diff --git a/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py b/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py
index 669b2b691..5579ababe 100644
--- a/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py
+++ b/examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py
@@ -26,7 +26,7 @@ def main():
     )
 
     sampling_param = SamplingParam.from_pretrained("FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers")
-    sampling_param.num_frames = 73
+    sampling_param.num_frames = 81
     sampling_param.width = 832
     sampling_param.height = 480
     sampling_param.seed = 1000
diff --git a/fastvideo/pipelines/stages/causal_denoising.py b/fastvideo/pipelines/stages/causal_denoising.py
index f97eb8291..777314547 100644
--- a/fastvideo/pipelines/stages/causal_denoising.py
+++ b/fastvideo/pipelines/stages/causal_denoising.py
@@ -400,6 +400,10 @@ class CausalDMDDenosingStage(DenoisingStage):
 
                 start_index += current_num_frames
 
+        if boundary_timestep is not None:
+            num_frames_to_remove = self.num_frames_per_block - 1
+            latents = latents[:, :, :-num_frames_to_remove, :, :]
+
         batch.latents = latents
         return batch
 
@@ -490,4 +494,4 @@ class CausalDMDDenosingStage(DenoisingStage):
         result.add_check(
             "negative_prompt_embeds", batch.negative_prompt_embeds, lambda x:
             not batch.do_classifier_free_guidance or V.list_not_empty(x))
-        return result
+        return result
\ No newline at end of file
diff --git a/fastvideo/pipelines/stages/input_validation.py b/fastvideo/pipelines/stages/input_validation.py
index 3d263673a..100199ec8 100644
--- a/fastvideo/pipelines/stages/input_validation.py
+++ b/fastvideo/pipelines/stages/input_validation.py
@@ -5,6 +5,7 @@ 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
@@ -13,6 +14,7 @@ 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__)
 
@@ -108,27 +110,25 @@ class InputValidationStage(PipelineStage):
                 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 = 720 * 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 = 480 * 832
+            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)
+            scale = max(ow / iw, oh / ih)
+            img = img.resize((round(iw * scale), round(ih * scale)),
+                             Image.LANCZOS)
+
+            # 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("final processed 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)