_factor.to(
+                        first_frame_latent.device, first_frame_latent.dtype)
+                else:
+                    first_frame_latent -= self.vae.shift_factor
+
+            if isinstance(self.vae.scaling_factor, torch.Tensor):
+                first_frame_latent = first_frame_latent * self.vae.scaling_factor.to(
+                    first_frame_latent.device, first_frame_latent.dtype)
+            else:
+                first_frame_latent = first_frame_latent * self.vae.scaling_factor
+
+            if fastvideo_args.vae_cpu_offload:
+                self.vae = self.vae.to("cpu")
+
+            # Fill the low noise and high noise kv cache with first_frame_latent and timestep 0
+            t_zero = torch.zeros([latents.shape[0], 1],
+                                 device=latents.device,
+                                 dtype=torch.long)
+            with torch.autocast(device_type="cuda",
+                                dtype=target_dtype,
+                                enabled=autocast_enabled), \
+                set_forward_context(current_timestep=0,
+                                    attn_metadata=None,
+                                    forward_batch=batch):
+                self.transformer(
+                    first_frame_latent.to(target_dtype),
+                    prompt_embeds,
+                    t_zero,
+                    kv_cache=kv_cache1,
+                    crossattn_cache=crossattn_cache,
+                    current_start=(pos_start_base + start_index) *
+                    self.frame_seq_length,
+                    start_frame=start_index,
+                    **image_kwargs,
+                    **pos_cond_kwargs,
                 )
-            num_blocks = t // self.num_frames_per_block
-            block_sizes = [self.num_frames_per_block] * num_blocks
-            start_index = 0
-        else:
-            if (t - 1) % self.num_frames_per_block != 0:
-                raise ValueError(
-                    "(num_frames - 1) must be divisible by num_frame_per_block when independent_first_frame=True"
-                )
-            num_blocks = (t - 1) // self.num_frames_per_block
-            block_sizes = [1] + [self.num_frames_per_block] * num_blocks
-            start_index = 0
+                if boundary_timestep is not None:
+                    self.transformer_2(
+                        first_frame_latent.to(target_dtype),
+                        prompt_embeds,
+                        t_zero,
+                        kv_cache=kv_cache2,
+                        crossattn_cache=crossattn_cache,
+                        current_start=(pos_start_base + start_index) *
+                        self.frame_seq_length,
+                        start_frame=start_index,
+                        **image_kwargs,
+                        **pos_cond_kwargs,
+                    )
+
+            start_index += 1
+            block_sizes.pop(0)
+            latents[:, :, :1, :, :] = first_frame_latent
 
         # DMD loop in causal blocks
         with self.progress_bar(total=len(block_sizes) *
@@ -222,7 +220,7 @@ class CausalDMDDenosingStage(DenoisingStage):
                 video_raw_latent_shape = noise_latents_btchw.shape
 
                 for i, t_cur in enumerate(timesteps):
-                    if self.transformer_2 is not None and fastvideo_args.pipeline_config.dit_config.boundary_ratio is not None and t_cur < fastvideo_args.pipeline_config.dit_config.boundary_ratio * self.scheduler.num_train_timesteps:
+                    if boundary_timestep is not None and t_cur < boundary_timestep:
                         current_model = self.transformer_2
                     else:
                         current_model = self.transformer
@@ -280,8 +278,8 @@ class CausalDMDDenosingStage(DenoisingStage):
                             latent_model_input,
                             prompt_embeds,
                             t_expanded_noise,
-                            kv_cache=self.kv_cache1,
-                            crossattn_cache=self.crossattn_cache,
+                            kv_cache=_get_kv_cache(t_cur),
+                            crossattn_cache=crossattn_cache,
                             current_start=(pos_start_base + start_index) *
                             self.frame_seq_length,
                             start_frame=start_index,
@@ -290,12 +288,22 @@ class CausalDMDDenosingStage(DenoisingStage):
                         ).permute(0, 2, 1, 3, 4)
 
