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

Signed-off-by: bjf-frz <frz123db@gmail.com>
This commit is contained in:
bjf-frz authored and GitHub committed 2026-04-21 20:33:09 +08:00
1 parent b001151e0d
commit 5f029ee4d5
5 files changed
-23

No files matched your search

@@ -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
@@ -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
@@ -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