[Enhancement]remove duplicate video preprocess in Wan2.2 pipeline (#2963)

Signed-off-by: bjf-frz <frz123db@gmail.com>

tests/diffusion/models/wan2_2/test_wan22_i2v_pipeline.py

@@ -44,7 +44,6 @@ def test_i2v_preprocess_requires_image_and_resizes_to_480p_aspect() -> None:
     assert result.sampling_params.height == 432
     assert result.sampling_params.width == 880
     assert prompt["multi_modal_data"]["image"].size == (880, 432)
-    assert prompt["additional_information"]["preprocessed_image"].shape[-2:] == (432, 880)
 
     missing_image = SimpleNamespace(
         prompts=[{"prompt": "p", "multi_modal_data": {}}],

tests/diffusion/models/wan2_2/test_wan22_ti2v_pipeline.py

@@ -41,7 +41,6 @@ def test_ti2v_preprocess_uses_720p_area_for_image_condition() -> None:
     assert result.sampling_params.height == 672
     assert result.sampling_params.width == 1344
     assert result.prompts[0]["multi_modal_data"]["image"].size == (1344, 672)
-    assert result.prompts[0]["additional_information"]["preprocessed_image"].shape[-2:] == (672, 1344)
 
 
 def test_ti2v_diffuse_without_image_condition_expands_patch_timesteps() -> None:

vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2.py

@@ -190,9 +190,6 @@ def get_wan22_pre_process_func(
 ):
     """Pre-process function for Wan2.2: optionally load and resize input image for I2V mode."""
     import numpy as np
-    from diffusers.video_processor import VideoProcessor
-
-    video_processor = VideoProcessor(vae_scale_factor=8)
 
     def pre_process_func(request: OmniDiffusionRequest) -> OmniDiffusionRequest:
         for i, prompt in enumerate(request.prompts):
@@ -236,10 +233,6 @@ def get_wan22_pre_process_func(
             )
             prompt["multi_modal_data"]["image"] = image  # type: ignore # key existence already checked above
 
-            # Preprocess for VAE
-            prompt["additional_information"]["preprocessed_image"] = video_processor.preprocess(
-                image, height=request.sampling_params.height, width=request.sampling_params.width
-            )
             request.prompts[i] = prompt
         return request
 

vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2_i2v.py

@@ -80,9 +80,6 @@ def get_wan22_i2v_pre_process_func(
     od_config: OmniDiffusionConfig,
 ):
     """Pre-process function for I2V: load and resize input image."""
-    from diffusers.video_processor import VideoProcessor
-
-    video_processor = VideoProcessor(vae_scale_factor=8)
 
     def pre_process_func(request: OmniDiffusionRequest) -> OmniDiffusionRequest:
         for i, prompt in enumerate(request.prompts):
@@ -128,10 +125,6 @@ def get_wan22_i2v_pre_process_func(
             )
             prompt["multi_modal_data"]["image"] = image  # type: ignore # key existence already checked above
 
-            # Preprocess for VAE
-            prompt["additional_information"]["preprocessed_image"] = video_processor.preprocess(
-                image, height=request.sampling_params.height, width=request.sampling_params.width
-            )
             request.prompts[i] = prompt
         return request
 

vllm_omni/diffusion/models/wan2_2/pipeline_wan2_2_ti2v.py

@@ -87,9 +87,6 @@ def get_wan22_ti2v_pre_process_func(
     od_config: OmniDiffusionConfig,
 ):
     """Pre-process function for TI2V: optionally load and resize input image."""
-    from diffusers.video_processor import VideoProcessor
-
-    video_processor = VideoProcessor(vae_scale_factor=8)
 
     def pre_process_func(request: OmniDiffusionRequest) -> OmniDiffusionRequest:
         for i, prompt in enumerate(request.prompts):
@@ -135,10 +132,6 @@ def get_wan22_ti2v_pre_process_func(
             )
             prompt["multi_modal_data"]["image"] = image  # type: ignore # key existence already checked above
 
-            # Preprocess for VAE
-            prompt["additional_information"]["preprocessed_image"] = video_processor.preprocess(
-                image, height=request.sampling_params.height, width=request.sampling_params.width
-            )
             request.prompts[i] = prompt
         return request