                     # Convert pred noise to pred video with FM Euler scheduler utilities
-                    pred_video_btchw = pred_noise_to_pred_video(
-                        pred_noise=pred_noise_btchw.flatten(0, 1),
-                        noise_input_latent=noise_latents.flatten(0, 1),
-                        timestep=t_expand,
-                        scheduler=self.scheduler).unflatten(
-                            0, pred_noise_btchw.shape[:2])
+                    if boundary_timestep is not None and t_cur >= boundary_timestep:
+                        pred_video_btchw = pred_noise_to_x_bound(
+                            pred_noise=pred_noise_btchw.flatten(0, 1),
+                            noise_input_latent=noise_latents.flatten(0, 1),
+                            timestep=t_expand,
+                            boundary_timestep=torch.ones_like(t_expand) *
+                            boundary_timestep,
+                            scheduler=self.scheduler).unflatten(
+                                0, pred_noise_btchw.shape[:2])
+                    else:
+                        pred_video_btchw = pred_noise_to_pred_video(
+                            pred_noise=pred_noise_btchw.flatten(0, 1),
+                            noise_input_latent=noise_latents.flatten(0, 1),
+                            timestep=t_expand,
+                            scheduler=self.scheduler).unflatten(
+                                0, pred_noise_btchw.shape[:2])
 
                     if i < len(timesteps) - 1:
                         next_timestep = timesteps[i + 1] * torch.ones(
@@ -309,11 +317,23 @@ class CausalDMDDenosingStage(DenoisingStage):
                                 batch.generator, list) else
                                        batch.generator)).to(self.device)
                         noise_btchw = noise
-                        noise_latents_btchw = self.scheduler.add_noise(
-                            pred_video_btchw.flatten(0, 1),
-                            noise_btchw.flatten(0, 1),
-                            next_timestep).unflatten(0,
-                                                     pred_video_btchw.shape[:2])
+                        if boundary_timestep is not None and i < len(
+                                high_noise_timesteps) - 1:
+                            noise_latents_btchw = self.scheduler.add_noise_high(
+                                pred_video_btchw.flatten(0, 1),
+                                noise_btchw.flatten(0, 1), next_timestep,
+                                torch.ones_like(next_timestep) *
+                                boundary_timestep).unflatten(
+                                    0, pred_video_btchw.shape[:2])
+                        elif boundary_timestep is not None and i == len(
+                                high_noise_timesteps) - 1:
+                            noise_latents_btchw = pred_video_btchw
+                        else:
+                            noise_latents_btchw = self.scheduler.add_noise(
+                                pred_video_btchw.flatten(0, 1),
+                                noise_btchw.flatten(0, 1),
+                                next_timestep).unflatten(
+                                    0, pred_video_btchw.shape[:2])
                         current_latents = noise_latents_btchw.permute(
                             0, 2, 1, 3, 4)
                     else:
@@ -341,18 +361,34 @@ class CausalDMDDenosingStage(DenoisingStage):
                                         attn_metadata=attn_metadata,
                                         forward_batch=batch):
                     t_expanded_context = t_context.unsqueeze(1)
-                    _ = current_model(
+
+                    if boundary_timestep is not None:
+                        self.transformer_2(
+                            context_bcthw,
+                            prompt_embeds,
+                            t_expanded_context,
+                            kv_cache=kv_cache2,
+                            crossattn_cache=crossattn_cache,
+                            current_start=(pos_start_base + start_index) *
+                            self.frame_seq_length,
+                            start_frame=start_index,
+                            **image_kwargs,
+                            **pos_cond_kwargs,
+                        )
+
+                    self.transformer(
                         context_bcthw,
                         prompt_embeds,
                         t_expanded_context,
-                        kv_cache=self.kv_cache1,
-                        crossattn_cache=self.crossattn_cache,
+                        kv_cache=kv_cache1,
+                        crossattn_cache=crossattn_cache,
                         current_start=(pos_start_base + start_index) *
                         self.frame_seq_length,
                         start_frame=start_index,
                         **image_kwargs,
                         **pos_cond_kwargs,
                     )
+
                 start_index += current_num_frames
 
         batch.latents = latents
@@ -392,7 +428,7 @@ class CausalDMDDenosingStage(DenoisingStage):
                 torch.tensor([0], dtype=torch.long, device=device),
             })
 
-        self.kv_cache1 = kv_cache1
+        return kv_cache1
 
     def _initialize_crossattn_cache(self, batch_size, max_text_len, dtype,
                                     device) -> None:
@@ -421,7 +457,7 @@ class CausalDMDDenosingStage(DenoisingStage):
                 "is_init":
                 False,
             })
-        self.crossattn_cache = crossattn_cache
+        return crossattn_cache
 
     def verify_input(self, batch: ForwardBatch,
                      fastvideo_args: FastVideoArgs) -> VerificationResult:

fastvideo/pipelines/stages/input_validation.py

@@ -5,7 +5,6 @@ Input validation stage for diffusion pipelines.
 
