[Misc] Build canonical image task prompts (#6049)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-08-12 08:30:34 +08:00
1 parent 58007c0084
commit 8b0a6779d4
14 files changed
+188 -266

No files matched your search

@@ -63,7 +63,9 @@ from vllm_omni.inputs.data import OmniDiffusionSamplingParams
from vllm_omni.lora.request import LoRARequest
from vllm_omni.lora.utils import stable_lora_int_id
from vllm_omni.model_extras import (
build_image_to_video_prompt,
build_image_to_video_prompt as build_model_image_to_video_prompt,
)
from vllm_omni.model_extras import (
get_extra_body_params,
get_model_class_name,
)
@@ -85,6 +87,22 @@ def parse_json_object(value: str, flag_name: str = "argument") -> dict[str, Any]
parse_profiler_config = functools.partial(parse_json_object, flag_name="--profiler-config")
def build_image_to_video_prompt(
prompt: str,
negative_prompt: str | None,
media_inputs: dict[str, Any],
) -> dict[str, Any]:
"""Build the canonical request envelope for the shared I2V example."""
result: dict[str, Any] = {
"prompt": prompt,
"modalities": ["video"],
"multi_modal_data": media_inputs,
}
if negative_prompt is not None:
result["negative_prompt"] = negative_prompt
return result
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description=(
@@ -566,10 +584,13 @@ def main():
# Preserve the historical empty-prompt behavior for non-LTX examples.
negative_prompt = ""
prompt_dict = build_image_to_video_prompt(
model_class_name=model_class_name,
prompt=args.prompt,
negative_prompt=negative_prompt,
media_inputs=media_inputs,
)
prompt_dict = build_model_image_to_video_prompt(
model_class_name=model_class_name,
prompt=prompt_dict,
height=height,
width=width,
num_frames=num_frames,