 import torch
 import torchvision.transforms.functional as TF
-from PIL import Image
 
 from fastvideo.fastvideo_args import FastVideoArgs
 from fastvideo.logger import init_logger
@@ -14,7 +13,6 @@ from fastvideo.pipelines.pipeline_batch_info import ForwardBatch
 from fastvideo.pipelines.stages.base import PipelineStage
 from fastvideo.pipelines.stages.validators import (StageValidators,
                                                    VerificationResult)
-from fastvideo.utils import best_output_size
 
 logger = init_logger(__name__)
 
@@ -106,27 +104,31 @@ class InputValidationStage(PipelineStage):
             batch.pil_image = image
 
         # further processing for ti2v task
-        if fastvideo_args.pipeline_config.ti2v_task and batch.pil_image is not None:
+        if (fastvideo_args.pipeline_config.ti2v_task
+                or fastvideo_args.pipeline_config.is_causal
+            ) and batch.pil_image is not None:
             img = batch.pil_image
-            ih, iw = img.height, img.width
-            patch_size = fastvideo_args.pipeline_config.dit_config.arch_config.patch_size
-            vae_stride = fastvideo_args.pipeline_config.vae_config.arch_config.scale_factor_spatial
-            dh, dw = patch_size[1] * vae_stride, patch_size[2] * vae_stride
-            max_area = 704 * 1280
-            ow, oh = best_output_size(iw, ih, dw, dh, max_area)
+            # ih, iw = img.height, img.width
+            # patch_size = fastvideo_args.pipeline_config.dit_config.arch_config.patch_size
+            # vae_stride = fastvideo_args.pipeline_config.vae_config.arch_config.scale_factor_spatial
+            # dh, dw = patch_size[1] * vae_stride, patch_size[2] * vae_stride
+            # max_area = 720 * 1280
+            # ow, oh = best_output_size(iw, ih, dw, dh, max_area)
 
-            scale = max(ow / iw, oh / ih)
-            img = img.resize((round(iw * scale), round(ih * scale)),
-                             Image.LANCZOS)
-            logger.info("resized img height: %s, img width: %s", img.height,
-                        img.width)
-
-            # center-crop
-            x1 = (img.width - ow) // 2
-            y1 = (img.height - oh) // 2
-            img = img.crop((x1, y1, x1 + ow, y1 + oh))
-            assert img.width == ow and img.height == oh
+            # scale = max(ow / iw, oh / ih)
+            # img = img.resize((round(iw * scale), round(ih * scale)),
+            #                  Image.LANCZOS)
+            # logger.info("resized img height: %s, img width: %s", img.height,
+            #             img.width)
 
+            # # center-crop
+            # x1 = (img.width - ow) // 2
+            # y1 = (img.height - oh) // 2
+            # img = img.crop((x1, y1, x1 + ow, y1 + oh))
+            # assert img.width == ow and img.height == oh
+            logger.info("img height: %s, img width: %s", img.height, img.width)
+            oh = img.height
+            ow = img.width
             # to tensor
             img = TF.to_tensor(img).sub_(0.5).div_(0.5).to(
                 self.device).unsqueeze(1)

fastvideo/training/distillation_pipeline.py

@@ -729,9 +729,6 @@ class DistillationPipeline(TrainingPipeline):
                                      self.num_train_timestep, [1],
                                      device=self.device,
                                      dtype=torch.long)
-            world_group = get_world_group()
-            if world_group.world_size > 1:
-                world_group.broadcast(timestep, src=0)
 
             timestep = shift_timestep(
                 timestep,
@@ -844,9 +841,6 @@ class DistillationPipeline(TrainingPipeline):
                                             self.num_train_timestep, [1],
                                             device=self.device,
                                             dtype=torch.long)
-        world_group = get_world_group()
-        if world_group.world_size > 1:
-            world_group.broadcast(fake_score_timestep, src=0)
 
         fake_score_timestep = shift_timestep(
             fake_score_timestep,

prompts/mixkit_i2v.jsonl

@@ -0,0 +1,66 @@
+[
+    {
+        "prompt": "Young man skating with a skateboard on the ramps with graffiti of a park with trees, on a sunny day.", 
+        "image_path": "images/mixkit-boy-skating-with-a-skateboard-in-a-park-with-ramps-34389.png"
+    },
+    {
+        "prompt": "In the midst of the joyous New Year's Eve celebration, the cheerful group of friends, their spirits lifted by the festivities, decides to immortalize the moment with a vibrant snapshot", 
+        "image_path": "images/mixkit-a-cheerful-group-of-friends-celebrate-new-years-eve-and-51525.png"
+    },
+    {
+        "prompt": "A man and a woman playing in a field with grass, during a bright afternoon, while cars pass by in the distance.", 
+        "image_path": "images/mixkit-a-cute-couple-playing-on-the-grass-4688.png"
+    },
+    {
+        "prompt": "Aerial view of a rocky mountain in the forest at a sunny day drone flight footage", 
+        "image_path": "images/mixkit-aerial-view-of-a-rocky-mountain-in-the-forest-50589.png"
+    },
+    {
+        "prompt": "A little girl wearing a pink security helmet and denim overall discovers the art of cycling amidst the serene park, as the camera captures her graceful progress.", 
+        "image_path": "images/mixkit-a-little-girl-cruises-through-the-forest-path-on-her-50088.png"
+    },
+    {
+        "prompt": "Aerial shot of a beach shore with sea waves. Big rocks on the sand at an alone beach.", 
+        "image_path": "images/mixkit-aerial-shot-of-a-beach-with-sea-waves-1087.png"
+    },
+    {
+        "prompt": "Young woman cleaning her house decorated with plants and decorations, while dancing happily to music in her headphones.", 
+        "image_path": "images/mixkit-woman-cleaning-her-house-dancing-happy-43379.png"
+    },
+    {
+        "prompt": "Aerial tour in a meadow surrounded by hills on the horizon, while some birds fly low over a lake.", 
+        "image_path": "images/mixkit-birds-flying-low-over-a-lake-in-a-meadow-41417.png"
+    },
+    {
+        "prompt": "In the video, a lone rider guides a majestic horse across an expansive, open field as the sun sets in the background. The rider, dressed in a classic blue shirt and wide-brimmed hat, sits confidently in the saddle, silhouetted against the warm glow of the evening sky. The horse moves gracefully, its mane and tail flowing with each step, creating a sense of harmony between horse and rider. Surrounding the pair, towering trees form a natural border, their leaves gently rustling in the breeze. The shadows lengthen on the ground, accentuating the serene and timeless feel of the scene. The distant hills and wooden fences frame the horizon, adding depth to the tranquil landscape. A few horses graze peacefully in the background, blending into the pastoral setting. The overall ambiance evokes a sense of calmness and quietude, capturing a perfect moment in the golden light of dusk.", 
+        "image_path": "images/mixkit-a-rancher-riding-a-horse-at-sunset-1143.png"
+    },
+    {
+        "prompt": "In the video, a martial artist dressed in a traditional white uniform with a black belt demonstrates a series of precise movements against a stark black background. The individual gracefully transitions between stances, embodying a sense of focused discipline and control. Each motion is executed with a deliberate pace, showcasing the fluidity of martial arts techniques. The soft lighting creates subtle highlights on the uniform, adding depth to the figure as it moves. The practitioner begins with an open-hand pose, feet firmly grounded, gradually shifting to a powerful forward punch. The fluidity of the sequence displays a mastery of balance and poise. Every trajectory of the limbs is precise and deliberate, capturing the elegance and strength of martial arts. The serene, isolated setting enhances the intensity and concentration of the practitioner. This visual presentation is an elegant interplay of motion and stillness, displaying the art form's discipline and grace.", 
+        "image_path": "images/mixkit-a-young-man-practicing-his-karate-moves-49635.png"
+    },
+    {
+        "prompt": "In a serene and softly lit yoga studio, three individuals engage in a yoga session, each performing an upward-facing stretch. The central figure is a woman with shoulder-length brown hair, dressed in a light cropped top and green leggings, her posture reflecting grace and concentration. To her right, another participant, a woman in a purple outfit, mirrors the pose with equal poise. On her left, a person with a bun focuses intently, supported slightly by yoga blocks beneath their hands. The warm-colored wooden floor contrasts soothingly with the soft pastel mural on the back wall, featuring an abstract design and partial visage of a serene face. Natural light floods the space from a large window on the right, where lush greens peek through, adding an element of tranquility. In the corner of the room, a collection of meditation instruments, including a gong and a Buddha statue, subtly frame the peaceful setting. The mood is calm yet focused, as all three participants are deeply engaged in their practice. The scene combines elements of balance, harmony, and a shared journey towards mindfulness. This depiction captures the essence of a yoga session that blends personal growth with collective experience.", 
+        "image_path": "images/mixkit-small-group-of-people-doing-yoga-together-43730.png"
+    },
+    {
+        "prompt": "In the deep blue expanse of the ocean, two dolphins glide effortlessly, their sleek bodies reflecting the sunlight filtering through the water. The prominent shadows and caustics create a shimmering effect on their skin, capturing the beauty of their natural habitat. Each dolphin moves with a fluid grace, occasionally interacting with gentle nudges, showcasing their playful and social nature. The scene is vibrant and dynamic, with the clear blue background accentuating the dolphins' movements, making it an ideal subject for AI recreation.", 
+        "image_path": "images/mixkit-dolphins-underwater-4133.png"
+    },
+    {
+        "prompt": "A bustling ski slope comes alive with skiers descending a pristine, snow-covered hill, surrounded by towering, snow-draped evergreens. Several figures stand atop the slope, silhouetted against a clear blue sky, preparing to embark on their ski run. The chair lift on the right continuously drops off eager adventurers, adding to the excitement at the hilltop. Each skier, clad in colorful winter gear, carves distinct paths into the textured snow as they weave their way down. The interplay of sunlight and shadows accentuates the myriad tracks etched into the slope, creating a dynamic visual rhythm. The scene captures a vibrant winter wonderland, full of action and the thrill of a perfect ski day.", 
+        "image_path": "images/mixkit-skiers-on-a-snowy-slope-3327.png"
+    },
+    {
+        "prompt": "A determined climber is scaling a massive rock face, showcasing exceptional strength and skill. The person, clad in a teal shirt and dark pants, climbs with precision, their movements measured and deliberate. They are secured by climbing gear, which includes ropes and a harness, emphasizing their commitment to safety. The rugged texture of the sandy-colored rock provides an imposing backdrop, adding drama and scale to the climb. In the distance, other large rock formations and sparse vegetation can be seen under a bright, overcast sky, contributing to the natural and adventurous atmosphere. The scene captures a moment of focus and challenge, highlighting the climber's tenacity and the breathtaking environment.",
+        "image_path": "images/mixkit-alpinist-climbing-a-huge-rock-in-a-desert-43306.png"
+    },
+    {
+        "prompt": "A silver SUV drives along a winding, snow-covered mountain road, with dense pine trees blanketed in snow lining both sides. The scene is serene, with the vehicle moving smoothly, possibly on a winter journey or vacation. As the SUV disappears around the bend, another, darker SUV follows, creating a sense of motion and perspective on the snow-dusted asphalt. The towering, snow-laden rock formation to the right contrasts with the dark green of the pines, highlighting the peacefulness of the wintry landscape.",
+        "image_path": "images/mixkit-curve-on-a-snowy-forest-road-3317.png"
+    },
+    {
+        "prompt": "A solitary boat glides across the expansive, tranquil expanse of a serene lake. The vessel leaves a gentle wake behind, creating delicate ripples across the mirror-like surface. The water appears a rich shade of teal, seamlessly blending with the sky at the horizon. Silhouettes of distant trees are faintly visible, creating a picturesque backdrop that enhances the solitary journey of the boat. The sky is a calm gradient, shifting from soft oranges near the shore to the pale blues above. In the distance, a few slender poles emerge from the water, remnants of an old structure or natural formation. The mood of the scene is one of peace and solitude, with the boat journeying steadily through the quiet landscape. There is a sense of endless possibilities as the boat moves toward the unseen beyond the frame. The simplicity and stillness of the scene invite contemplation and reflection, encapsulating a perfect moment of quietude on the water.",
+        "image_path": "images/mixkit-motorboat-on-a-large-lake-with-turquoise-blue-waters-4996.png"
+    }
+]